search

ashawkey / RAD-NeRF

Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
MIT License
862 stars 151 forks source link

RuntimeError: Given input size: (192x2x2). Calculated output size: (192x0x0). Output size is too small #57

Open shiyueGG opened 1 year ago

shiyueGG commented 1 year ago

==> Start Training Epoch 123, lr=0.000049 ... loss=0.0002 (0.0011), lr=0.000045: : 4% 59/1647 [00:02<00:33, 47.29it/s]Traceback (most recent call last): File "main.py", line 235, in trainer.train(train_loader, valid_loader, max_epoch) File "/root/RAD-NeRF/nerf/utils.py", line 906, in train self.train_one_epoch(train_loader) File "/root/RAD-NeRF/nerf/utils.py", line 1169, in train_one_epoch preds, truths, loss = self.train_step(data) File "/root/RAD-NeRF/nerf/utils.py", line 766, in train_step loss = loss + 0.01 self.criterion_lpips(pred_rgb, rgb) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(input, kwargs) File "/root/miniconda3/lib/python3.8/site-packages/lpips/lpips.py", line 119, in forward outs0, outs1 = self.net.forward(in0_input), self.net.forward(in1_input) File "/root/miniconda3/lib/python3.8/site-packages/lpips/pretrained_networks.py", line 85, in forward h = self.slice3(h) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, *kwargs) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/container.py", line 141, in forward input = module(input) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(input, kwargs) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/pooling.py", line 162, in forward return F.max_pool2d(input, self.kernel_size, self.stride, File "/root/miniconda3/lib/python3.8/site-packages/torch/_jit_internal.py", line 422, in fn return if_false(*args, **kwargs) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/functional.py", line 797, in _max_pool2d return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode) RuntimeError: Given input size: (192x2x2). Calculated output size: (192x0x0). Output size is too small loss=0.0002 (0.0011), lr=0.000045: : 4% 60/1647 [00:02<01:05, 24.31it/s]

chanchanalina commented 1 year ago

Hi, I have the same problem，Have you found the solution yet？

seanko commented 9 months ago

可能是中间处理出来的数据有问题，我也是这这种情况，我看了一下中间数据处理都是马赛克

muximuxi commented 9 months ago

可能是中间处理出来的数据有问题，我也是这这种情况，我看了一下中间数据处理都是马赛克

请问侧脸数据可以处理吗？我现在有侧脸的，估计是嘴巴区域小了就运算不了，请问怎么解决？