【Hackathon 8th No.23】Improved Training of Wasserstein GANs 论文复现 #1147
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
|
Thanks for your contribution! |
lijialin03
reviewed
Apr 29, 2025
| import paddle.nn as nn | ||
| import paddle.vision.transforms as transforms | ||
|
|
||
| from ..models.wgan_gp import WGAN_GP |
There was a problem hiding this comment.
运行时找会不到文件，改为动态修正的路径
ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.append(ROOT_DIR)
from models.wgan_gp import WGAN_GP
There was a problem hiding this comment.
嗯嗯好的，那就先关注跑通吧，我现在运行好像还是跑不通的
| nn.Linear(noise_dim, 512 * 4 * 4), | ||
| nn.BatchNorm1D(512 * 4 * 4), | ||
| nn.ReLU(), | ||
| lambda x: x.reshape([-1, 512, 4, 4]), |
There was a problem hiding this comment.
这里运行时会报错，Paddle 的 nn.Sequential 只能包含继承自 nn.Layer 的对象，不能包含 lambda 表达式，会触发 assert isinstance(layer, Layer) 错误，可以改为类似如下代码：
def __init__(self, noise_dim=100, output_channels=3):
super(CIFAR10Generator, self).__init__()
self.layers1 = nn.Sequential(
nn.Linear(noise_dim, 512 * 4 * 4),
nn.BatchNorm1D(512 * 4 * 4),
nn.ReLU(),
)
self.layers2 = nn.Sequential(
nn.Conv2DTranspose(512, 256, 4, 2, 1),
nn.BatchNorm2D(256),
nn.ReLU(),
nn.Conv2DTranspose(256, 128, 4, 2, 1),
nn.BatchNorm2D(128),
nn.ReLU(),
nn.Conv2DTranspose(128, output_channels, 4, 2, 1),
nn.Tanh(),
)
def forward(self, x):
x = self.layers1(x)
x = x.reshape([-1, 512, 4, 4])
x = self.layers2(x)
return x
| real_output = self.discriminator(real_data) | ||
| fake_output = self.discriminator(fake_data) | ||
|
|
||
| gp = self.gradient_penalty(real_data, fake_data) |
There was a problem hiding this comment.
运行过程中报错：RuntimeError: (Unavailable) The Op flatten_grad doesn't have any grad op. If you don't intend calculating higher order derivatives, please set create_graphto False. (at ../paddle/fluid/eager/api/generated/eager_generated/backwards/nodes.cc:15349)
|
以cifar这个case为例，目前我这边验证的状态是：
|
|
close due to the following PR is merged: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
PR types
PR changes
Describe