-
I get the following ValueError when converting a keras model (trained on a GPU with CuDNN layers) to onnx:
ValueError: Node 'sequential_1/dropout_1/cond/mul/y': Unknown input node '^sequential_1/dr…
ghost updated
5 years ago
-
都配置好了？
-
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
in ()
251 FLAGS = enrich_options(FLA…
-
# general warnings
```
WARNING:tensorflow:From C:\Users\ril_l\repo\ai-study\assignment_5\reader.py:120: range_input_producer (from tensorflow.python.training.input) is deprecated and will be removed…
-
I wish to implement clstm's network architecture in Keras, to facilitate extension and modifications to the network, and also to add gpu support.
I'm pretty much a newbie to NNs, and I'm trying to …
-
@usimarit, I was looking into WER computation and have a feeling you could be overestimating the WER.
Here is one example (from conformer model I trained):
decode = "gentlemen he said in a hoarse …
-
Hi, can you approximate train time of 100k examples on Gtx 1080? I started it, seems very slow. Thanks.
-
Hi!
I am currently trying to start a simple training by following the instructions from the README.md. Everything works up to the point where I want to start the training.
Executing
```
pyth…
-
Has anyone successfully set up their environment for the code to run? I am repeatedly getting an error saying CUDNN_STATUS_EXECUTION_FAILED with an Internal error which "Failed to call T…
-
作者，您好，我在您的代码的基础上添加新模型BiGRU
def build_model(self, trainset_shape, model_name='Keras model', model_file=None):
"""
Build Keras model, eg. 'GRU', 'LSTM', 'DNN', 'BPNN', 'CUDNNLSTM', 'C…