tomowang
commented
5 years ago nation and gender will use basic CNN model to train
Open upupbo opened 5 years ago
tomowang
commented
5 years ago nation and gender will use basic CNN model to train
cb@ceo-pc:~/code/ocr1/id-card-ocr-master$ python train.py /home/cb/anaconda3/lib/python3.6/site-packages/torch/nn/modules/rnn.py:522: RuntimeWarning: RNN module weights are not part of single contiguous chunk of memory. This means they need to be compacted at every call, possibly greatly increasing memory usage. To compact weights again call flatten_parameters(). self.dropout, self.training, self.bidirectional, self.batch_first) Traceback (most recent call last): File "train.py", line 133, in
train('nation')
File "train.py", line 118, in train
cost = train_batch(crnn, train_iter)
File "train.py", line 103, in train_batch
cost = criterion(preds, text, preds_size, length) / batch_size
File "/home/cb/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/home/cb/anaconda3/lib/python3.6/site-packages/torch/nn/modules/loss.py", line 1332, in forward
self.zero_infinity)
File "/home/cb/anaconda3/lib/python3.6/site-packages/torch/nn/functional.py", line 1813, in ctc_loss
zero_infinity)
RuntimeError: input_lengths needs to have size to match batch_size