-
## Description
When using FusedRNNCell + MKLDNN backend: Graph optimization and Quantization (experimental), it leads to the QuantizedFullyConnectedOp Error like below,
MXNetError: Error in operat…
-
## 🐛 Bug
RuntimeError: param_from.type() == param_to.type() ASSERT FAILED at /opt/conda/conda-bld/pytorch_1533739672741/work/aten/src/ATen/native/cudnn/RNN.cpp:491, please report a bug to PyTorch. pa…
-
Could you please share the ROUGE-1, ROUGE-2 and ROUGE-L score on non-anonymized CNNDM using SummaRuRNN?
-
dear xin，
I was worked on consumer DataFlow，and def the class as：
class DataFlow(RNGDataFlow):
def __init__(self, data_path, batch_size):
self.batch_size = batch_size
…
-
Can someone please tell me how to run train2.py ?
I have already trained train1.py and tested it using eval1.py have a case generated as TIMIT_ACTUAL1 .
I do not understand what to use as the argu…
-
Hi,
I got a little confused of the figure in readme. It says the output shape of RNN is 256*64, but should it be 256*32 as the shape of the last RNN layer is 32?
-
Windows 10 Pro
Intel Core i7 6800K
tqdm 4.23.2
tensorflow 1.5.0
tensorpack 0.9.0
Here's my code:
$ py train1.py -case timit
case: timit, logdir: cases/timit/train1
[32m[1105 18:49:05 @logger.…
-
- [x] I'm up-to-date with the latest release (v 0.4.7:
pip install -U talos
- [x] I've confirmed that my Keras model works outside of Talos.
- input shape (4000, 1000) output shap…
shbfy updated
5 years ago
-
When running `kiwi train --config experiments/train_nuqe.yaml` I ran into the following error:
```
2019-02-26 15:48:32.631 [root setup:380] This is run ID: 9124ced8667849acb40f10a124109234
2019-0…
-
When setting `use_bias=True` for a `GRU` layer in a `Bidirectional` layer, we end up with `ERROR: invalid shape` in the C++ part.
---
Steps to quickly reproduce:
In `get_test_model_recurrent`…