-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
57 changed files
with
331,984 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
.vscode | ||
__pycache__ | ||
experiments | ||
train_trm_coco.py |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,280 @@ | ||
|
||
import PIL.Image | ||
import random | ||
import numpy as np | ||
import pydensecrf.densecrf as dcrf | ||
from pydensecrf.utils import unary_from_softmax | ||
import os | ||
import cv2 | ||
|
||
class RandomResizeLong(): | ||
|
||
def __init__(self, min_long, max_long): | ||
self.min_long = min_long | ||
self.max_long = max_long | ||
|
||
def __call__(self, img, sal=None): | ||
|
||
target_long = random.randint(self.min_long, self.max_long) | ||
w, h = img.size | ||
|
||
if w < h: | ||
target_shape = (int(round(w * target_long / h)), target_long) | ||
else: | ||
target_shape = (target_long, int(round(h * target_long / w))) | ||
|
||
img = img.resize(target_shape, resample=PIL.Image.CUBIC) | ||
if sal: | ||
sal = sal.resize(target_shape, resample=PIL.Image.CUBIC) | ||
return img, sal | ||
return img | ||
|
||
|
||
class RandomCrop(): | ||
|
||
def __init__(self, cropsize): | ||
self.cropsize = cropsize | ||
|
||
def __call__(self, imgarr, sal=None): | ||
|
||
h, w, c = imgarr.shape | ||
|
||
ch = min(self.cropsize, h) | ||
cw = min(self.cropsize, w) | ||
|
||
w_space = w - self.cropsize | ||
h_space = h - self.cropsize | ||
|
||
if w_space > 0: | ||
cont_left = 0 | ||
img_left = random.randrange(w_space+1) | ||
else: | ||
cont_left = random.randrange(-w_space+1) | ||
img_left = 0 | ||
|
||
if h_space > 0: | ||
cont_top = 0 | ||
img_top = random.randrange(h_space+1) | ||
else: | ||
cont_top = random.randrange(-h_space+1) | ||
img_top = 0 | ||
|
||
container = np.zeros((self.cropsize, self.cropsize, imgarr.shape[-1]), np.float32) | ||
container[cont_top:cont_top+ch, cont_left:cont_left+cw] = \ | ||
imgarr[img_top:img_top+ch, img_left:img_left+cw] | ||
if sal is not None: | ||
container_sal = np.zeros((self.cropsize, self.cropsize,1), np.float32) | ||
container_sal[cont_top:cont_top+ch, cont_left:cont_left+cw,0] = \ | ||
sal[img_top:img_top+ch, img_left:img_left+cw] | ||
return container, container_sal | ||
|
||
return container | ||
|
||
def get_random_crop_box(imgsize, cropsize): | ||
h, w = imgsize | ||
|
||
ch = min(cropsize, h) | ||
cw = min(cropsize, w) | ||
|
||
w_space = w - cropsize | ||
h_space = h - cropsize | ||
|
||
if w_space > 0: | ||
cont_left = 0 | ||
img_left = random.randrange(w_space + 1) | ||
else: | ||
cont_left = random.randrange(-w_space + 1) | ||
img_left = 0 | ||
|
||
if h_space > 0: | ||
cont_top = 0 | ||
img_top = random.randrange(h_space + 1) | ||
else: | ||
cont_top = random.randrange(-h_space + 1) | ||
img_top = 0 | ||
|
||
return cont_top, cont_top+ch, cont_left, cont_left+cw, img_top, img_top+ch, img_left, img_left+cw | ||
|
||
def crop_with_box(img, box): | ||
if len(img.shape) == 3: | ||
img_cont = np.zeros((max(box[1]-box[0], box[4]-box[5]), max(box[3]-box[2], box[7]-box[6]), img.shape[-1]), dtype=img.dtype) | ||
else: | ||
img_cont = np.zeros((max(box[1] - box[0], box[4] - box[5]), max(box[3] - box[2], box[7] - box[6])), dtype=img.dtype) | ||
img_cont[box[0]:box[1], box[2]:box[3]] = img[box[4]:box[5], box[6]:box[7]] | ||
return img_cont | ||
|
||
|
||
def random_crop(images, cropsize, fills): | ||
if isinstance(images[0], PIL.Image.Image): | ||
imgsize = images[0].size[::-1] | ||
else: | ||
imgsize = images[0].shape[:2] | ||
box = get_random_crop_box(imgsize, cropsize) | ||
|
||
new_images = [] | ||
for img, f in zip(images, fills): | ||
|
||
if isinstance(img, PIL.Image.Image): | ||
img = img.crop((box[6], box[4], box[7], box[5])) | ||
cont = PIL.Image.new(img.mode, (cropsize, cropsize)) | ||
cont.paste(img, (box[2], box[0])) | ||
new_images.append(cont) | ||
|
||
else: | ||
if len(img.shape) == 3: | ||
cont = np.ones((cropsize, cropsize, img.shape[2]), img.dtype)*f | ||
else: | ||
cont = np.ones((cropsize, cropsize), img.dtype)*f | ||
cont[box[0]:box[1], box[2]:box[3]] = img[box[4]:box[5], box[6]:box[7]] | ||
new_images.append(cont) | ||
|
||
return new_images | ||
|
||
|
||
class AvgPool2d(): | ||
|
||
def __init__(self, ksize): | ||
self.ksize = ksize | ||
|
||
def __call__(self, img): | ||
import skimage.measure | ||
|
||
return skimage.measure.block_reduce(img, (self.ksize, self.ksize, 1), np.mean) | ||
|
||
|
||
class RandomHorizontalFlip(): | ||
def __init__(self): | ||
return | ||
|
||
def __call__(self, img, sal=None): | ||
if bool(random.getrandbits(1)): | ||
#img = img.transpose(PIL.Image.FLIP_LEFT_RIGHT) | ||
img = np.fliplr(img).copy() | ||
if sal: | ||
#sal = sal.transpose(PIL.Image.FLIP_LEFT_RIGHT) | ||
sal = np.fliplr(sal).copy() | ||
return img, sal | ||
return img | ||
else: | ||
if sal: | ||
return img, sal | ||
return img | ||
|
||
|
||
class CenterCrop(): | ||
|
||
def __init__(self, cropsize, default_value=0): | ||
self.cropsize = cropsize | ||
self.default_value = default_value | ||
|
||
def __call__(self, npimg): | ||
|
||
h, w = npimg.shape[:2] | ||
|
||
ch = min(self.cropsize, h) | ||
cw = min(self.cropsize, w) | ||
|
||
sh = h - self.cropsize | ||
sw = w - self.cropsize | ||
|
||
if sw > 0: | ||
cont_left = 0 | ||
img_left = int(round(sw / 2)) | ||
else: | ||
cont_left = int(round(-sw / 2)) | ||
img_left = 0 | ||
|
||
if sh > 0: | ||
cont_top = 0 | ||
img_top = int(round(sh / 2)) | ||
else: | ||
cont_top = int(round(-sh / 2)) | ||
img_top = 0 | ||
|
||
if len(npimg.shape) == 2: | ||
container = np.ones((self.cropsize, self.cropsize), npimg.dtype)*self.default_value | ||
else: | ||
container = np.ones((self.cropsize, self.cropsize, npimg.shape[2]), npimg.dtype)*self.default_value | ||
|
||
container[cont_top:cont_top+ch, cont_left:cont_left+cw] = \ | ||
npimg[img_top:img_top+ch, img_left:img_left+cw] | ||
|
||
return container | ||
|
||
|
||
def HWC_to_CHW(tensor, sal=False): | ||
if sal: | ||
tensor = np.expand_dims(tensor, axis=0) | ||
else: | ||
tensor = np.transpose(tensor, (2, 0, 1)) | ||
return tensor | ||
|
||
|
||
class RescaleNearest(): | ||
def __init__(self, scale): | ||
self.scale = scale | ||
|
||
def __call__(self, npimg): | ||
import cv2 | ||
return cv2.resize(npimg, None, fx=self.scale, fy=self.scale, interpolation=cv2.INTER_NEAREST) | ||
|
||
|
||
|
||
|
||
def crf_inference(img, probs, t=10, scale_factor=1, labels=21): | ||
import pydensecrf.densecrf as dcrf | ||
from pydensecrf.utils import unary_from_softmax | ||
|
||
h, w = img.shape[:2] | ||
n_labels = labels | ||
|
||
d = dcrf.DenseCRF2D(w, h, n_labels) | ||
|
||
unary = unary_from_softmax(probs) | ||
unary = np.ascontiguousarray(unary) | ||
|
||
d.setUnaryEnergy(unary) | ||
d.addPairwiseGaussian(sxy=3/scale_factor, compat=3) | ||
d.addPairwiseBilateral(sxy=80/scale_factor, srgb=13, rgbim=np.copy(img), compat=10) | ||
Q = d.inference(t) | ||
|
||
return np.array(Q).reshape((n_labels, h, w)) | ||
|
||
def crf_inference_ysh(name, probs, t=10, scale_factor=1, labels=21): | ||
|
||
image_path = os.path.join('./data/VOC2012/JPEGImages', name + '.jpg') | ||
img = cv2.imread(image_path, cv2.IMREAD_COLOR).astype(np.float32) | ||
img = np.ascontiguousarray(np.uint8(img)) | ||
|
||
h, w = img.shape[:2] | ||
n_labels = labels | ||
|
||
d = dcrf.DenseCRF2D(w, h, n_labels) | ||
|
||
unary = unary_from_softmax(probs) | ||
unary = np.ascontiguousarray(unary) | ||
|
||
d.setUnaryEnergy(unary) | ||
|
||
# d.addPairwiseGaussian(sxy=1, compat=3) # 64.85 | ||
# d.addPairwiseBilateral(sxy=67, srgb=3, rgbim=np.copy(img), compat=4) # 64.85 | ||
|
||
d.addPairwiseGaussian(sxy=1, compat=3) # 64.86/no normal | ||
d.addPairwiseBilateral(sxy=67, srgb=3, rgbim=np.copy(img), compat=4) #64.86/no normal | ||
|
||
# d.addPairwiseGaussian(sxy=3, compat=3) #RRM | ||
# d.addPairwiseBilateral(sxy=80, srgb=13, rgbim=np.copy(img), compat=10) #RRM t=10 | ||
|
||
# d.addPairwiseGaussian(sxy=1, compat=3) #good | ||
# d.addPairwiseBilateral(sxy=67, srgb=3, rgbim=np.copy(img), compat=4) #good | ||
|
||
# d.addPairwiseGaussian(sxy=2, compat=3,kernel=dcrf.DIAG_KERNEL,normalization=dcrf.NORMALIZE_SYMMETRIC) | ||
# d.addPairwiseBilateral(sxy=80, srgb=13, rgbim=np.copy(img),kernel=dcrf.DIAG_KERNEL, normalization=dcrf.NORMALIZE_SYMMETRIC,compat=4) #good | ||
|
||
# d.addPairwiseGaussian(sxy=2, compat=3, kernel=dcrf.DIAG_KERNEL, normalization=dcrf.NORMALIZE_SYMMETRIC) | ||
# d.addPairwiseBilateral(sxy=80, srgb=13, rgbim=np.copy(img), kernel=dcrf.DIAG_KERNEL,normalization=dcrf.NORMALIZE_SYMMETRIC, compat=4) # good | ||
|
||
|
||
Q = d.inference(t) | ||
|
||
return np.array(Q).reshape((n_labels, h, w)) |
Oops, something went wrong.