Input and target shapes not matching

[tharindu-mathew]

I'm trying to train a custom dataset, and I'm running into this issue. I'm simply trying to match rgb image sequence to rgb image sequence.

Command: python train.py --name p_256_g1 \ --dataroot datasets/custom/ --dataset_mode temporal \ --input_nc 3 --loadSize 256 \ --max_frames_per_gpu 2 --n_frames_total 6 --gpu_ids 1,2,3,4 \ --n_downsample_G 2 --num_D 1 \ --no_first_img

Error: Traceback (most recent call last): File "train.py", line 329, in train() File "train.py", line 117, in train losses = modelD(0, reshape([real_B, fake_B, fake_B_raw, real_A, real_B_prev, fake_B_prev, flow, weight, flow_ref, conf_ref])) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call result = self.forward(*input, kwargs) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 114, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 124, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 65, in parallel_apply raise output File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 41, in _worker output = module(*input, *kwargs) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call result = self.forward(input, kwargs) File "/scratch2/mathewc/vid2vid/models/vid2vid_model_D.py", line 184, in forward loss_G_VGG = (self.criterionVGG(fake_B, real_B) lambda_feat) if not self.opt.no_vgg else torch.zeros_like(loss_W) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call result = self.forward(input, kwargs) File "/scratch2/mathewc/vid2vid/models/networks.py", line 756, in forward loss += self.weights[i] self.criterion(x_vgg[i], y_vgg[i].detach()) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call result = self.forward(input, kwargs) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/modules/loss.py", line 85, in forward reduce=self.reduce) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/functional.py", line 1558, in l1_loss input, target, size_average, reduce) File "/scratch2/mathewc/anaconda3/envs/vid2vid/lib/python3.6/site-packages/torch/nn/functional.py", line 1537, in _pointwise_loss return lambd_optimized(input, target, size_average, reduce) RuntimeError: input and target shapes do not match: input [1 x 64 x 128 x 256], target [2 x 64 x 128 x 256] at /opt/conda/conda-bld/pytorch_1524590031827/work/aten/src/THCUNN/generic/AbsCriterion.cu:15