ming024
RuntimeError: mat1 and mat2 shapes cannot be multiplied (16x70 and 36x256)
Hello! I am working on my custom dataset. While running the train.py script, I get the following error:
Training: 0%| | 0/300000 [00:00<?, ?it/sPrepare training ... | 0/25 [00:00<?, ?it/s] Number of FastSpeech2 Parameters: 35076161 Removing weight norm... Traceback (most recent call last): File "train.py", line 258, in
main(args, configs) File "train.py", line 96, in main output = model(*(batch[2:])) File "/home/samin/anaconda3/envs/FastSpeech2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/samin/anaconda3/envs/FastSpeech2/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 166, in forward return self.module(*inputs[0], **kwargs[0]) File "/home/samin/anaconda3/envs/FastSpeech2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/samin/Study/TTS/tts_system/FastSpeech2/model/fastspeech2.py", line 116, in forward output = self.encoder(texts, src_masks) File "/home/samin/anaconda3/envs/FastSpeech2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/samin/Study/TTS/tts_system/FastSpeech2/transformer/Models.py", line 111, in forward enc_output = self.src_word_emb(src_seq) + self.position_enc[ File "/home/samin/anaconda3/envs/FastSpeech2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/samin/anaconda3/envs/FastSpeech2/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 103, in forward return F.linear(input, self.weight, self.bias) File "/home/samin/anaconda3/envs/FastSpeech2/lib/python3.7/site-packages/torch/nn/functional.py", line 1848, in linear return torch._C._nn.linear(input, weight, bias) RuntimeError: mat1 and mat2 shapes cannot be multiplied (16x70 and 36x256) Training: 0%| | 1/300000 [00:00<8:26:55, 9.86it/s] Epoch 1: 0%| | 0/25 [00:00<?, ?it/s]
Could you please provide any solution?
