sh1newu / SepMark

SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection
40 stars 8 forks source link

Asking for help #8

Open JusticeByLu opened 3 months ago

JusticeByLu commented 3 months ago

Thank you for providing the code, but I encountered an issue during the replication process. There was a missing image error while executing the training file Dual-Mark_main.cy. The dataset was downloaded from the provided link. The error is as follows: Start training :

cuda Traceback (most recent call last): File "D:\PyCharm_workspace\copyrightprotection\SepMark-main\Dual_Mark_main.py", line 193, in main() File "D:\PyCharm_workspace\copyrightprotection\SepMark-main\Dual_Mark_main.py", line 101, in main result = network.train(image, message, mask) File "D:\PyCharm_workspace\copyrightprotection\SepMark-main\network\Dual_Mark.py", line 52, in train encoded_images, noised_images, decoded_messages_C, decoded_messages_R, decoded_messages_F = self.encoder_decoder(images, messages, masks) File "D:\Anaconda\Anaconda\envs\SepMark\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, kwargs) File "D:\Anaconda\Anaconda\envs\SepMark\lib\site-packages\torch\nn\parallel\data_parallel.py", line 166, in forward return self.module(*inputs[0], *kwargs[0]) File "D:\Anaconda\Anaconda\envs\SepMark\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(input, kwargs) File "D:\PyCharm_workspace\copyrightprotection\SepMark-main\network\DW_EncoderDecoder.py", line 23, in forward noised_image_C, noised_image_R, noised_image_F = self.noise([encoded_image, image, mask]) File "D:\Anaconda\Anaconda\envs\SepMark\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, *kwargs) File "D:\PyCharm_workspace\copyrightprotection\SepMark-main\network\Random_Noise.py", line 35, in forward noised_image_F[index] = random_noise_layer_F([forward_image[index].clone().unsqueeze(0), forward_cover_image[index].clone().unsqueeze(0), forward_mask[index].clone().unsqueeze(0)]) File "D:\Anaconda\Anaconda\envs\SepMark\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(input, **kwargs) File "D:\PyCharm_workspace\copyrightprotection\SepMark-main\network\noise_layers\simswap\test_one_image.py", line 61, in forward img_a = Image.open(pic_a).convert('RGB') File "D:\Anaconda\Anaconda\envs\SepMark\lib\site-packages\PIL\Image.py", line 3092, in open fp = builtins.open(filename, "rb") FileNotFoundError: [Errno 2] No such file or directory: '/home/likaide/sda4/wxs/Dataset/dual_watermark/celeba_256/val/168125.png'

sh1newu commented 2 months ago

Sorry for the late reply. If the issue hasn't been resolved, you should try downloading the entire dataset (celeba_256/val used for face swapping) and placing it in the correct location.