From a8e87d9abeb022882f2e0c3591f6f6646a3174d9 Mon Sep 17 00:00:00 2001 From: meadej Date: Fri, 10 Mar 2023 12:37:46 -0500 Subject: [PATCH 1/4] Camera updates to save metadata --- axis-ptz/camera.py | 159 +++++++++++++++++++++++++++++++-------------- 1 file changed, 112 insertions(+), 47 deletions(-) diff --git a/axis-ptz/camera.py b/axis-ptz/camera.py index e28c5c9..ac3cf7e 100755 --- a/axis-ptz/camera.py +++ b/axis-ptz/camera.py @@ -81,15 +81,46 @@ currentPlane = None -camera_latitude = None -camera_longitude = None -camera_altitude = None camera_lead = None include_age = strtobool(os.getenv("INCLUDE_AGE", "True")) def calculate_bearing_correction(b): return (b + cameraBearingCorrection) % 360 +def _format_file_save_filepath(file_extension: str = None): + """ + A method for formatting the filepath of an image based off of the current state of global variables. + For use in JPEG, BMP, and JSON saving. + Args: + file_extension: The desired file extension with leading dot (.jpg, .bmp) + Returns: + A String object representing the filepath without the filetype extension. + """ + captureDir = None + + if args.flat_file_structure: + captureDir = "capture" + else: + captureDir = "capture{}".format(currentPlane["type"]) + try: + os.makedirs(captureDir) + except OSError as e: + if e.errno != errno.EEXIST: + raise # This was not a "directory exist" error.. + filepath = "{}/{}_{}_{}_{}_{}".format( + captureDir, + currentPlane["icao24"], + int(bearing), + int(elevation), + int(distance3d), + datetime.now().strftime("%Y-%m-%d-%H-%M-%S"), + ) + + if file_extension is not None: + filepath = filepath + str(file_extension) + + return str(filepath) + # Copied from VaPix/Sensecam to customize the folder structure for saving pictures def get_jpeg_request(): # 5.2.4.1 @@ -139,25 +170,7 @@ def get_jpeg_request(): # 5.2.4.1 disk_time = datetime.now() if resp.status_code == 200: - captureDir = None - - if args.flat_file_structure: - captureDir = "capture/" - else: - captureDir = "capture/{}".format(currentPlane["type"]) - try: - os.makedirs(captureDir) - except OSError as e: - if e.errno != errno.EEXIST: - raise # This was not a "directory exist" error.. - filename = "{}/{}_{}_{}_{}_{}.jpg".format( - captureDir, - currentPlane["icao24"], - int(bearing), - int(elevation), - int(distance3d), - datetime.now().strftime("%Y-%m-%d-%H-%M-%S"), - ) + filename = _format_file_save_filepath(file_extension=".jpg") # Original with open(filename, "wb") as var: @@ -224,20 +237,7 @@ def get_bmp_request(): # 5.2.4.1 ) if resp.status_code == 200: - captureDir = "capture/{}".format(currentPlane["type"]) - try: - os.makedirs(captureDir) - except OSError as e: - if e.errno != errno.EEXIST: - raise # This was not a "directory exist" error.. - filename = "{}/{}_{}_{}_{}_{}.bmp".format( - captureDir, - currentPlane["icao24"], - int(bearing), - int(elevation), - int(distance3d), - datetime.now().strftime("%Y-%m-%d-%H-%M-%S"), - ) + filename = _format_file_save_filepath(file_extension=".bmp") with open(filename, "wb") as var: var.write(resp.content) @@ -522,8 +522,50 @@ def calculateCameraPositionA(): ) cameraPan = calculate_bearing_correction(cameraPan) +def get_json_request(): + """ + A method to save the metadata of the currently-tracking aircraft and the camera to a JSON file alongside BMP and + JPEG requests. + Args: + None + Returns: + A dictionary containing the contents os the JSON metadata file. + """ + image_filepath = _format_file_save_filepath(file_extension=".jpg") + filepath = os.path.join( + logging_directory, + os.path.basename(_format_file_save_filepath(file_extension=".json")) + ) + + file_content_dictionary = { + "timestamp": datetime.now().strftime("%Y-%m-%d-%H-%M-%S"), + "imagefile": image_filepath, + "camera": { + "bearing": bearing, + "zoom": cameraZoom, + "pan": cameraPan, + "tilt": cameraTilt, + "lat": camera_latitude, + "long": camera_longitude, + "alt": camera_altitude + }, + "aircraft": { + "lat": currentPlane["lat"], + "long": currentPlane["lon"], + "alt": currentPlane["altitude"] + } + } + + try: + with open(filepath, "w") as fh: + fh.write(json.dumps(file_content_dictionary)) + except Exception as e: + print("Error saving JSON log - " + str(e)) + + return file_content_dictionary -def moveCamera(ip, username, password): + +def moveCamera(ip, username, password, mqtt_client): movePeriod = 100 # milliseconds moveTimeout = datetime.now() @@ -582,6 +624,13 @@ def moveCamera(ip, username, password): if captureTimeout <= datetime.now(): time.sleep(cameraDelay) get_jpeg_request() + capture_metadata = get_json_request() + mqtt_client.publish( + "skyscan/captures/data", + json.dumps(capture_metadata), + 0, + False + ) captureTimeout = captureTimeout + timedelta( milliseconds=capturePeriod ) @@ -774,6 +823,7 @@ def main(): global cameraConfig global flight_topic global object_topic + global logging_directory global Active parser = argparse.ArgumentParser(description="An MQTT based camera controller") @@ -836,7 +886,19 @@ def main(): help="The zoom setting for the camera (0-9999)", default=9999, ) - parser.add_argument("-v", "--verbose", action="store_true", help="Verbose output") + parser.add_argument( + "-l", + "--log-directory", + type=str, + help="The directory for the camera to write capture logs to.", + default="/flash/processed/log" + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Verbose output" + ) parser.add_argument( "-f", "--flat-file-structure", @@ -897,15 +959,8 @@ def main(): camera_lead = args.camera_lead # cameraConfig = vapix_config.CameraConfiguration(args.axis_ip, args.axis_username, args.axis_password) - cameraMove = threading.Thread( - target=moveCamera, - args=[args.axis_ip, args.axis_username, args.axis_password], - daemon=True, - ) - cameraMove.start() - # Sleep for a bit so we're not hammering the HAT with updates - delay = 0.005 - time.sleep(delay) + logging_directory = args.log_directory + flight_topic = args.mqtt_flight_topic object_topic = args.mqtt_object_topic print( @@ -933,6 +988,16 @@ def main(): False, ) + cameraMove = threading.Thread( + target=moveCamera, + args=[args.axis_ip, args.axis_username, args.axis_password, client], + daemon=True, + ) + cameraMove.start() + # Sleep for a bit so we're not hammering the HAT with updates + delay = 0.005 + time.sleep(delay) + ############################################# ## Main Loop ## ############################################# From c3698e0649209093f9ea2bc4116b95f126cf580a Mon Sep 17 00:00:00 2001 From: meadej Date: Fri, 10 Mar 2023 14:08:11 -0500 Subject: [PATCH 2/4] Removed edge-detect capability. Moved to own repository --- .github/workflows/dockerbuild.yml | 7 +- edge-detect/README.md | 15 - edge-detect/ai/Dockerfile | 35 - edge-detect/ai/LICENSE.md | 674 -------------- edge-detect/ai/README.md | 1 - edge-detect/ai/datasets2.py | 1361 ----------------------------- edge-detect/ai/sort.py | 245 ------ edge-detect/docker-compose.yml | 15 - 8 files changed, 4 insertions(+), 2349 deletions(-) delete mode 100644 edge-detect/README.md delete mode 100644 edge-detect/ai/Dockerfile delete mode 100644 edge-detect/ai/LICENSE.md delete mode 100644 edge-detect/ai/README.md delete mode 100644 edge-detect/ai/datasets2.py delete mode 100644 edge-detect/ai/sort.py delete mode 100644 edge-detect/docker-compose.yml diff --git a/.github/workflows/dockerbuild.yml b/.github/workflows/dockerbuild.yml index a5fea70..bf17efd 100644 --- a/.github/workflows/dockerbuild.yml +++ b/.github/workflows/dockerbuild.yml @@ -39,8 +39,9 @@ jobs: - name: Build Images env: # Every folder in the repo that has a Dockerfile within it, comma separated - DOCKERFOLDERS: "edge-detect/ai,tracker,piaware,pan-tilt-pi,notebook-server,egi,axis-ptz" + DOCKERFOLDERS: "tracker,piaware,pan-tilt-pi,notebook-server,egi,axis-ptz" PROJECT_NAME: "skyscan" + REPO_NAME: "${{ secrets.DOCKER_NAMESPACE }}" run: | IFS="," read -ra ARR <<< "$DOCKERFOLDERS" @@ -52,7 +53,7 @@ jobs: echo "Building $folder" echo $SUBNAME docker buildx build "$folder" --push \ - --tag iqtlabs/$PROJECT_NAME-$SUBNAME:latest \ - --tag iqtlabs/$PROJECT_NAME-$SUBNAME:${{ steps.get_tag.outputs.IMAGE_TAG }} \ + --tag $REPO_NAME/$PROJECT_NAME-$SUBNAME:latest \ + --tag $REPO_NAME/$PROJECT_NAME-$SUBNAME:${{ steps.get_tag.outputs.IMAGE_TAG }} \ --platform linux/arm64,linux/amd64 done diff --git a/edge-detect/README.md b/edge-detect/README.md deleted file mode 100644 index ebad753..0000000 --- a/edge-detect/README.md +++ /dev/null @@ -1,15 +0,0 @@ -# Aircraft Image Detection System # - -## Edge Detection Overview ## -This edge detection system is designed to digest images captured by the SkyScan system and determine whether there is an aircraft fully in frame or not. A lack of aircraft in the image can occur if the aircraft the system was tracking when the image was taken was occluded (e.g., behind a building, tree, etc.) or too distant. - -## Installation ## -The edge detection system uses docker compose and runs two services, one to move files out of the file structure generated by the SkyScan system into a central location (the `filemover` service) and the other to perform aircraft localization and detection (the `ai` service). - -In order to properly run the localization service, a weights file (commonly `weights.pt` or `localizer.pt`) must be placed in the `/weights` directory, which will then be mounted inside of the container. - -## Operation ## - -Both services can be launched using the command `docker compose up` if run in this `edge-detect` directory. The ai service will then begin taking raw images from `/flash/unprocessed` (placed there by the filemover service) or another volume specified in its place in the Dockerfile included in the `ai` folder. It then sorts them into `plane` and `noplane` folders also located, with the current configuration, under `/flash`. - -Additionally, the location of planes within each image is saved to JSON files under `/flash/log`. \ No newline at end of file diff --git a/edge-detect/ai/Dockerfile b/edge-detect/ai/Dockerfile deleted file mode 100644 index c9a1c6a..0000000 --- a/edge-detect/ai/Dockerfile +++ /dev/null @@ -1,35 +0,0 @@ -FROM python:3.9.15-bullseye -LABEL org.label-schema.schema-version 1.0 -LABEL org.label-schema.vendor IQT Labs -LABEL org.label-schema.name SkyScan Edge AI - -# Dependencies -RUN apt-get update && apt-get upgrade --assume-yes && apt-get install -y zip htop screen libgl1-mesa-glx -RUN python --version - -# YOLOv7 -RUN git clone https://github.com/WongKinYiu/yolov7.git /yolov7 -WORKDIR /yolov7 -RUN sed -i '/thop/d' requirements.txt -RUN sed -i '/torchvision/d' requirements.txt -RUN sed -i '/torch/d' requirements.txt - -RUN pip install torch==1.8.1 -f https://download.pytorch.org/whl/torch/ -RUN pip install torchvision==0.9.1 -f https://download.pytorch.org/whl/torchvision/ -RUN pip install -r requirements.txt - -# SkyScan Edge AI -ADD sort.py ./ -ADD datasets2.py utils/ -RUN mkdir /data - -# Run -CMD ["bash", "-c", "python sort.py \ ---weights ../data/weights/localizer.pt \ ---agnostic-nms --nosave --conf 0.25 --img-size 640 --device cpu \ ---source-dir ../data/tosort \ ---plane-dir ../data/plane \ ---noplane-dir ../data/noplane \ ---log-dir ../data/log \ ---save-json" ] - diff --git a/edge-detect/ai/LICENSE.md b/edge-detect/ai/LICENSE.md deleted file mode 100644 index f288702..0000000 --- a/edge-detect/ai/LICENSE.md +++ /dev/null @@ -1,674 +0,0 @@ - GNU GENERAL PUBLIC LICENSE - Version 3, 29 June 2007 - - Copyright (C) 2007 Free Software Foundation, Inc. - Everyone is permitted to copy and distribute verbatim copies - of this license document, but changing it is not allowed. - - Preamble - - The GNU General Public License is a free, copyleft license for -software and other kinds of works. - - The licenses for most software and other practical works are designed -to take away your freedom to share and change the works. By contrast, -the GNU General Public License is intended to guarantee your freedom to -share and change all versions of a program--to make sure it remains free -software for all its users. We, the Free Software Foundation, use the -GNU General Public License for most of our software; it applies also to -any other work released this way by its authors. You can apply it to -your programs, too. - - When we speak of free software, we are referring to freedom, not -price. Our General Public Licenses are designed to make sure that you -have the freedom to distribute copies of free software (and charge for -them if you wish), that you receive source code or can get it if you -want it, that you can change the software or use pieces of it in new -free programs, and that you know you can do these things. - - To protect your rights, we need to prevent others from denying you -these rights or asking you to surrender the rights. Therefore, you have -certain responsibilities if you distribute copies of the software, or if -you modify it: responsibilities to respect the freedom of others. - - For example, if you distribute copies of such a program, whether -gratis or for a fee, you must pass on to the recipients the same -freedoms that you received. You must make sure that they, too, receive -or can get the source code. And you must show them these terms so they -know their rights. - - Developers that use the GNU GPL protect your rights with two steps: -(1) assert copyright on the software, and (2) offer you this License -giving you legal permission to copy, distribute and/or modify it. - - For the developers' and authors' protection, the GPL clearly explains -that there is no warranty for this free software. For both users' and -authors' sake, the GPL requires that modified versions be marked as -changed, so that their problems will not be attributed erroneously to -authors of previous versions. - - Some devices are designed to deny users access to install or run -modified versions of the software inside them, although the manufacturer -can do so. This is fundamentally incompatible with the aim of -protecting users' freedom to change the software. The systematic -pattern of such abuse occurs in the area of products for individuals to -use, which is precisely where it is most unacceptable. Therefore, we -have designed this version of the GPL to prohibit the practice for those -products. If such problems arise substantially in other domains, we -stand ready to extend this provision to those domains in future versions -of the GPL, as needed to protect the freedom of users. - - Finally, every program is threatened constantly by software patents. -States should not allow patents to restrict development and use of -software on general-purpose computers, but in those that do, we wish to -avoid the special danger that patents applied to a free program could -make it effectively proprietary. To prevent this, the GPL assures that -patents cannot be used to render the program non-free. - - The precise terms and conditions for copying, distribution and -modification follow. - - TERMS AND CONDITIONS - - 0. Definitions. - - "This License" refers to version 3 of the GNU General Public License. - - "Copyright" also means copyright-like laws that apply to other kinds of -works, such as semiconductor masks. - - "The Program" refers to any copyrightable work licensed under this -License. Each licensee is addressed as "you". "Licensees" and -"recipients" may be individuals or organizations. - - To "modify" a work means to copy from or adapt all or part of the work -in a fashion requiring copyright permission, other than the making of an -exact copy. The resulting work is called a "modified version" of the -earlier work or a work "based on" the earlier work. - - A "covered work" means either the unmodified Program or a work based -on the Program. - - To "propagate" a work means to do anything with it that, without -permission, would make you directly or secondarily liable for -infringement under applicable copyright law, except executing it on a -computer or modifying a private copy. Propagation includes copying, -distribution (with or without modification), making available to the -public, and in some countries other activities as well. - - To "convey" a work means any kind of propagation that enables other -parties to make or receive copies. Mere interaction with a user through -a computer network, with no transfer of a copy, is not conveying. - - An interactive user interface displays "Appropriate Legal Notices" -to the extent that it includes a convenient and prominently visible -feature that (1) displays an appropriate copyright notice, and (2) -tells the user that there is no warranty for the work (except to the -extent that warranties are provided), that licensees may convey the -work under this License, and how to view a copy of this License. If -the interface presents a list of user commands or options, such as a -menu, a prominent item in the list meets this criterion. - - 1. Source Code. - - The "source code" for a work means the preferred form of the work -for making modifications to it. "Object code" means any non-source -form of a work. - - A "Standard Interface" means an interface that either is an official -standard defined by a recognized standards body, or, in the case of -interfaces specified for a particular programming language, one that -is widely used among developers working in that language. - - The "System Libraries" of an executable work include anything, other -than the work as a whole, that (a) is included in the normal form of -packaging a Major Component, but which is not part of that Major -Component, and (b) serves only to enable use of the work with that -Major Component, or to implement a Standard Interface for which an -implementation is available to the public in source code form. A -"Major Component", in this context, means a major essential component -(kernel, window system, and so on) of the specific operating system -(if any) on which the executable work runs, or a compiler used to -produce the work, or an object code interpreter used to run it. - - The "Corresponding Source" for a work in object code form means all -the source code needed to generate, install, and (for an executable -work) run the object code and to modify the work, including scripts to -control those activities. However, it does not include the work's -System Libraries, or general-purpose tools or generally available free -programs which are used unmodified in performing those activities but -which are not part of the work. For example, Corresponding Source -includes interface definition files associated with source files for -the work, and the source code for shared libraries and dynamically -linked subprograms that the work is specifically designed to require, -such as by intimate data communication or control flow between those -subprograms and other parts of the work. - - The Corresponding Source need not include anything that users -can regenerate automatically from other parts of the Corresponding -Source. - - The Corresponding Source for a work in source code form is that -same work. - - 2. Basic Permissions. - - All rights granted under this License are granted for the term of -copyright on the Program, and are irrevocable provided the stated -conditions are met. This License explicitly affirms your unlimited -permission to run the unmodified Program. The output from running a -covered work is covered by this License only if the output, given its -content, constitutes a covered work. This License acknowledges your -rights of fair use or other equivalent, as provided by copyright law. - - You may make, run and propagate covered works that you do not -convey, without conditions so long as your license otherwise remains -in force. You may convey covered works to others for the sole purpose -of having them make modifications exclusively for you, or provide you -with facilities for running those works, provided that you comply with -the terms of this License in conveying all material for which you do -not control copyright. Those thus making or running the covered works -for you must do so exclusively on your behalf, under your direction -and control, on terms that prohibit them from making any copies of -your copyrighted material outside their relationship with you. - - Conveying under any other circumstances is permitted solely under -the conditions stated below. Sublicensing is not allowed; section 10 -makes it unnecessary. - - 3. Protecting Users' Legal Rights From Anti-Circumvention Law. - - No covered work shall be deemed part of an effective technological -measure under any applicable law fulfilling obligations under article -11 of the WIPO copyright treaty adopted on 20 December 1996, or -similar laws prohibiting or restricting circumvention of such -measures. - - When you convey a covered work, you waive any legal power to forbid -circumvention of technological measures to the extent such circumvention -is effected by exercising rights under this License with respect to -the covered work, and you disclaim any intention to limit operation or -modification of the work as a means of enforcing, against the work's -users, your or third parties' legal rights to forbid circumvention of -technological measures. - - 4. Conveying Verbatim Copies. - - You may convey verbatim copies of the Program's source code as you -receive it, in any medium, provided that you conspicuously and -appropriately publish on each copy an appropriate copyright notice; -keep intact all notices stating that this License and any -non-permissive terms added in accord with section 7 apply to the code; -keep intact all notices of the absence of any warranty; and give all -recipients a copy of this License along with the Program. - - You may charge any price or no price for each copy that you convey, -and you may offer support or warranty protection for a fee. - - 5. Conveying Modified Source Versions. - - You may convey a work based on the Program, or the modifications to -produce it from the Program, in the form of source code under the -terms of section 4, provided that you also meet all of these conditions: - - a) The work must carry prominent notices stating that you modified - it, and giving a relevant date. - - b) The work must carry prominent notices stating that it is - released under this License and any conditions added under section - 7. This requirement modifies the requirement in section 4 to - "keep intact all notices". - - c) You must license the entire work, as a whole, under this - License to anyone who comes into possession of a copy. This - License will therefore apply, along with any applicable section 7 - additional terms, to the whole of the work, and all its parts, - regardless of how they are packaged. This License gives no - permission to license the work in any other way, but it does not - invalidate such permission if you have separately received it. - - d) If the work has interactive user interfaces, each must display - Appropriate Legal Notices; however, if the Program has interactive - interfaces that do not display Appropriate Legal Notices, your - work need not make them do so. - - A compilation of a covered work with other separate and independent -works, which are not by their nature extensions of the covered work, -and which are not combined with it such as to form a larger program, -in or on a volume of a storage or distribution medium, is called an -"aggregate" if the compilation and its resulting copyright are not -used to limit the access or legal rights of the compilation's users -beyond what the individual works permit. Inclusion of a covered work -in an aggregate does not cause this License to apply to the other -parts of the aggregate. - - 6. Conveying Non-Source Forms. - - You may convey a covered work in object code form under the terms -of sections 4 and 5, provided that you also convey the -machine-readable Corresponding Source under the terms of this License, -in one of these ways: - - a) Convey the object code in, or embodied in, a physical product - (including a physical distribution medium), accompanied by the - Corresponding Source fixed on a durable physical medium - customarily used for software interchange. - - b) Convey the object code in, or embodied in, a physical product - (including a physical distribution medium), accompanied by a - written offer, valid for at least three years and valid for as - long as you offer spare parts or customer support for that product - model, to give anyone who possesses the object code either (1) a - copy of the Corresponding Source for all the software in the - product that is covered by this License, on a durable physical - medium customarily used for software interchange, for a price no - more than your reasonable cost of physically performing this - conveying of source, or (2) access to copy the - Corresponding Source from a network server at no charge. - - c) Convey individual copies of the object code with a copy of the - written offer to provide the Corresponding Source. This - alternative is allowed only occasionally and noncommercially, and - only if you received the object code with such an offer, in accord - with subsection 6b. - - d) Convey the object code by offering access from a designated - place (gratis or for a charge), and offer equivalent access to the - Corresponding Source in the same way through the same place at no - further charge. You need not require recipients to copy the - Corresponding Source along with the object code. If the place to - copy the object code is a network server, the Corresponding Source - may be on a different server (operated by you or a third party) - that supports equivalent copying facilities, provided you maintain - clear directions next to the object code saying where to find the - Corresponding Source. Regardless of what server hosts the - Corresponding Source, you remain obligated to ensure that it is - available for as long as needed to satisfy these requirements. - - e) Convey the object code using peer-to-peer transmission, provided - you inform other peers where the object code and Corresponding - Source of the work are being offered to the general public at no - charge under subsection 6d. - - A separable portion of the object code, whose source code is excluded -from the Corresponding Source as a System Library, need not be -included in conveying the object code work. - - A "User Product" is either (1) a "consumer product", which means any -tangible personal property which is normally used for personal, family, -or household purposes, or (2) anything designed or sold for incorporation -into a dwelling. In determining whether a product is a consumer product, -doubtful cases shall be resolved in favor of coverage. For a particular -product received by a particular user, "normally used" refers to a -typical or common use of that class of product, regardless of the status -of the particular user or of the way in which the particular user -actually uses, or expects or is expected to use, the product. A product -is a consumer product regardless of whether the product has substantial -commercial, industrial or non-consumer uses, unless such uses represent -the only significant mode of use of the product. - - "Installation Information" for a User Product means any methods, -procedures, authorization keys, or other information required to install -and execute modified versions of a covered work in that User Product from -a modified version of its Corresponding Source. The information must -suffice to ensure that the continued functioning of the modified object -code is in no case prevented or interfered with solely because -modification has been made. - - If you convey an object code work under this section in, or with, or -specifically for use in, a User Product, and the conveying occurs as -part of a transaction in which the right of possession and use of the -User Product is transferred to the recipient in perpetuity or for a -fixed term (regardless of how the transaction is characterized), the -Corresponding Source conveyed under this section must be accompanied -by the Installation Information. But this requirement does not apply -if neither you nor any third party retains the ability to install -modified object code on the User Product (for example, the work has -been installed in ROM). - - The requirement to provide Installation Information does not include a -requirement to continue to provide support service, warranty, or updates -for a work that has been modified or installed by the recipient, or for -the User Product in which it has been modified or installed. Access to a -network may be denied when the modification itself materially and -adversely affects the operation of the network or violates the rules and -protocols for communication across the network. - - Corresponding Source conveyed, and Installation Information provided, -in accord with this section must be in a format that is publicly -documented (and with an implementation available to the public in -source code form), and must require no special password or key for -unpacking, reading or copying. - - 7. Additional Terms. - - "Additional permissions" are terms that supplement the terms of this -License by making exceptions from one or more of its conditions. -Additional permissions that are applicable to the entire Program shall -be treated as though they were included in this License, to the extent -that they are valid under applicable law. If additional permissions -apply only to part of the Program, that part may be used separately -under those permissions, but the entire Program remains governed by -this License without regard to the additional permissions. - - When you convey a copy of a covered work, you may at your option -remove any additional permissions from that copy, or from any part of -it. (Additional permissions may be written to require their own -removal in certain cases when you modify the work.) You may place -additional permissions on material, added by you to a covered work, -for which you have or can give appropriate copyright permission. - - Notwithstanding any other provision of this License, for material you -add to a covered work, you may (if authorized by the copyright holders of -that material) supplement the terms of this License with terms: - - a) Disclaiming warranty or limiting liability differently from the - terms of sections 15 and 16 of this License; or - - b) Requiring preservation of specified reasonable legal notices or - author attributions in that material or in the Appropriate Legal - Notices displayed by works containing it; or - - c) Prohibiting misrepresentation of the origin of that material, or - requiring that modified versions of such material be marked in - reasonable ways as different from the original version; or - - d) Limiting the use for publicity purposes of names of licensors or - authors of the material; or - - e) Declining to grant rights under trademark law for use of some - trade names, trademarks, or service marks; or - - f) Requiring indemnification of licensors and authors of that - material by anyone who conveys the material (or modified versions of - it) with contractual assumptions of liability to the recipient, for - any liability that these contractual assumptions directly impose on - those licensors and authors. - - All other non-permissive additional terms are considered "further -restrictions" within the meaning of section 10. If the Program as you -received it, or any part of it, contains a notice stating that it is -governed by this License along with a term that is a further -restriction, you may remove that term. If a license document contains -a further restriction but permits relicensing or conveying under this -License, you may add to a covered work material governed by the terms -of that license document, provided that the further restriction does -not survive such relicensing or conveying. - - If you add terms to a covered work in accord with this section, you -must place, in the relevant source files, a statement of the -additional terms that apply to those files, or a notice indicating -where to find the applicable terms. - - Additional terms, permissive or non-permissive, may be stated in the -form of a separately written license, or stated as exceptions; -the above requirements apply either way. - - 8. Termination. - - You may not propagate or modify a covered work except as expressly -provided under this License. Any attempt otherwise to propagate or -modify it is void, and will automatically terminate your rights under -this License (including any patent licenses granted under the third -paragraph of section 11). - - However, if you cease all violation of this License, then your -license from a particular copyright holder is reinstated (a) -provisionally, unless and until the copyright holder explicitly and -finally terminates your license, and (b) permanently, if the copyright -holder fails to notify you of the violation by some reasonable means -prior to 60 days after the cessation. - - Moreover, your license from a particular copyright holder is -reinstated permanently if the copyright holder notifies you of the -violation by some reasonable means, this is the first time you have -received notice of violation of this License (for any work) from that -copyright holder, and you cure the violation prior to 30 days after -your receipt of the notice. - - Termination of your rights under this section does not terminate the -licenses of parties who have received copies or rights from you under -this License. If your rights have been terminated and not permanently -reinstated, you do not qualify to receive new licenses for the same -material under section 10. - - 9. Acceptance Not Required for Having Copies. - - You are not required to accept this License in order to receive or -run a copy of the Program. Ancillary propagation of a covered work -occurring solely as a consequence of using peer-to-peer transmission -to receive a copy likewise does not require acceptance. However, -nothing other than this License grants you permission to propagate or -modify any covered work. These actions infringe copyright if you do -not accept this License. Therefore, by modifying or propagating a -covered work, you indicate your acceptance of this License to do so. - - 10. Automatic Licensing of Downstream Recipients. - - Each time you convey a covered work, the recipient automatically -receives a license from the original licensors, to run, modify and -propagate that work, subject to this License. You are not responsible -for enforcing compliance by third parties with this License. - - An "entity transaction" is a transaction transferring control of an -organization, or substantially all assets of one, or subdividing an -organization, or merging organizations. If propagation of a covered -work results from an entity transaction, each party to that -transaction who receives a copy of the work also receives whatever -licenses to the work the party's predecessor in interest had or could -give under the previous paragraph, plus a right to possession of the -Corresponding Source of the work from the predecessor in interest, if -the predecessor has it or can get it with reasonable efforts. - - You may not impose any further restrictions on the exercise of the -rights granted or affirmed under this License. For example, you may -not impose a license fee, royalty, or other charge for exercise of -rights granted under this License, and you may not initiate litigation -(including a cross-claim or counterclaim in a lawsuit) alleging that -any patent claim is infringed by making, using, selling, offering for -sale, or importing the Program or any portion of it. - - 11. Patents. - - A "contributor" is a copyright holder who authorizes use under this -License of the Program or a work on which the Program is based. The -work thus licensed is called the contributor's "contributor version". - - A contributor's "essential patent claims" are all patent claims -owned or controlled by the contributor, whether already acquired or -hereafter acquired, that would be infringed by some manner, permitted -by this License, of making, using, or selling its contributor version, -but do not include claims that would be infringed only as a -consequence of further modification of the contributor version. For -purposes of this definition, "control" includes the right to grant -patent sublicenses in a manner consistent with the requirements of -this License. - - Each contributor grants you a non-exclusive, worldwide, royalty-free -patent license under the contributor's essential patent claims, to -make, use, sell, offer for sale, import and otherwise run, modify and -propagate the contents of its contributor version. - - In the following three paragraphs, a "patent license" is any express -agreement or commitment, however denominated, not to enforce a patent -(such as an express permission to practice a patent or covenant not to -sue for patent infringement). To "grant" such a patent license to a -party means to make such an agreement or commitment not to enforce a -patent against the party. - - If you convey a covered work, knowingly relying on a patent license, -and the Corresponding Source of the work is not available for anyone -to copy, free of charge and under the terms of this License, through a -publicly available network server or other readily accessible means, -then you must either (1) cause the Corresponding Source to be so -available, or (2) arrange to deprive yourself of the benefit of the -patent license for this particular work, or (3) arrange, in a manner -consistent with the requirements of this License, to extend the patent -license to downstream recipients. "Knowingly relying" means you have -actual knowledge that, but for the patent license, your conveying the -covered work in a country, or your recipient's use of the covered work -in a country, would infringe one or more identifiable patents in that -country that you have reason to believe are valid. - - If, pursuant to or in connection with a single transaction or -arrangement, you convey, or propagate by procuring conveyance of, a -covered work, and grant a patent license to some of the parties -receiving the covered work authorizing them to use, propagate, modify -or convey a specific copy of the covered work, then the patent license -you grant is automatically extended to all recipients of the covered -work and works based on it. - - A patent license is "discriminatory" if it does not include within -the scope of its coverage, prohibits the exercise of, or is -conditioned on the non-exercise of one or more of the rights that are -specifically granted under this License. You may not convey a covered -work if you are a party to an arrangement with a third party that is -in the business of distributing software, under which you make payment -to the third party based on the extent of your activity of conveying -the work, and under which the third party grants, to any of the -parties who would receive the covered work from you, a discriminatory -patent license (a) in connection with copies of the covered work -conveyed by you (or copies made from those copies), or (b) primarily -for and in connection with specific products or compilations that -contain the covered work, unless you entered into that arrangement, -or that patent license was granted, prior to 28 March 2007. - - Nothing in this License shall be construed as excluding or limiting -any implied license or other defenses to infringement that may -otherwise be available to you under applicable patent law. - - 12. No Surrender of Others' Freedom. - - If conditions are imposed on you (whether by court order, agreement or -otherwise) that contradict the conditions of this License, they do not -excuse you from the conditions of this License. If you cannot convey a -covered work so as to satisfy simultaneously your obligations under this -License and any other pertinent obligations, then as a consequence you may -not convey it at all. For example, if you agree to terms that obligate you -to collect a royalty for further conveying from those to whom you convey -the Program, the only way you could satisfy both those terms and this -License would be to refrain entirely from conveying the Program. - - 13. Use with the GNU Affero General Public License. - - Notwithstanding any other provision of this License, you have -permission to link or combine any covered work with a work licensed -under version 3 of the GNU Affero General Public License into a single -combined work, and to convey the resulting work. The terms of this -License will continue to apply to the part which is the covered work, -but the special requirements of the GNU Affero General Public License, -section 13, concerning interaction through a network will apply to the -combination as such. - - 14. Revised Versions of this License. - - The Free Software Foundation may publish revised and/or new versions of -the GNU General Public License from time to time. Such new versions will -be similar in spirit to the present version, but may differ in detail to -address new problems or concerns. - - Each version is given a distinguishing version number. If the -Program specifies that a certain numbered version of the GNU General -Public License "or any later version" applies to it, you have the -option of following the terms and conditions either of that numbered -version or of any later version published by the Free Software -Foundation. If the Program does not specify a version number of the -GNU General Public License, you may choose any version ever published -by the Free Software Foundation. - - If the Program specifies that a proxy can decide which future -versions of the GNU General Public License can be used, that proxy's -public statement of acceptance of a version permanently authorizes you -to choose that version for the Program. - - Later license versions may give you additional or different -permissions. However, no additional obligations are imposed on any -author or copyright holder as a result of your choosing to follow a -later version. - - 15. Disclaimer of Warranty. - - THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY -APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT -HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY -OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, -THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR -PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM -IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF -ALL NECESSARY SERVICING, REPAIR OR CORRECTION. - - 16. Limitation of Liability. - - IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING -WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS -THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY -GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE -USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF -DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD -PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), -EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF -SUCH DAMAGES. - - 17. Interpretation of Sections 15 and 16. - - If the disclaimer of warranty and limitation of liability provided -above cannot be given local legal effect according to their terms, -reviewing courts shall apply local law that most closely approximates -an absolute waiver of all civil liability in connection with the -Program, unless a warranty or assumption of liability accompanies a -copy of the Program in return for a fee. - - END OF TERMS AND CONDITIONS - - How to Apply These Terms to Your New Programs - - If you develop a new program, and you want it to be of the greatest -possible use to the public, the best way to achieve this is to make it -free software which everyone can redistribute and change under these terms. - - To do so, attach the following notices to the program. It is safest -to attach them to the start of each source file to most effectively -state the exclusion of warranty; and each file should have at least -the "copyright" line and a pointer to where the full notice is found. - - - Copyright (C) - - This program is free software: you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation, either version 3 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program. If not, see . - -Also add information on how to contact you by electronic and paper mail. - - If the program does terminal interaction, make it output a short -notice like this when it starts in an interactive mode: - - Copyright (C) - This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. - This is free software, and you are welcome to redistribute it - under certain conditions; type `show c' for details. - -The hypothetical commands `show w' and `show c' should show the appropriate -parts of the General Public License. Of course, your program's commands -might be different; for a GUI interface, you would use an "about box". - - You should also get your employer (if you work as a programmer) or school, -if any, to sign a "copyright disclaimer" for the program, if necessary. -For more information on this, and how to apply and follow the GNU GPL, see -. - - The GNU General Public License does not permit incorporating your program -into proprietary programs. If your program is a subroutine library, you -may consider it more useful to permit linking proprietary applications with -the library. If this is what you want to do, use the GNU Lesser General -Public License instead of this License. But first, please read -. diff --git a/edge-detect/ai/README.md b/edge-detect/ai/README.md deleted file mode 100644 index 81f385d..0000000 --- a/edge-detect/ai/README.md +++ /dev/null @@ -1 +0,0 @@ -The files datasets2.py and sort.py are derived from https://github.com/WongKinYiu/yolov7 and are being released under the GNU General Public License v3.0. (The remainder of this repo is released under the Apache License 2.0.) diff --git a/edge-detect/ai/datasets2.py b/edge-detect/ai/datasets2.py deleted file mode 100644 index 911e76d..0000000 --- a/edge-detect/ai/datasets2.py +++ /dev/null @@ -1,1361 +0,0 @@ -# Dataset utils and dataloaders - -import glob -import logging -import math -import os -import random -import shutil -import time -from itertools import repeat -from multiprocessing.pool import ThreadPool -from pathlib import Path -from threading import Thread - -import cv2 -import numpy as np -import torch -import torch.nn.functional as F -from PIL import Image, ExifTags -from torch.utils.data import Dataset -from tqdm import tqdm - -import pickle -from copy import deepcopy -#from pycocotools import mask as maskUtils -from torchvision.utils import save_image -from torchvision.ops import roi_pool, roi_align, ps_roi_pool, ps_roi_align - -from utils.general import check_requirements, xyxy2xywh, xywh2xyxy, xywhn2xyxy, xyn2xy, segment2box, segments2boxes, \ - resample_segments, clean_str -from utils.torch_utils import torch_distributed_zero_first - -# Parameters -help_url = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data' -img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng', 'webp', 'mpo'] # acceptable image suffixes -vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv'] # acceptable video suffixes -logger = logging.getLogger(__name__) - -# Get orientation exif tag -for orientation in ExifTags.TAGS.keys(): - if ExifTags.TAGS[orientation] == 'Orientation': - break - - -def get_hash(files): - # Returns a single hash value of a list of files - return sum(os.path.getsize(f) for f in files if os.path.isfile(f)) - - -def exif_size(img): - # Returns exif-corrected PIL size - s = img.size # (width, height) - try: - rotation = dict(img._getexif().items())[orientation] - if rotation == 6: # rotation 270 - s = (s[1], s[0]) - elif rotation == 8: # rotation 90 - s = (s[1], s[0]) - except: - pass - - return s - - -def create_dataloader(path, imgsz, batch_size, stride, opt, hyp=None, augment=False, cache=False, pad=0.0, rect=False, - rank=-1, world_size=1, workers=8, image_weights=False, quad=False, prefix=''): - # Make sure only the first process in DDP process the dataset first, and the following others can use the cache - with torch_distributed_zero_first(rank): - dataset = LoadImagesAndLabels(path, imgsz, batch_size, - augment=augment, # augment images - hyp=hyp, # augmentation hyperparameters - rect=rect, # rectangular training - cache_images=cache, - single_cls=opt.single_cls, - stride=int(stride), - pad=pad, - image_weights=image_weights, - prefix=prefix) - - batch_size = min(batch_size, len(dataset)) - nw = min([os.cpu_count() // world_size, batch_size if batch_size > 1 else 0, workers]) # number of workers - sampler = torch.utils.data.distributed.DistributedSampler(dataset) if rank != -1 else None - loader = torch.utils.data.DataLoader if image_weights else InfiniteDataLoader - # Use torch.utils.data.DataLoader() if dataset.properties will update during training else InfiniteDataLoader() - dataloader = loader(dataset, - batch_size=batch_size, - num_workers=nw, - sampler=sampler, - pin_memory=True, - collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn) - return dataloader, dataset - - -class InfiniteDataLoader(torch.utils.data.dataloader.DataLoader): - """ Dataloader that reuses workers - - Uses same syntax as vanilla DataLoader - """ - - def __init__(self, *args, **kwargs): - super().__init__(*args, **kwargs) - object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler)) - self.iterator = super().__iter__() - - def __len__(self): - return len(self.batch_sampler.sampler) - - def __iter__(self): - for i in range(len(self)): - yield next(self.iterator) - - -class _RepeatSampler(object): - """ Sampler that repeats forever - - Args: - sampler (Sampler) - """ - - def __init__(self, sampler): - self.sampler = sampler - - def __iter__(self): - while True: - yield from iter(self.sampler) - - -class LoadImages: # for inference - def __init__(self, path, img_size=640, stride=32): - p = str(Path(path).absolute()) # os-agnostic absolute path - if '*' in p: - files = sorted(glob.glob(p, recursive=True)) # glob - elif os.path.isdir(p): - files = sorted(glob.glob(os.path.join(p, '*.*'))) # dir - elif os.path.isfile(p): - files = [p] # files - else: - raise Exception(f'ERROR: {p} does not exist') - - images = [x for x in files if x.split('.')[-1].lower() in img_formats] - videos = [x for x in files if x.split('.')[-1].lower() in vid_formats] - ni, nv = len(images), len(videos) - - self.img_size = img_size - self.stride = stride - self.files = images + videos - self.nf = ni + nv # number of files - self.video_flag = [False] * ni + [True] * nv - self.mode = 'image' - if any(videos): - self.new_video(videos[0]) # new video - else: - self.cap = None - assert self.nf > 0, f'No images or videos found in {p}. ' \ - f'Supported formats are:\nimages: {img_formats}\nvideos: {vid_formats}' - - def __iter__(self): - self.count = 0 - return self - - def __next__(self): - if self.count == self.nf: - raise StopIteration - path = self.files[self.count] - - if self.video_flag[self.count]: - # Read video - self.mode = 'video' - ret_val, img0 = self.cap.read() - if not ret_val: - self.count += 1 - self.cap.release() - if self.count == self.nf: # last video - raise StopIteration - else: - path = self.files[self.count] - self.new_video(path) - ret_val, img0 = self.cap.read() - - self.frame += 1 - print(f'video {self.count + 1}/{self.nf} ({self.frame}/{self.nframes}) {path}: ', end='') - - else: - # Read image - self.count += 1 - img0 = cv2.imread(path) # BGR - assert img0 is not None, 'Image Not Found ' + path - #print(f'image {self.count}/{self.nf} {path}: ', end='') - - # Padded resize - img = letterbox(img0, self.img_size, stride=self.stride)[0] - - # Convert - img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 - img = np.ascontiguousarray(img) - - return path, img, img0, self.cap - - def new_video(self, path): - self.frame = 0 - self.cap = cv2.VideoCapture(path) - self.nframes = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT)) - - def __len__(self): - return self.nf # number of files - - -class LoadWebcam: # for inference - def __init__(self, pipe='0', img_size=640, stride=32): - self.img_size = img_size - self.stride = stride - - if pipe.isnumeric(): - pipe = eval(pipe) # local camera - # pipe = 'rtsp://192.168.1.64/1' # IP camera - # pipe = 'rtsp://username:password@192.168.1.64/1' # IP camera with login - # pipe = 'http://wmccpinetop.axiscam.net/mjpg/video.mjpg' # IP golf camera - - self.pipe = pipe - self.cap = cv2.VideoCapture(pipe) # video capture object - self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3) # set buffer size - - def __iter__(self): - self.count = -1 - return self - - def __next__(self): - self.count += 1 - if cv2.waitKey(1) == ord('q'): # q to quit - self.cap.release() - cv2.destroyAllWindows() - raise StopIteration - - # Read frame - if self.pipe == 0: # local camera - ret_val, img0 = self.cap.read() - img0 = cv2.flip(img0, 1) # flip left-right - else: # IP camera - n = 0 - while True: - n += 1 - self.cap.grab() - if n % 30 == 0: # skip frames - ret_val, img0 = self.cap.retrieve() - if ret_val: - break - - # Print - assert ret_val, f'Camera Error {self.pipe}' - img_path = 'webcam.jpg' - print(f'webcam {self.count}: ', end='') - - # Padded resize - img = letterbox(img0, self.img_size, stride=self.stride)[0] - - # Convert - img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 - img = np.ascontiguousarray(img) - - return img_path, img, img0, None - - def __len__(self): - return 0 - - -class LoadFromDir: # for inference - def __init__(self, path, img_size=640, stride=32, log_dir="/data/log"): - self.path = path - self.img_size = img_size - self.stride = stride - self.mode = 'image' - self.log_dir = log_dir - - def __iter__(self): - self.count = 0 - return self - - def __next__(self): - # Check for files in folder, waiting if necessary - img0 = None - img_path = None - while True: - if os.path.isdir(self.path): - img_paths = glob.glob(os.path.join(self.path, '*')) - if len(img_paths) > 0: - img_path = min(img_paths, key=os.path.getctime) - img0 = cv2.imread(img_path) - if os.path.isdir(img_path) or img0 is None: - print("Found non-file object ... moving to logs") - base_folder = os.path.basename(img_path) - shutil.move(img_path, os.path.join(self.log_dir, base_folder)) - else: - break - time.sleep(0.5) - - # Process image - self.count += 1 - img = letterbox(img0, self.img_size, stride=self.stride)[0] # Size - img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, channel first - img = np.ascontiguousarray(img) - return img_path, img, img0, None - - def __len__(self): - return 0 - - -class LoadStreams: # multiple IP or RTSP cameras - def __init__(self, sources='streams.txt', img_size=640, stride=32): - self.mode = 'stream' - self.img_size = img_size - self.stride = stride - - if os.path.isfile(sources): - with open(sources, 'r') as f: - sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())] - else: - sources = [sources] - - n = len(sources) - self.imgs = [None] * n - self.sources = [clean_str(x) for x in sources] # clean source names for later - for i, s in enumerate(sources): - # Start the thread to read frames from the video stream - print(f'{i + 1}/{n}: {s}... ', end='') - url = eval(s) if s.isnumeric() else s - if 'youtube.com/' in str(url) or 'youtu.be/' in str(url): # if source is YouTube video - check_requirements(('pafy', 'youtube_dl')) - import pafy - url = pafy.new(url).getbest(preftype="mp4").url - cap = cv2.VideoCapture(url) - assert cap.isOpened(), f'Failed to open {s}' - w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)) - h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) - self.fps = cap.get(cv2.CAP_PROP_FPS) % 100 - - _, self.imgs[i] = cap.read() # guarantee first frame - thread = Thread(target=self.update, args=([i, cap]), daemon=True) - print(f' success ({w}x{h} at {self.fps:.2f} FPS).') - thread.start() - print('') # newline - - # check for common shapes - s = np.stack([letterbox(x, self.img_size, stride=self.stride)[0].shape for x in self.imgs], 0) # shapes - self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal - if not self.rect: - print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.') - - def update(self, index, cap): - # Read next stream frame in a daemon thread - n = 0 - while cap.isOpened(): - n += 1 - # _, self.imgs[index] = cap.read() - cap.grab() - if n == 4: # read every 4th frame - success, im = cap.retrieve() - self.imgs[index] = im if success else self.imgs[index] * 0 - n = 0 - time.sleep(1 / self.fps) # wait time - - def __iter__(self): - self.count = -1 - return self - - def __next__(self): - self.count += 1 - img0 = self.imgs.copy() - if cv2.waitKey(1) == ord('q'): # q to quit - cv2.destroyAllWindows() - raise StopIteration - - # Letterbox - img = [letterbox(x, self.img_size, auto=self.rect, stride=self.stride)[0] for x in img0] - - # Stack - img = np.stack(img, 0) - - # Convert - img = img[:, :, :, ::-1].transpose(0, 3, 1, 2) # BGR to RGB, to bsx3x416x416 - img = np.ascontiguousarray(img) - - return self.sources, img, img0, None - - def __len__(self): - return 0 # 1E12 frames = 32 streams at 30 FPS for 30 years - - -def img2label_paths(img_paths): - # Define label paths as a function of image paths - sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep # /images/, /labels/ substrings - return ['txt'.join(x.replace(sa, sb, 1).rsplit(x.split('.')[-1], 1)) for x in img_paths] - - -class LoadImagesAndLabels(Dataset): # for training/testing - def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False, - cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''): - self.img_size = img_size - self.augment = augment - self.hyp = hyp - self.image_weights = image_weights - self.rect = False if image_weights else rect - self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training) - self.mosaic_border = [-img_size // 2, -img_size // 2] - self.stride = stride - self.path = path - #self.albumentations = Albumentations() if augment else None - - try: - f = [] # image files - for p in path if isinstance(path, list) else [path]: - p = Path(p) # os-agnostic - if p.is_dir(): # dir - f += glob.glob(str(p / '**' / '*.*'), recursive=True) - # f = list(p.rglob('**/*.*')) # pathlib - elif p.is_file(): # file - with open(p, 'r') as t: - t = t.read().strip().splitlines() - parent = str(p.parent) + os.sep - f += [x.replace('./', parent) if x.startswith('./') else x for x in t] # local to global path - # f += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib) - else: - raise Exception(f'{prefix}{p} does not exist') - self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in img_formats]) - # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in img_formats]) # pathlib - assert self.img_files, f'{prefix}No images found' - except Exception as e: - raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {help_url}') - - # Check cache - self.label_files = img2label_paths(self.img_files) # labels - cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache') # cached labels - if cache_path.is_file(): - cache, exists = torch.load(cache_path), True # load - #if cache['hash'] != get_hash(self.label_files + self.img_files) or 'version' not in cache: # changed - # cache, exists = self.cache_labels(cache_path, prefix), False # re-cache - else: - cache, exists = self.cache_labels(cache_path, prefix), False # cache - - # Display cache - nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupted, total - if exists: - d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted" - tqdm(None, desc=prefix + d, total=n, initial=n) # display cache results - assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {help_url}' - - # Read cache - cache.pop('hash') # remove hash - cache.pop('version') # remove version - labels, shapes, self.segments = zip(*cache.values()) - self.labels = list(labels) - self.shapes = np.array(shapes, dtype=np.float64) - self.img_files = list(cache.keys()) # update - self.label_files = img2label_paths(cache.keys()) # update - if single_cls: - for x in self.labels: - x[:, 0] = 0 - - n = len(shapes) # number of images - bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index - nb = bi[-1] + 1 # number of batches - self.batch = bi # batch index of image - self.n = n - self.indices = range(n) - - # Rectangular Training - if self.rect: - # Sort by aspect ratio - s = self.shapes # wh - ar = s[:, 1] / s[:, 0] # aspect ratio - irect = ar.argsort() - self.img_files = [self.img_files[i] for i in irect] - self.label_files = [self.label_files[i] for i in irect] - self.labels = [self.labels[i] for i in irect] - self.shapes = s[irect] # wh - ar = ar[irect] - - # Set training image shapes - shapes = [[1, 1]] * nb - for i in range(nb): - ari = ar[bi == i] - mini, maxi = ari.min(), ari.max() - if maxi < 1: - shapes[i] = [maxi, 1] - elif mini > 1: - shapes[i] = [1, 1 / mini] - - self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride - - # Cache images into memory for faster training (WARNING: large datasets may exceed system RAM) - self.imgs = [None] * n - if cache_images: - if cache_images == 'disk': - self.im_cache_dir = Path(Path(self.img_files[0]).parent.as_posix() + '_npy') - self.img_npy = [self.im_cache_dir / Path(f).with_suffix('.npy').name for f in self.img_files] - self.im_cache_dir.mkdir(parents=True, exist_ok=True) - gb = 0 # Gigabytes of cached images - self.img_hw0, self.img_hw = [None] * n, [None] * n - results = ThreadPool(8).imap(lambda x: load_image(*x), zip(repeat(self), range(n))) - pbar = tqdm(enumerate(results), total=n) - for i, x in pbar: - if cache_images == 'disk': - if not self.img_npy[i].exists(): - np.save(self.img_npy[i].as_posix(), x[0]) - gb += self.img_npy[i].stat().st_size - else: - self.imgs[i], self.img_hw0[i], self.img_hw[i] = x - gb += self.imgs[i].nbytes - pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB)' - pbar.close() - - def cache_labels(self, path=Path('./labels.cache'), prefix=''): - # Cache dataset labels, check images and read shapes - x = {} # dict - nm, nf, ne, nc = 0, 0, 0, 0 # number missing, found, empty, duplicate - pbar = tqdm(zip(self.img_files, self.label_files), desc='Scanning images', total=len(self.img_files)) - for i, (im_file, lb_file) in enumerate(pbar): - try: - # verify images - im = Image.open(im_file) - im.verify() # PIL verify - shape = exif_size(im) # image size - segments = [] # instance segments - assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels' - assert im.format.lower() in img_formats, f'invalid image format {im.format}' - - # verify labels - if os.path.isfile(lb_file): - nf += 1 # label found - with open(lb_file, 'r') as f: - l = [x.split() for x in f.read().strip().splitlines()] - if any([len(x) > 8 for x in l]): # is segment - classes = np.array([x[0] for x in l], dtype=np.float32) - segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in l] # (cls, xy1...) - l = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh) - l = np.array(l, dtype=np.float32) - if len(l): - assert l.shape[1] == 5, 'labels require 5 columns each' - assert (l >= 0).all(), 'negative labels' - assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels' - assert np.unique(l, axis=0).shape[0] == l.shape[0], 'duplicate labels' - else: - ne += 1 # label empty - l = np.zeros((0, 5), dtype=np.float32) - else: - nm += 1 # label missing - l = np.zeros((0, 5), dtype=np.float32) - x[im_file] = [l, shape, segments] - except Exception as e: - nc += 1 - print(f'{prefix}WARNING: Ignoring corrupted image and/or label {im_file}: {e}') - - pbar.desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels... " \ - f"{nf} found, {nm} missing, {ne} empty, {nc} corrupted" - pbar.close() - - if nf == 0: - print(f'{prefix}WARNING: No labels found in {path}. See {help_url}') - - x['hash'] = get_hash(self.label_files + self.img_files) - x['results'] = nf, nm, ne, nc, i + 1 - x['version'] = 0.1 # cache version - torch.save(x, path) # save for next time - logging.info(f'{prefix}New cache created: {path}') - return x - - def __len__(self): - return len(self.img_files) - - # def __iter__(self): - # self.count = -1 - # print('ran dataset iter') - # #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF) - # return self - - def __getitem__(self, index): - index = self.indices[index] # linear, shuffled, or image_weights - - hyp = self.hyp - mosaic = self.mosaic and random.random() < hyp['mosaic'] - if mosaic: - # Load mosaic - if random.random() < 0.8: - img, labels = load_mosaic(self, index) - else: - img, labels = load_mosaic9(self, index) - shapes = None - - # MixUp https://arxiv.org/pdf/1710.09412.pdf - if random.random() < hyp['mixup']: - if random.random() < 0.8: - img2, labels2 = load_mosaic(self, random.randint(0, len(self.labels) - 1)) - else: - img2, labels2 = load_mosaic9(self, random.randint(0, len(self.labels) - 1)) - r = np.random.beta(8.0, 8.0) # mixup ratio, alpha=beta=8.0 - img = (img * r + img2 * (1 - r)).astype(np.uint8) - labels = np.concatenate((labels, labels2), 0) - - else: - # Load image - img, (h0, w0), (h, w) = load_image(self, index) - - # Letterbox - shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape - img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment) - shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling - - labels = self.labels[index].copy() - if labels.size: # normalized xywh to pixel xyxy format - labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1]) - - if self.augment: - # Augment imagespace - if not mosaic: - img, labels = random_perspective(img, labels, - degrees=hyp['degrees'], - translate=hyp['translate'], - scale=hyp['scale'], - shear=hyp['shear'], - perspective=hyp['perspective']) - - - #img, labels = self.albumentations(img, labels) - - # Augment colorspace - augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v']) - - # Apply cutouts - # if random.random() < 0.9: - # labels = cutout(img, labels) - - if random.random() < hyp['paste_in']: - sample_labels, sample_images, sample_masks = [], [], [] - while len(sample_labels) < 30: - sample_labels_, sample_images_, sample_masks_ = load_samples(self, random.randint(0, len(self.labels) - 1)) - sample_labels += sample_labels_ - sample_images += sample_images_ - sample_masks += sample_masks_ - #print(len(sample_labels)) - if len(sample_labels) == 0: - break - labels = pastein(img, labels, sample_labels, sample_images, sample_masks) - - nL = len(labels) # number of labels - if nL: - labels[:, 1:5] = xyxy2xywh(labels[:, 1:5]) # convert xyxy to xywh - labels[:, [2, 4]] /= img.shape[0] # normalized height 0-1 - labels[:, [1, 3]] /= img.shape[1] # normalized width 0-1 - - if self.augment: - # flip up-down - if random.random() < hyp['flipud']: - img = np.flipud(img) - if nL: - labels[:, 2] = 1 - labels[:, 2] - - # flip left-right - if random.random() < hyp['fliplr']: - img = np.fliplr(img) - if nL: - labels[:, 1] = 1 - labels[:, 1] - - labels_out = torch.zeros((nL, 6)) - if nL: - labels_out[:, 1:] = torch.from_numpy(labels) - - # Convert - img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 - img = np.ascontiguousarray(img) - - return torch.from_numpy(img), labels_out, self.img_files[index], shapes - - @staticmethod - def collate_fn(batch): - img, label, path, shapes = zip(*batch) # transposed - for i, l in enumerate(label): - l[:, 0] = i # add target image index for build_targets() - return torch.stack(img, 0), torch.cat(label, 0), path, shapes - - @staticmethod - def collate_fn4(batch): - img, label, path, shapes = zip(*batch) # transposed - n = len(shapes) // 4 - img4, label4, path4, shapes4 = [], [], path[:n], shapes[:n] - - ho = torch.tensor([[0., 0, 0, 1, 0, 0]]) - wo = torch.tensor([[0., 0, 1, 0, 0, 0]]) - s = torch.tensor([[1, 1, .5, .5, .5, .5]]) # scale - for i in range(n): # zidane torch.zeros(16,3,720,1280) # BCHW - i *= 4 - if random.random() < 0.5: - im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2., mode='bilinear', align_corners=False)[ - 0].type(img[i].type()) - l = label[i] - else: - im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2) - l = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s - img4.append(im) - label4.append(l) - - for i, l in enumerate(label4): - l[:, 0] = i # add target image index for build_targets() - - return torch.stack(img4, 0), torch.cat(label4, 0), path4, shapes4 - - -# Ancillary functions -------------------------------------------------------------------------------------------------- -def load_image(self, index): - # loads 1 image from dataset, returns img, original hw, resized hw - img = self.imgs[index] - if img is None: # not cached - path = self.img_files[index] - img = cv2.imread(path) # BGR - assert img is not None, 'Image Not Found ' + path - h0, w0 = img.shape[:2] # orig hw - r = self.img_size / max(h0, w0) # resize image to img_size - if r != 1: # always resize down, only resize up if training with augmentation - interp = cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR - img = cv2.resize(img, (int(w0 * r), int(h0 * r)), interpolation=interp) - return img, (h0, w0), img.shape[:2] # img, hw_original, hw_resized - else: - return self.imgs[index], self.img_hw0[index], self.img_hw[index] # img, hw_original, hw_resized - - -def augment_hsv(img, hgain=0.5, sgain=0.5, vgain=0.5): - r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains - hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV)) - dtype = img.dtype # uint8 - - x = np.arange(0, 256, dtype=np.int16) - lut_hue = ((x * r[0]) % 180).astype(dtype) - lut_sat = np.clip(x * r[1], 0, 255).astype(dtype) - lut_val = np.clip(x * r[2], 0, 255).astype(dtype) - - img_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))).astype(dtype) - cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img) # no return needed - - -def hist_equalize(img, clahe=True, bgr=False): - # Equalize histogram on BGR image 'img' with img.shape(n,m,3) and range 0-255 - yuv = cv2.cvtColor(img, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV) - if clahe: - c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8)) - yuv[:, :, 0] = c.apply(yuv[:, :, 0]) - else: - yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram - return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB - - -def load_mosaic(self, index): - # loads images in a 4-mosaic - - labels4, segments4 = [], [] - s = self.img_size - yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border] # mosaic center x, y - indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices - for i, index in enumerate(indices): - # Load image - img, _, (h, w) = load_image(self, index) - - # place img in img4 - if i == 0: # top left - img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles - x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image) - x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image) - elif i == 1: # top right - x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc - x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h - elif i == 2: # bottom left - x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h) - x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h) - elif i == 3: # bottom right - x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h) - x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h) - - img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax] - padw = x1a - x1b - padh = y1a - y1b - - # Labels - labels, segments = self.labels[index].copy(), self.segments[index].copy() - if labels.size: - labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh) # normalized xywh to pixel xyxy format - segments = [xyn2xy(x, w, h, padw, padh) for x in segments] - labels4.append(labels) - segments4.extend(segments) - - # Concat/clip labels - labels4 = np.concatenate(labels4, 0) - for x in (labels4[:, 1:], *segments4): - np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective() - # img4, labels4 = replicate(img4, labels4) # replicate - - # Augment - #img4, labels4, segments4 = remove_background(img4, labels4, segments4) - #sample_segments(img4, labels4, segments4, probability=self.hyp['copy_paste']) - img4, labels4, segments4 = copy_paste(img4, labels4, segments4, probability=self.hyp['copy_paste']) - img4, labels4 = random_perspective(img4, labels4, segments4, - degrees=self.hyp['degrees'], - translate=self.hyp['translate'], - scale=self.hyp['scale'], - shear=self.hyp['shear'], - perspective=self.hyp['perspective'], - border=self.mosaic_border) # border to remove - - return img4, labels4 - - -def load_mosaic9(self, index): - # loads images in a 9-mosaic - - labels9, segments9 = [], [] - s = self.img_size - indices = [index] + random.choices(self.indices, k=8) # 8 additional image indices - for i, index in enumerate(indices): - # Load image - img, _, (h, w) = load_image(self, index) - - # place img in img9 - if i == 0: # center - img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles - h0, w0 = h, w - c = s, s, s + w, s + h # xmin, ymin, xmax, ymax (base) coordinates - elif i == 1: # top - c = s, s - h, s + w, s - elif i == 2: # top right - c = s + wp, s - h, s + wp + w, s - elif i == 3: # right - c = s + w0, s, s + w0 + w, s + h - elif i == 4: # bottom right - c = s + w0, s + hp, s + w0 + w, s + hp + h - elif i == 5: # bottom - c = s + w0 - w, s + h0, s + w0, s + h0 + h - elif i == 6: # bottom left - c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h - elif i == 7: # left - c = s - w, s + h0 - h, s, s + h0 - elif i == 8: # top left - c = s - w, s + h0 - hp - h, s, s + h0 - hp - - padx, pady = c[:2] - x1, y1, x2, y2 = [max(x, 0) for x in c] # allocate coords - - # Labels - labels, segments = self.labels[index].copy(), self.segments[index].copy() - if labels.size: - labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady) # normalized xywh to pixel xyxy format - segments = [xyn2xy(x, w, h, padx, pady) for x in segments] - labels9.append(labels) - segments9.extend(segments) - - # Image - img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:] # img9[ymin:ymax, xmin:xmax] - hp, wp = h, w # height, width previous - - # Offset - yc, xc = [int(random.uniform(0, s)) for _ in self.mosaic_border] # mosaic center x, y - img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s] - - # Concat/clip labels - labels9 = np.concatenate(labels9, 0) - labels9[:, [1, 3]] -= xc - labels9[:, [2, 4]] -= yc - c = np.array([xc, yc]) # centers - segments9 = [x - c for x in segments9] - - for x in (labels9[:, 1:], *segments9): - np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective() - # img9, labels9 = replicate(img9, labels9) # replicate - - # Augment - #img9, labels9, segments9 = remove_background(img9, labels9, segments9) - img9, labels9, segments9 = copy_paste(img9, labels9, segments9, probability=self.hyp['copy_paste']) - img9, labels9 = random_perspective(img9, labels9, segments9, - degrees=self.hyp['degrees'], - translate=self.hyp['translate'], - scale=self.hyp['scale'], - shear=self.hyp['shear'], - perspective=self.hyp['perspective'], - border=self.mosaic_border) # border to remove - - return img9, labels9 - - -def load_samples(self, index): - # loads images in a 4-mosaic - - labels4, segments4 = [], [] - s = self.img_size - yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border] # mosaic center x, y - indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices - for i, index in enumerate(indices): - # Load image - img, _, (h, w) = load_image(self, index) - - # place img in img4 - if i == 0: # top left - img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles - x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image) - x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image) - elif i == 1: # top right - x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc - x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h - elif i == 2: # bottom left - x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h) - x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h) - elif i == 3: # bottom right - x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h) - x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h) - - img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax] - padw = x1a - x1b - padh = y1a - y1b - - # Labels - labels, segments = self.labels[index].copy(), self.segments[index].copy() - if labels.size: - labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh) # normalized xywh to pixel xyxy format - segments = [xyn2xy(x, w, h, padw, padh) for x in segments] - labels4.append(labels) - segments4.extend(segments) - - # Concat/clip labels - labels4 = np.concatenate(labels4, 0) - for x in (labels4[:, 1:], *segments4): - np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective() - # img4, labels4 = replicate(img4, labels4) # replicate - - # Augment - #img4, labels4, segments4 = remove_background(img4, labels4, segments4) - sample_labels, sample_images, sample_masks = sample_segments(img4, labels4, segments4, probability=0.5) - - return sample_labels, sample_images, sample_masks - - -def copy_paste(img, labels, segments, probability=0.5): - # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy) - n = len(segments) - if probability and n: - h, w, c = img.shape # height, width, channels - im_new = np.zeros(img.shape, np.uint8) - for j in random.sample(range(n), k=round(probability * n)): - l, s = labels[j], segments[j] - box = w - l[3], l[2], w - l[1], l[4] - ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area - if (ioa < 0.30).all(): # allow 30% obscuration of existing labels - labels = np.concatenate((labels, [[l[0], *box]]), 0) - segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1)) - cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED) - - result = cv2.bitwise_and(src1=img, src2=im_new) - result = cv2.flip(result, 1) # augment segments (flip left-right) - i = result > 0 # pixels to replace - # i[:, :] = result.max(2).reshape(h, w, 1) # act over ch - img[i] = result[i] # cv2.imwrite('debug.jpg', img) # debug - - return img, labels, segments - - -def remove_background(img, labels, segments): - # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy) - n = len(segments) - h, w, c = img.shape # height, width, channels - im_new = np.zeros(img.shape, np.uint8) - img_new = np.ones(img.shape, np.uint8) * 114 - for j in range(n): - cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED) - - result = cv2.bitwise_and(src1=img, src2=im_new) - - i = result > 0 # pixels to replace - img_new[i] = result[i] # cv2.imwrite('debug.jpg', img) # debug - - return img_new, labels, segments - - -def sample_segments(img, labels, segments, probability=0.5): - # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy) - n = len(segments) - sample_labels = [] - sample_images = [] - sample_masks = [] - if probability and n: - h, w, c = img.shape # height, width, channels - for j in random.sample(range(n), k=round(probability * n)): - l, s = labels[j], segments[j] - box = l[1].astype(int).clip(0,w-1), l[2].astype(int).clip(0,h-1), l[3].astype(int).clip(0,w-1), l[4].astype(int).clip(0,h-1) - - #print(box) - if (box[2] <= box[0]) or (box[3] <= box[1]): - continue - - sample_labels.append(l[0]) - - mask = np.zeros(img.shape, np.uint8) - - cv2.drawContours(mask, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED) - sample_masks.append(mask[box[1]:box[3],box[0]:box[2],:]) - - result = cv2.bitwise_and(src1=img, src2=mask) - i = result > 0 # pixels to replace - mask[i] = result[i] # cv2.imwrite('debug.jpg', img) # debug - #print(box) - sample_images.append(mask[box[1]:box[3],box[0]:box[2],:]) - - return sample_labels, sample_images, sample_masks - - -def replicate(img, labels): - # Replicate labels - h, w = img.shape[:2] - boxes = labels[:, 1:].astype(int) - x1, y1, x2, y2 = boxes.T - s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels) - for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices - x1b, y1b, x2b, y2b = boxes[i] - bh, bw = y2b - y1b, x2b - x1b - yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y - x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh] - img[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax] - labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0) - - return img, labels - - -def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32): - # Resize and pad image while meeting stride-multiple constraints - shape = img.shape[:2] # current shape [height, width] - if isinstance(new_shape, int): - new_shape = (new_shape, new_shape) - - # Scale ratio (new / old) - r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) - if not scaleup: # only scale down, do not scale up (for better test mAP) - r = min(r, 1.0) - - # Compute padding - ratio = r, r # width, height ratios - new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) - dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding - if auto: # minimum rectangle - dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding - elif scaleFill: # stretch - dw, dh = 0.0, 0.0 - new_unpad = (new_shape[1], new_shape[0]) - ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios - - dw /= 2 # divide padding into 2 sides - dh /= 2 - - if shape[::-1] != new_unpad: # resize - img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR) - top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) - left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) - img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border - return img, ratio, (dw, dh) - - -def random_perspective(img, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0, - border=(0, 0)): - # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10)) - # targets = [cls, xyxy] - - height = img.shape[0] + border[0] * 2 # shape(h,w,c) - width = img.shape[1] + border[1] * 2 - - # Center - C = np.eye(3) - C[0, 2] = -img.shape[1] / 2 # x translation (pixels) - C[1, 2] = -img.shape[0] / 2 # y translation (pixels) - - # Perspective - P = np.eye(3) - P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y) - P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x) - - # Rotation and Scale - R = np.eye(3) - a = random.uniform(-degrees, degrees) - # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations - s = random.uniform(1 - scale, 1.1 + scale) - # s = 2 ** random.uniform(-scale, scale) - R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s) - - # Shear - S = np.eye(3) - S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg) - S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg) - - # Translation - T = np.eye(3) - T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels) - T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels) - - # Combined rotation matrix - M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT - if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed - if perspective: - img = cv2.warpPerspective(img, M, dsize=(width, height), borderValue=(114, 114, 114)) - else: # affine - img = cv2.warpAffine(img, M[:2], dsize=(width, height), borderValue=(114, 114, 114)) - - # Visualize - # import matplotlib.pyplot as plt - # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel() - # ax[0].imshow(img[:, :, ::-1]) # base - # ax[1].imshow(img2[:, :, ::-1]) # warped - - # Transform label coordinates - n = len(targets) - if n: - use_segments = any(x.any() for x in segments) - new = np.zeros((n, 4)) - if use_segments: # warp segments - segments = resample_segments(segments) # upsample - for i, segment in enumerate(segments): - xy = np.ones((len(segment), 3)) - xy[:, :2] = segment - xy = xy @ M.T # transform - xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine - - # clip - new[i] = segment2box(xy, width, height) - - else: # warp boxes - xy = np.ones((n * 4, 3)) - xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1 - xy = xy @ M.T # transform - xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine - - # create new boxes - x = xy[:, [0, 2, 4, 6]] - y = xy[:, [1, 3, 5, 7]] - new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T - - # clip - new[:, [0, 2]] = new[:, [0, 2]].clip(0, width) - new[:, [1, 3]] = new[:, [1, 3]].clip(0, height) - - # filter candidates - i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10) - targets = targets[i] - targets[:, 1:5] = new[i] - - return img, targets - - -def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n) - # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio - w1, h1 = box1[2] - box1[0], box1[3] - box1[1] - w2, h2 = box2[2] - box2[0], box2[3] - box2[1] - ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio - return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates - - -def bbox_ioa(box1, box2): - # Returns the intersection over box2 area given box1, box2. box1 is 4, box2 is nx4. boxes are x1y1x2y2 - box2 = box2.transpose() - - # Get the coordinates of bounding boxes - b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3] - b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3] - - # Intersection area - inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \ - (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0) - - # box2 area - box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + 1e-16 - - # Intersection over box2 area - return inter_area / box2_area - - -def cutout(image, labels): - # Applies image cutout augmentation https://arxiv.org/abs/1708.04552 - h, w = image.shape[:2] - - # create random masks - scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction - for s in scales: - mask_h = random.randint(1, int(h * s)) - mask_w = random.randint(1, int(w * s)) - - # box - xmin = max(0, random.randint(0, w) - mask_w // 2) - ymin = max(0, random.randint(0, h) - mask_h // 2) - xmax = min(w, xmin + mask_w) - ymax = min(h, ymin + mask_h) - - # apply random color mask - image[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)] - - # return unobscured labels - if len(labels) and s > 0.03: - box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32) - ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area - labels = labels[ioa < 0.60] # remove >60% obscured labels - - return labels - - -def pastein(image, labels, sample_labels, sample_images, sample_masks): - # Applies image cutout augmentation https://arxiv.org/abs/1708.04552 - h, w = image.shape[:2] - - # create random masks - scales = [0.75] * 2 + [0.5] * 4 + [0.25] * 4 + [0.125] * 4 + [0.0625] * 6 # image size fraction - for s in scales: - if random.random() < 0.2: - continue - mask_h = random.randint(1, int(h * s)) - mask_w = random.randint(1, int(w * s)) - - # box - xmin = max(0, random.randint(0, w) - mask_w // 2) - ymin = max(0, random.randint(0, h) - mask_h // 2) - xmax = min(w, xmin + mask_w) - ymax = min(h, ymin + mask_h) - - box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32) - if len(labels): - ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area - else: - ioa = np.zeros(1) - - if (ioa < 0.30).all() and len(sample_labels) and (xmax > xmin+20) and (ymax > ymin+20): # allow 30% obscuration of existing labels - sel_ind = random.randint(0, len(sample_labels)-1) - #print(len(sample_labels)) - #print(sel_ind) - #print((xmax-xmin, ymax-ymin)) - #print(image[ymin:ymax, xmin:xmax].shape) - #print([[sample_labels[sel_ind], *box]]) - #print(labels.shape) - hs, ws, cs = sample_images[sel_ind].shape - r_scale = min((ymax-ymin)/hs, (xmax-xmin)/ws) - r_w = int(ws*r_scale) - r_h = int(hs*r_scale) - - if (r_w > 10) and (r_h > 10): - r_mask = cv2.resize(sample_masks[sel_ind], (r_w, r_h)) - r_image = cv2.resize(sample_images[sel_ind], (r_w, r_h)) - temp_crop = image[ymin:ymin+r_h, xmin:xmin+r_w] - m_ind = r_mask > 0 - if m_ind.astype(np.int).sum() > 60: - temp_crop[m_ind] = r_image[m_ind] - #print(sample_labels[sel_ind]) - #print(sample_images[sel_ind].shape) - #print(temp_crop.shape) - box = np.array([xmin, ymin, xmin+r_w, ymin+r_h], dtype=np.float32) - if len(labels): - labels = np.concatenate((labels, [[sample_labels[sel_ind], *box]]), 0) - else: - labels = np.array([[sample_labels[sel_ind], *box]]) - - image[ymin:ymin+r_h, xmin:xmin+r_w] = temp_crop - - return labels - -class Albumentations: - # YOLOv5 Albumentations class (optional, only used if package is installed) - def __init__(self): - self.transform = None - import albumentations as A - - self.transform = A.Compose([ - A.CLAHE(p=0.01), - A.RandomBrightnessContrast(brightness_limit=0.2, contrast_limit=0.2, p=0.01), - A.RandomGamma(gamma_limit=[80, 120], p=0.01), - A.Blur(p=0.01), - A.MedianBlur(p=0.01), - A.ToGray(p=0.01), - A.ImageCompression(quality_lower=75, p=0.01),], - bbox_params=A.BboxParams(format='pascal_voc', label_fields=['class_labels'])) - - #logging.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p)) - - def __call__(self, im, labels, p=1.0): - if self.transform and random.random() < p: - new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed - im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])]) - return im, labels - - -def create_folder(path='./new'): - # Create folder - if os.path.exists(path): - shutil.rmtree(path) # delete output folder - os.makedirs(path) # make new output folder - - -def flatten_recursive(path='../coco'): - # Flatten a recursive directory by bringing all files to top level - new_path = Path(path + '_flat') - create_folder(new_path) - for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)): - shutil.copyfile(file, new_path / Path(file).name) - - -def extract_boxes(path='../coco/'): # from utils.datasets import *; extract_boxes('../coco128') - # Convert detection dataset into classification dataset, with one directory per class - - path = Path(path) # images dir - shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None # remove existing - files = list(path.rglob('*.*')) - n = len(files) # number of files - for im_file in tqdm(files, total=n): - if im_file.suffix[1:] in img_formats: - # image - im = cv2.imread(str(im_file))[..., ::-1] # BGR to RGB - h, w = im.shape[:2] - - # labels - lb_file = Path(img2label_paths([str(im_file)])[0]) - if Path(lb_file).exists(): - with open(lb_file, 'r') as f: - lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # labels - - for j, x in enumerate(lb): - c = int(x[0]) # class - f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg' # new filename - if not f.parent.is_dir(): - f.parent.mkdir(parents=True) - - b = x[1:] * [w, h, w, h] # box - # b[2:] = b[2:].max() # rectangle to square - b[2:] = b[2:] * 1.2 + 3 # pad - b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int) - - b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image - b[[1, 3]] = np.clip(b[[1, 3]], 0, h) - assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}' - - -def autosplit(path='../coco', weights=(0.9, 0.1, 0.0), annotated_only=False): - """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files - Usage: from utils.datasets import *; autosplit('../coco') - Arguments - path: Path to images directory - weights: Train, val, test weights (list) - annotated_only: Only use images with an annotated txt file - """ - path = Path(path) # images dir - files = sum([list(path.rglob(f"*.{img_ext}")) for img_ext in img_formats], []) # image files only - n = len(files) # number of files - indices = random.choices([0, 1, 2], weights=weights, k=n) # assign each image to a split - - txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt'] # 3 txt files - [(path / x).unlink() for x in txt if (path / x).exists()] # remove existing - - print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only) - for i, img in tqdm(zip(indices, files), total=n): - if not annotated_only or Path(img2label_paths([str(img)])[0]).exists(): # check label - with open(path / txt[i], 'a') as f: - f.write(str(img) + '\n') # add image to txt file - - -def load_segmentations(self, index): - key = '/work/handsomejw66/coco17/' + self.img_files[index] - #print(key) - # /work/handsomejw66/coco17/ - return self.segs[key] diff --git a/edge-detect/ai/sort.py b/edge-detect/ai/sort.py deleted file mode 100644 index 5ead40b..0000000 --- a/edge-detect/ai/sort.py +++ /dev/null @@ -1,245 +0,0 @@ -import argparse -import time -import os -import shutil -from pathlib import Path -import json - -import cv2 -import torch -import torch.backends.cudnn as cudnn -from numpy import random - -from models.experimental import attempt_load -from utils.datasets import LoadStreams, LoadImages -from utils.datasets2 import LoadFromDir -from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \ - scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path -from utils.plots import plot_one_box -from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel - - -def dirsort(save_img=False): - source, weights, view_img, save_txt, save_json, imgsz, trace = opt.source_dir, opt.weights, opt.view_img, opt.save_txt, opt.save_json, opt.img_size, not opt.no_trace - save_img = not opt.nosave and not source.endswith('.txt') # save inference images - webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith( - ('rtsp://', 'rtmp://', 'http://', 'https://')) - - # Directories - plane_dir, noplane_dir, log_dir = opt.plane_dir, opt.noplane_dir, opt.log_dir - Path(source).mkdir(parents=True, exist_ok=True) - Path(plane_dir).mkdir(parents=True, exist_ok=True) - Path(noplane_dir).mkdir(parents=True, exist_ok=True) - Path(log_dir).mkdir(parents=True, exist_ok=True) - - # Initialize - set_logging() - device = select_device(opt.device) - half = device.type != 'cpu' # half precision only supported on CUDA - - # Load model - model = attempt_load(weights, map_location=device) # load FP32 model - stride = int(model.stride.max()) # model stride - imgsz = check_img_size(imgsz, s=stride) # check img_size - - if trace: - model = TracedModel(model, device, opt.img_size) - - if half: - model.half() # to FP16 - - # Second-stage classifier - classify = False - if classify: - modelc = load_classifier(name='resnet101', n=2) # initialize - modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval() - - # Set Dataloader - watch_dir = True - vid_path, vid_writer = None, None - if watch_dir: - dataset = LoadFromDir(source, img_size=imgsz, stride=stride, log_dir=opt.log_dir) - elif webcam: - view_img = check_imshow() - cudnn.benchmark = True # set True to speed up constant image size inference - dataset = LoadStreams(source, img_size=imgsz, stride=stride) - else: - dataset = LoadImages(source, img_size=imgsz, stride=stride) - - # Get names and colors - names = model.module.names if hasattr(model, 'module') else model.names - colors = [[random.randint(0, 255) for _ in range(3)] for _ in names] - - # Run inference - if device.type != 'cpu': - model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once - old_img_w = old_img_h = imgsz - old_img_b = 1 - - t0 = time.time() - for path, img, im0s, vid_cap in dataset: - img = torch.from_numpy(img).to(device) - img = img.half() if half else img.float() # uint8 to fp16/32 - img /= 255.0 # 0 - 255 to 0.0 - 1.0 - if img.ndimension() == 3: - img = img.unsqueeze(0) - - # Warmup - if device.type != 'cpu' and (old_img_b != img.shape[0] or old_img_h != img.shape[2] or old_img_w != img.shape[3]): - old_img_b = img.shape[0] - old_img_h = img.shape[2] - old_img_w = img.shape[3] - for i in range(3): - model(img, augment=opt.augment)[0] - - # Inference - t1 = time_synchronized() - pred = model(img, augment=opt.augment)[0] - t2 = time_synchronized() - - # Apply NMS - pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms) - t3 = time_synchronized() - - # Apply Classifier - if classify: - pred = apply_classifier(pred, modelc, img, im0s) - - # Process detections - for i, det in enumerate(pred): # detections per image - if webcam: # batch_size >= 1 - p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count - else: - p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0) - - p = Path(p) # to Path - save_path = str(log_dir / Path('images') / p.name) # img.jpg - txt_path = str(log_dir / Path('labels') / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt - gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh - if len(det): - # Rescale boxes from img_size to im0 size - det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() - - # Print results - for c in det[:, -1].unique(): - n = (det[:, -1] == c).sum() # detections per class - s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string - - # Write results - for *xyxy, conf, cls in reversed(det): - if save_txt: # Write to file - xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh - line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh) # label format - with open(txt_path + '.txt', 'a') as f: - f.write(('%g ' * len(line)).rstrip() % line + '\n') - - if save_img or view_img: # Add bbox to image - label = f'{names[int(cls)]} {conf:.2f}' - plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=1) - - # Print time (inference + NMS) - print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS') - - # Stream results - if view_img: - cv2.imshow(str(p), im0) - cv2.waitKey(1) # 1 millisecond - - # Save results (image with detections) - if save_img: - if dataset.mode == 'image': - write_flag = cv2.imwrite(save_path, im0) - if not write_flag: - print('! Image write error') - print(f" The image with the result is saved in: {save_path}") - else: # 'video' or 'stream' - if vid_path != save_path: # new video - vid_path = save_path - if isinstance(vid_writer, cv2.VideoWriter): - vid_writer.release() # release previous video writer - if vid_cap: # video - fps = vid_cap.get(cv2.CAP_PROP_FPS) - w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) - h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) - else: # stream - fps, w, h = 30, im0.shape[1], im0.shape[0] - save_path += '.mp4' - vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) - vid_writer.write(im0) - - # Move image file to destination folder based on model output - if pred[0].shape[0] > 0: - print('plane') - shutil.move(path, os.path.join(plane_dir, os.path.basename(path))) - else: - shutil.move(path, os.path.join(noplane_dir, os.path.basename(path))) - print('noplane') - - if save_json: - struct = [] - for rowidx in range(pred[0].shape[0]): - row = pred[0][rowidx, :] - entry = {} - entry['bbox'] = row[:4].numpy().tolist() - entry['score'] = row[4].numpy().item() - entry['category_id'] = row[5].int().numpy().item() - struct.append(entry) - path = os.path.join( - log_dir, os.path.splitext(os.path.basename(path))[0] + '.json') - if len(struct) > 0: - json.dump(struct, open(path, 'w')) - - if save_txt or save_img: - s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else '' - #print(f"Results saved to {save_dir}{s}") - - print(f'Done. ({time.time() - t0:.3f}s)') - - -if __name__ == '__main__': - parser = argparse.ArgumentParser() - parser.add_argument('--weights', nargs='+', type=str, default='yolov7.pt', help='model.pt path(s)') - - parser.add_argument('--source-dir', type=str, - default='/data/edge_sandbox/tosort', - help='Folder of images to sort') - parser.add_argument('--plane-dir', type=str, - default='/data/edge_sandbox/plane', - help='Folder to save images of aircraft') - parser.add_argument('--noplane-dir', type=str, - default='/data/edge_sandbox/noplane', - help='Folder to save images lacking aircraft') - parser.add_argument('--log-dir', type=str, - default='/data/edge_sandbox/log', - help='Folder to store log information') - - #parser.add_argument('--source', type=str, default='inference/images', help='source') # file/folder, 0 for webcam - parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)') - parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold') - parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS') - parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') - parser.add_argument('--view-img', action='store_true', help='display results') - parser.add_argument('--save-txt', action='store_true', help='save results to *.txt') - parser.add_argument('--save-img', action='store_true', help='save image with bounding boxes') - parser.add_argument('--save-json', action='store_true', help='save results to *.json') - parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels') - parser.add_argument('--nosave', action='store_true', help='do not save images/videos') - parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3') - parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS') - parser.add_argument('--augment', action='store_true', help='augmented inference') - parser.add_argument('--update', action='store_true', help='update all models') - #parser.add_argument('--project', default='runs/detect', help='save results to project/name') - #parser.add_argument('--name', default='exp', help='save results to project/name') - #parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment') - parser.add_argument('--no-trace', action='store_true', help='don`t trace model') - opt = parser.parse_args() - print(opt) - #check_requirements(exclude=('pycocotools', 'thop')) - - with torch.no_grad(): - if opt.update: # update all models (to fix SourceChangeWarning) - for opt.weights in ['yolov7.pt']: - dirsort() - strip_optimizer(opt.weights) - else: - dirsort() diff --git a/edge-detect/docker-compose.yml b/edge-detect/docker-compose.yml deleted file mode 100644 index ee829c2..0000000 --- a/edge-detect/docker-compose.yml +++ /dev/null @@ -1,15 +0,0 @@ -version: '3.7' - -services: - skyscan-edge: - build: ./ai/ - command: "python sort.py --weights ../data/weights/localizer.pt --agnostic-nms --nosave --conf 0.25 --img-size 640 --device cpu --source-dir ../data/tosort --plane-dir ../data/plane --noplane-dir ../data/noplane --log-dir ../data/log --save-json & python processFiles.py" - environment: - - "HOSTNAME=${HOSTNAME}" - volumes: - - ./weights:/data/weights/ - - /flash/raw:/data/tosort - - /flash/processed/plane:/data/plane - - /flash/processed/noplane:/data/noplane - - /flash/processed/log:/data/log - restart: unless-stopped From 32ce09d9025f0045c9af06e47a191da28b8a5570 Mon Sep 17 00:00:00 2001 From: meadej Date: Mon, 13 Mar 2023 11:44:51 -0400 Subject: [PATCH 3/4] Ensured camera module was not saving JSON --- axis-ptz/camera.py | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/axis-ptz/camera.py b/axis-ptz/camera.py index ac3cf7e..3839337 100755 --- a/axis-ptz/camera.py +++ b/axis-ptz/camera.py @@ -532,10 +532,6 @@ def get_json_request(): A dictionary containing the contents os the JSON metadata file. """ image_filepath = _format_file_save_filepath(file_extension=".jpg") - filepath = os.path.join( - logging_directory, - os.path.basename(_format_file_save_filepath(file_extension=".json")) - ) file_content_dictionary = { "timestamp": datetime.now().strftime("%Y-%m-%d-%H-%M-%S"), @@ -556,12 +552,6 @@ def get_json_request(): } } - try: - with open(filepath, "w") as fh: - fh.write(json.dumps(file_content_dictionary)) - except Exception as e: - print("Error saving JSON log - " + str(e)) - return file_content_dictionary From 333d6dc87e9adab3ba26a8a65f468333d224b2b9 Mon Sep 17 00:00:00 2001 From: meadej Date: Mon, 13 Mar 2023 11:46:19 -0400 Subject: [PATCH 4/4] Explicit initialization added back in --- axis-ptz/camera.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/axis-ptz/camera.py b/axis-ptz/camera.py index 3839337..cb7a982 100755 --- a/axis-ptz/camera.py +++ b/axis-ptz/camera.py @@ -80,6 +80,9 @@ camera_yaw = 0 currentPlane = None +camera_altitude = None +camera_latitude = None +camera_longitude = None camera_lead = None include_age = strtobool(os.getenv("INCLUDE_AGE", "True"))