-
in [this Stackoverflow answer](https://stackoverflow.com/a/49666510/1389680), Astrid uses LSTM as shown here, but additionally resets states after epochs. As a newcomer in LSTM usage, I wonder: Would …
jondo updated
6 years ago
-
On TF 1.4.0 with CUDA 8.0 and cuDNN 7, I get a segmentation fault if I use an orthogonal initializer for the `kernel_initializer` argument of `cudnn_rnn.CudnnLSTM` (the layers version not the op). I'm…
-
I am testing how to use CudnnLSTM, there is not a lot of documentation on this. In my own experiment, I found when use AdamOptimizer with CudnnLSTM, it always raises the following Exception.
I als…
boche updated
6 years ago
-
### System information
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**:
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: 16.04
- *…
-
INFO:tensorflow:Starting Queues.
2018-01-10 18:45:29.789178: E tensorflow/stream_executor/cuda/cuda_blas.cc:366] failed to create cublas handle: CUBLAS_STATUS_NOT_INITIALIZED
2018-01-10 18:45:29.843…
-
### System information
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**: No
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: Linux U…
samgd updated
6 years ago
-
### System information
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**: No
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: Windows…
-
Hi, I'm trying to implementing the attention mechanism in my project. However, my sequences have varying lengths and I’m using bucketing to solve the issue. Therefore, I define the LSTM input shape as…
-
I know the layer has just been added with limited features. The CuDNNLSTM layer works absolutely fine. But does it work with the Bidirectional wrapper?
OS: Windows10
Conda env
Keras version: mast…
-
I need to freeze lstm layer(using Bidirectional wrapper).
So I freeze layer using
`singleModel.layers[x].trainable = False`
But it seems to not be frozen.
After checking layer(by seeing # of Tr…