PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
机器配置
[12/09 06:21:57] ppgan INFO: Downloading DF2K_JPEG.pdparams from https://paddlegan.bj.bcebos.com/applic
ations/DF2K_JPEG.pdparams to C:\Users\Administrator.cache\ppgan\DF2K_JPEG.pdparams
100%|█████████████████████████████████████████████████████████| 65294/65294 [00:33<00:00, 1938.92it/s]
Traceback (most recent call last):
File "tools/video-enhance.py", line 148, in
frames_path, temp_video_path = predictor.run(temp_video_path)
File "d:\code\paddlegan-develop\ppgan\apps\realsr_predictor.py", line 109, in run
pred_img = self.run_image(input)
File "d:\code\paddlegan-develop\ppgan\apps\realsr_predictor.py", line 64, in run_image
out = self.model(x)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\paddle\fluid\dy
graph\layers.py", line 914, in call
outputs = self.forward(*inputs, *kwargs)
File "d:\code\paddlegan-develop\ppgan\models\generators\rrdb_net.py", line 92, in forward
self.upconv2(F.interpolate(fea, scale_factor=2, mode='nearest')))
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\paddle\fluid\dy
graph\layers.py", line 914, in call
outputs = self.forward(inputs, *kwargs)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\paddle\nn\layer
\conv.py", line 677, in forward
use_cudnn=self._use_cudnn)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\paddle\nn\funct
ional\conv.py", line 123, in _conv_nd
pre_bias = getattr(_C_ops, op_type)(x, weight, attrs)
MemoryError: (ResourceExhausted) Fail to alloc memory of 50099286016 size.
[Hint: p should not be null.] (at C:\home\workspace\Paddlerelease\paddle\fluid\memory\detail\system
allocator.cc:65)
[operator < conv2d > error]
机器配置 [12/09 06:21:57] ppgan INFO: Downloading DF2K_JPEG.pdparams from https://paddlegan.bj.bcebos.com/applic ations/DF2K_JPEG.pdparams to C:\Users\Administrator.cache\ppgan\DF2K_JPEG.pdparams 100%|█████████████████████████████████████████████████████████| 65294/65294 [00:33<00:00, 1938.92it/s] Traceback (most recent call last): File "tools/video-enhance.py", line 148, in
frames_path, temp_video_path = predictor.run(temp_video_path)
File "d:\code\paddlegan-develop\ppgan\apps\realsr_predictor.py", line 109, in run
pred_img = self.run_image(input)
File "d:\code\paddlegan-develop\ppgan\apps\realsr_predictor.py", line 64, in run_image
out = self.model(x)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\paddle\fluid\dy
graph\layers.py", line 914, in call
outputs = self.forward(*inputs, *kwargs)
File "d:\code\paddlegan-develop\ppgan\models\generators\rrdb_net.py", line 92, in forward
self.upconv2(F.interpolate(fea, scale_factor=2, mode='nearest')))
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\paddle\fluid\dy
graph\layers.py", line 914, in call
outputs = self.forward(inputs, *kwargs)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\paddle\nn\layer
\conv.py", line 677, in forward
use_cudnn=self._use_cudnn)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\paddle\nn\funct
ional\conv.py", line 123, in _conv_nd
pre_bias = getattr(_C_ops, op_type)(x, weight, attrs)
MemoryError: (ResourceExhausted) Fail to alloc memory of 50099286016 size.
[Hint: p should not be null.] (at C:\home\workspace\Paddlerelease\paddle\fluid\memory\detail\system
allocator.cc:65)
[operator < conv2d > error]
执行命令 python tools/video-enhance.py --input C:/Users/Administrator/Desktop/061249.p ng --process_order DeOldify RealSR --output C:/Users/Administrator/Desktop/