Sorry to bother you, when I run the program, the following problem occurs
[INFO] global 000171; step 0170; step_loss: 0.7252; lr: 0.00e+00
[INFO] global 000181; step 0180; step_loss: 0.7251; lr: 0.00e+00
[INFO] global 000191; step 0190; step_loss: 0.7287; lr: 0.00e+00
epoch 0000; epoch_loss: 0.7207
Traceback (most recent call last):
File "training/transformer_model_fn.py", line 206, in
model_fn.train()
File "/root/pytorchtrans/potr-main/training/../training/seq2seq_model_fn.py", line 297, in train
eval_loss = self.evaluate_fn(e, _time)
File "/root/miniconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 26, in decorate_context
return func(*args, kwargs)
File "/root/pytorchtrans/potr-main/training/../training/seq2seq_model_fn.py", line 503, in evaluate_h36m
decoder_pred = self._model(
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, *kwargs)
File "/root/pytorchtrans/potr-main/data/../models/PoseTransformer.py", line 203, in forward
return self.forward_autoregressive(
File "/root/pytorchtrans/potr-main/data/../models/PoseTransformer.py", line 421, in forward_autoregressive
pose_code = self._pose_embedding(pred_pose)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(input, kwargs)
File "/root/pytorchtrans/potr-main/models/../models/PoseGCN.py", line 346, in forward
B, S, D = x.size()
ValueError: not enough values to unpack (expected 3, got 2)
I don't know how to solve this problem, hope to get your help, thank you
Sorry to bother you, when I run the program, the following problem occurs [INFO] global 000171; step 0170; step_loss: 0.7252; lr: 0.00e+00 [INFO] global 000181; step 0180; step_loss: 0.7251; lr: 0.00e+00 [INFO] global 000191; step 0190; step_loss: 0.7287; lr: 0.00e+00 epoch 0000; epoch_loss: 0.7207 Traceback (most recent call last): File "training/transformer_model_fn.py", line 206, in
model_fn.train()
File "/root/pytorchtrans/potr-main/training/../training/seq2seq_model_fn.py", line 297, in train
eval_loss = self.evaluate_fn(e, _time)
File "/root/miniconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 26, in decorate_context
return func(*args, kwargs)
File "/root/pytorchtrans/potr-main/training/../training/seq2seq_model_fn.py", line 503, in evaluate_h36m
decoder_pred = self._model(
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, *kwargs)
File "/root/pytorchtrans/potr-main/data/../models/PoseTransformer.py", line 203, in forward
return self.forward_autoregressive(
File "/root/pytorchtrans/potr-main/data/../models/PoseTransformer.py", line 421, in forward_autoregressive
pose_code = self._pose_embedding(pred_pose)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(input, kwargs)
File "/root/pytorchtrans/potr-main/models/../models/PoseGCN.py", line 346, in forward
B, S, D = x.size()
ValueError: not enough values to unpack (expected 3, got 2)
I don't know how to solve this problem, hope to get your help, thank you