eschmidbauer/DL-Art-School
1
0
Fork 0
forked from mrq/DL-Art-School
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Script updates

Browse Source
This commit is contained in:
James Betker 2020-12-29 20:24:41 -07:00
parent b84469e922
commit 9dc3c8f0ff
3 changed files with 22 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
codes/scripts/extract_square_images.py
View File

@ -19,9 +19,9 @@ def main():
# compression time. If read raw images during training, use 0 for faster IO speed.
opt['dest'] = 'file'
opt['input_folder'] = ['F:\\4k6k\\datasets\\images\\youtube\\images']
opt['save_folder'] = 'F:\\4k6k\\datasets\\images\\ge_full_1024'
opt['imgsize'] = 1024
opt['input_folder'] = ['F:\\4k6k\\datasets\\ns_images\\imagesets\\imgset4']
opt['save_folder'] = 'F:\\4k6k\\datasets\\ns_images\\256_unsupervised_new'
opt['imgsize'] = 256
#opt['bottom_crop'] = 120
save_folder = opt['save_folder']
@ -52,6 +52,7 @@ class TiledDataset(data.Dataset):
print("Error with ", path)
return None
if len(img.shape) == 2:
print("Skipping due to greyscale")
return None
# Perform explicit crops first. These are generally used to get rid of watermarks so we dont even want to
@ -61,7 +62,8 @@ class TiledDataset(data.Dataset):
h, w, c = img.shape
# Uncomment to filter any image that doesnt meet a threshold size.
if min(h,w) < 1024:
if min(h,w) < 256:
print("Skipping due to threshold")
return None
# We must convert the image into a square.
@ -70,13 +72,7 @@ class TiledDataset(data.Dataset):
img = img[(h - dim) // 2:dim + (h - dim) // 2, (w - dim) // 2:dim + (w - dim) // 2, :]
img = cv2.resize(img, (self.opt['imgsize'], self.opt['imgsize']), interpolation=cv2.INTER_AREA)
# I was having some issues with unicode filenames with cv2. Hence using PIL.
# cv2.imwrite(osp.join(self.opt['save_folder'], basename + ".jpg"), img, [cv2.IMWRITE_JPEG_QUALITY, self.opt['compression_level']])
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = (img * 255).astype(np.uint8)
img = Image.fromarray(img)
img.save(osp.join(self.opt['save_folder'], basename + ".jpg"), "JPEG", quality=self.opt['compression_level'], optimize=True)
cv2.imwrite(osp.join(self.opt['save_folder'], basename + ".jpg"), img, [cv2.IMWRITE_JPEG_QUALITY, self.opt['compression_level']])
return None
def __len__(self):

20
codes/scripts/extract_subimages_with_ref.py
View File

@ -13,19 +13,19 @@ import torch
def main():
split_img = False
opt = {}
opt['n_thread'] = 7
opt['n_thread'] = 4
opt['compression_level'] = 90 # JPEG compression quality rating.
# CV_IMWRITE_PNG_COMPRESSION from 0 to 9. A higher value means a smaller size and longer
# compression time. If read raw images during training, use 0 for faster IO speed.
opt['dest'] = 'file'
opt['input_folder'] = 'F:\\4k6k\\datasets\\images\youtube\\images_cook'
opt['save_folder'] = 'F:\\4k6k\\datasets\\images\\youtube_massive_cook'
opt['crop_sz'] = [512, 1024, 2048] # the size of each sub-image
opt['step'] = [256, 512, 1024] # step of the sliding crop window
opt['input_folder'] = 'F:\\4k6k\\datasets\\ns_images\\imagesets\\images'
opt['save_folder'] = 'F:\\4k6k\\datasets\\ns_images\\imagesets\\512_with_ref_new'
opt['crop_sz'] = [1024, 2048] # the size of each sub-image
opt['step'] = [700, 1200] # step of the sliding crop window
opt['exclusions'] = [[],[],[]] # image names matching these terms wont be included in the processing.
opt['thres_sz'] = 128 # size threshold
opt['resize_final_img'] = [.5, .25, .125]
opt['thres_sz'] = 256 # size threshold
opt['resize_final_img'] = [.5, .25]
opt['only_resize'] = False
opt['vertical_split'] = False
opt['input_image_max_size_before_being_halved'] = 5500 # As described, images larger than this dimensional size will be halved before anything else is done.
@ -245,7 +245,7 @@ class TiledDataset(data.Dataset):
for exc in exclusions:
if exc in path:
excluded = True
break;
break
if excluded:
continue
results.extend(self.get_for_scale(img, crop_sz, step, resize_factor, ref_resize_factor))
@ -262,6 +262,7 @@ def extract_single(opt, writer):
dataset = TiledDataset(opt)
dataloader = data.DataLoader(dataset, num_workers=opt['n_thread'], collate_fn=identity)
tq = tqdm(dataloader)
i = 0
for spl_imgs in tq:
if spl_imgs is None:
continue
@ -272,7 +273,8 @@ def extract_single(opt, writer):
imgs, path = imgs
if imgs is None or len(imgs) <= 1:
continue
path = path + "_" + lbl
path = f'{path}_{lbl}_{i}'
i += 1
ref_id = writer.write_reference_image(imgs[0], path)
for tile in imgs[1:]:
writer.write_tile_image(ref_id, tile)

7
codes/scripts/srflow_latent_space_playground.py
View File

@ -162,7 +162,8 @@ if __name__ == "__main__":
torch.backends.cudnn.benchmark = True
srg_analyze = False
parser = argparse.ArgumentParser()
parser.add_argument('-opt', type=str, help='Path to options YAML file.', default='../../options/train_exd_imgsetext_srflow_bigboi_frompsnr.yml')
parser.add_argument('-opt', type=str, help='Path to options YAML file.', default='../options/train_exd_imgsetext_srflow_bigboi_ganbase.yml')
#parser.add_argument('-opt', type=str, help='Path to options YAML file.', default='../../options/train_exd_imgsetext_srflow_bigboi_frompsnr.yml')
opt = option.parse(parser.parse_args().opt, is_train=False)
opt = option.dict_to_nonedict(opt)
utils.util.loaded_options = opt
@ -180,8 +181,8 @@ if __name__ == "__main__":
gen.eval()
mode = "feed_through" # temperature | restore | latent_transfer | feed_through
imgs_to_resample_pattern = "F:\\4k6k\\datasets\\ns_images\\adrianna\\val2\\lr\\*"
#imgs_to_resample_pattern = "F:\\4k6k\\datasets\\ns_images\\adrianna\\analyze\\analyze_xx\\*"
#imgs_to_resample_pattern = "F:\\4k6k\\datasets\\ns_images\\adrianna\\val2\\lr\\*"
imgs_to_resample_pattern = "F:\\4k6k\\datasets\\ns_images\\adrianna\\analyze\\analyze_xx\\*"
#imgs_to_resample_pattern = "F:\\4k6k\\datasets\\ns_images\\imagesets\\images-half\\*lanette*"
scale = 2
resample_factor = 2 # When != 1, the HR image is upsampled by this factor using a bicubic to get the local latents. E.g. set this to '2' to get 2x upsampling.