-
When I tries to use the bidirectional LSTM operator, I found some bugs and fixed parts of them. So, I've created https://github.com/gdh1995/TIM-VX/commit/9ae1832eb37e0a01b544b69f916d6244805d5641 to sh…
-
Every layer that gets created should get a unique name which shows up on the printout of the network. This name should then be used for retrieving the configuration from the modelwrapper initialisatio…
-
Hi, I got a error when I tried to execute create_model([6],bidirectional=True).
"List index out of range"
the problem came to line
temp = concatenate([bi_encoder_states[i],bi_encoder_stat…
-
RNN cannot be jit compiled, see error below:
```
Detected unsupported operations when trying to compile graph __inference_one_step_on_data_993[] on XLA_GPU_JIT: CudnnRNN (No registered 'CudnnRNN' Op…
-
### 🐛 Describe the bug
Hi,
I have noticed recently that PyTorch fails in a specific way when using the PackedSequence Class with MPS. I've replicated the issue using a fresh minimal conda environm…
-
I'm training a CRNN to do captcha recognition. Without CTC, it reach 90% sequence for certain type of captcha. The problem is it can only recognize captchas with similar character segmentation. So I t…
-
## ❓ Questions and Help
### Please note that this issue tracker is not a help form and this issue will be closed.
Ok, I need to script pytorch LSTM as when I do tracing it gets different answers w…
-
hi,when i run train,I have already encountered this problem：
NOTFoundError:key recog/rnn/bidirectional_rnn/fw/lstm_cell/biases/exponentialMovingAverage not found in checkpoint
Can anyone guide m…
-
-
### Description
So I want to turn below Keras code which uses bidirectional LSTM into transformer:
`lstmLayer = keras.layers.Bidirectional( keras.layers.CuDNNLSTM(args.rnnSize, return_sequences =…