help wanted

[CYJnrclw]

Why did tcn model run wrong?

[cedricmoorejr]

@CYJnrlcw,

Could you provide a bit more information to pinpoint the issue? For example:

• What steps did you follow to run the model?
• Are there any error messages or logs you could share?
• What environment are you using (e.g., Python version, operating system, and dependencies)?

[CYJnrclw]

TCN( (tcn): EncoderDecoderNet( (encoder): Encoder( (module): Sequential( (conv_0): Conv1d(155, 64, kernel_size=(61,), stride=(1,), padding=(30,)) (cn_0): ChannelNorm() (relu_0): ReLU() (pool_0): MaxPool1d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (conv_1): Conv1d(64, 256, kernel_size=(61,), stride=(1,), padding=(30,)) (cn_1): ChannelNorm() (relu_1): ReLU() (pool_1): MaxPool1d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ) ) (middle_lstm): LSTM_Layer_tcn( (lstm): GRU(256, 64, batch_first=True, bidirectional=True) ) (decoder): Decoder( (module): Sequential( (up_0): Upsample(scale_factor=2.0, mode='nearest') (conv_0): ConvTranspose1d(256, 96, kernel_size=(61,), stride=(1,), padding=(30,)) (cn_0): ChannelNorm() (relu_0): ReLU() (up_1): Upsample(scale_factor=2.0, mode='nearest') (conv_1): ConvTranspose1d(96, 64, kernel_size=(61,), stride=(1,), padding=(30,)) (cn_1): ChannelNorm() (relu_1): ReLU() ) ) (fc1): Linear(in_features=64, out_features=32, bias=True) (fc2): Linear(in_features=32, out_features=10, bias=True) ) (max_pool): GlobalMaxPooling1D() ) len dataloader: 3519 RuntimeError: Given transposed=1, weight of size [256, 96, 61], expected input[10, 128, 14] to have 256 channels, but got 128 channels instead

[hamidrezaro]

@CYJnrclw Please provide which script you are running, and the data and model parameters you use to run that script.

[CYJnrclw]

python train_recognition.py --model tcn --dataloader v2 --modality 16