Pix2pix #2296
Merged
Pix2pix #2296
Conversation
This file contains hidden or 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
ceci3
reviewed
May 26, 2019
PaddleCV/gan/.pre-commit-config.yaml
Outdated
| @@ -0,0 +1,35 @@ | |||
| repos: | |||
| if args.crop_type == 'Centor': | ||
| img1 = CentorCrop(img1, args.crop_size, args.crop_size) | ||
| img2 = CentorCrop(img2, args.crop_size, args.crop_size) | ||
| elif args.crop_type == 'Random': |
There was a problem hiding this comment.
上面的get_preprocess_param 去掉crop_pos，这里可以直接调用RandomCrop
PaddleCV/gan/data_reader.py
Outdated
| img2 = (np.array(img2).astype('float32') / 255.0 - 0.5) / 0.5 | ||
| img2 = img2.transpose([2, 0, 1]) | ||
| if return_name: | ||
| #batch_out_1.append( |
PaddleCV/gan/data_reader.py
Outdated
| batch_out_2.append(img2) | ||
| batch_out_3.append(os.path.basename(files[0])) | ||
| else: | ||
| #batch_out_1.append( |
PaddleCV/gan/data_reader.py
Outdated
| if len(batch_out_1) == self.batch_size: | ||
| if return_name: | ||
| yield batch_out_1, batch_out_2, batch_out_3 | ||
| #yield batch_out_1 |
PaddleCV/gan/scripts/run_pix2pix.sh
Outdated
| #export FLAGS_reader_queue_speed_test_mode=True | ||
| export FLAGS_eager_delete_tensor_gb=0.0 | ||
| export FLAGS_fast_eager_deletion_mode=1 | ||
| export FLAGS_fraction_of_gpu_memory_to_use=0.01 |
PaddleCV/gan/trainer/Pix2pix.py
Outdated
| loss_name=dis_trainer.d_loss.name, | ||
| build_strategy=build_strategy) | ||
|
|
||
| #losses = [[], []] |
PaddleCV/gan/trainer/Pix2pix.py
Outdated
| 0], d_loss_real[0], d_loss_fake[0], batch_time)) | ||
|
|
||
| #losses[0].append(g_A_loss[0]) | ||
| #losses[1].append(d_A_loss[0]) |
PaddleCV/gan/util/config.py
Outdated
| add_arg('model_net', str, "cgan", "The model used.") | ||
| add_arg('dataset', str, "mnist", "The dataset used.") | ||
| add_arg('model_net', str, "Pix2pix", "The model used.") | ||
| add_arg('dataset', str, "cityscapes", "The dataset used.") |
| add_arg('norm_type', str, "batch_norm", "Which normalization to used") | ||
| add_arg('learning_rate', int, 0.0002, "the initialize learning rate") | ||
| add_arg('learning_rate', float, 0.0002, "the initialize learning rate") | ||
| add_arg('lambda_L1', float, 100.0, "the initialize learning rate") |
…2pix Conflicts: PaddleCV/gan/data_reader.py PaddleCV/gan/scripts/run_pix2pix.sh PaddleCV/gan/trainer/Pix2pix.py PaddleCV/gan/util/config.py
…2pix Conflicts: PaddleCV/gan/data_reader.py PaddleCV/gan/scripts/run_pix2pix.sh PaddleCV/gan/trainer/Pix2pix.py PaddleCV/gan/util/config.py
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
add pix2pix to models