Rename files/folders for better structure

.gitignore

@@ -76,7 +76,7 @@ target/
 .ipynb_checkpoints/
 
 # exclude data from source control by default
-/data/
+/datasets/
 /saved_models/
 # Mac OS-specific storage files
 .DS_Store

Makefile

@@ -5,7 +5,6 @@
 #################################################################################
 
 PROJECT_DIR := $(shell dirname $(realpath $(lastword $(MAKEFILE_LIST))))
-BUCKET = [OPTIONAL] your-bucket-for-syncing-data (do not include 's3:https://')
 PROFILE = default
 PROJECT_NAME = CycleGAN-Tensorflow
 PYTHON_INTERPRETER = python3
@@ -27,7 +26,7 @@ requirements: test_environment
 
 ## Make Dataset
 data: requirements
- $(PYTHON_INTERPRETER) src/data/make_dataset.py
+ $(PYTHON_INTERPRETER) src/data/download_data.py
 
 ## Delete all compiled Python files
 clean:

README.md

@@ -14,33 +14,30 @@ Project Organization
  ├── LICENSE
  ├── Makefile <- Makefile with commands like `make data` or `make train`
  ├── README.md
- ├── data
- │   └── raw <- Raw data before any processing.
+ ├── datasets <- All datasets are stored here
  │
- ├── saved_models <- Checkpointed models and tensorboard summaries.
+ ├── saved_models <- Checkpointed models and tensorboard summaries
  │
  ├── setup.py <- makes project pip installable (pip install -e .) so src can be imported
- └── src <- Source code for use in this project.
+ └── src <- Source code for use in this project
      ├── __init__.py <- Makes src a Python module
   │
-  ├── train.py <- Run this to train.
+  ├── train.py <- Run this to train
   │
-  ├── test.py <- Run this to test.
+  ├── test.py <- Run this to test
   │
-     ├── pipeline <- Code for downloading or loading data 
+     ├── data <- Code for downloading or loading data 
      │   ├── data.py
      │   └── download_data.py
   │
-     ├── options <- Files for command line options
-     │   └── base_options.py
-  │
      ├── models <- Code for defining the network structure and loss functions
-  │   ├── __init__.py <- model helper functions
+  │   ├── __init__.py
      │   ├── network.py
-  │   ├── cyclegan.py
+  │   ├── cyclegan.py <- CycleGAN model class
      │   └── losses.py
   │
-     └── utils <- Utility files, including scripts for visualisation
+     └── utils <- Utility files
+     ├── options.py <- File for command line options
         └── image_history_buffer.py
 
 --------

setup.py

@@ -1,10 +1,8 @@
 from setuptools import find_packages, setup
 
-setup(
- name='src',
- packages=find_packages(),
- version='0.1.0',
- description='A Tensorflow implementation of CycleGAN using Eager Execution, tf.keras.layers, and tf.data.',
- author='Herbie Bradley',
- license='MIT',
-)
+setup(name='src',
+ packages=find_packages(),
+ version='0.1.0',
+ description='A Tensorflow implementation of CycleGAN using Eager Execution, tf.keras.layers, and tf.data.',
+ author='Herbie Bradley',
+ license='MIT')

src/pipeline/download_data.py → src/data/download_data.py

@@ -15,14 +15,10 @@ def download_data(dataset_id, download_location):
 
 if __name__ == "__main__":
  parser = argparse.ArgumentParser()
- parser.add_argument(
- "--dataset_id",
- type=str,
- default="horse2zebra",
- help="String identifying the dataset to download. For example, \
- 'horse2zebra', 'monet2photo', 'summer2winter_yosemite', 'apple2orange', etc")
- FLAGS, unparsed = parser.parse_known_args()
+ parser.add_argument("--dataset_id", type=str, default="horse2zebra", help="String identifying the dataset to download. For example, \
+ 'horse2zebra', 'monet2photo', 'summer2winter_yosemite', 'apple2orange', etc")
+ opt = parser.parse_args()
  project_dir = os.path.abspath(os.path.join(os.getcwd(), os.pardir, os.pardir))
  raw_data = os.path.join(project_dir, 'data', 'raw')
- download_data(FLAGS.dataset_id, download_location=raw_data)
+ download_data(opt.dataset_id, download_location=raw_data)
  # TODO: Add code to check if dataset is already there.