-
This part of the code:
```
# Create the training and inference logits
train_logits, inference_logits = seq2seq_model(
tf.reverse(input_data, [-1]), targets, keep_prob, batch_size, sequence_l…
-
I'm trying to apply this awesome tool on BERT model. But it seems doesn's work with TF while loop. The model code is basically same as https://github.com/CLUEbenchmark/CLUENER2020/blob/master/tf_vers…
-
tensorflow==2.3.0
When fiting lstm with rnn set `stateful=True` using Orca, it seems that distrubuted training is not supported yet by origin tf.distribute?
```
Traceback (most recent call last):…
-
**System information**.
TensorFlow version (you are using): v2.7.0
Are you willing to contribute it (Yes/No) : Potentially, if the fix is easy enough.
**Describe the feature and the current beh…
-
NOTE: When I place the training file in the /data/tinyshakespear directory and run just: th train.lua -gpuid -0 -num_layers 3 -rnn_size 600 -eval_val_every 30000
the program runs.
But when I a…
-
I am getting nan outputs from the encoder of pruned transducer streaming model.
tensor([[[nan, nan, nan, ..., nan, nan, nan],
[nan, nan, nan, ..., nan, nan, nan],
[nan, nan, nan…
-
### 🐛 Describe the bug
Normally `call_for_per_sample_grads` detects inputs where it can't compute per sample gradients and throws user-friendly exception with the explanation.
However, in some scena…
-
I've been using the `recurrentshop-1` branch and unable to save models that have RecurrentModel layers in them. Here's an example using the `test_recurrent_model.py` in the tests.
```python
from r…
-
RNN + LSTM support now merged into Caffe, https://github.com/BVLC/caffe/pull/3948.
This paves the way for robust integration within dd.
beniz updated
6 years ago
-
Nice project
very intresting projects.
I tested it on nexus5 (snapdragon 800)
Are you planning to develop the project further?
for example
- new Nets: googlenet inception, squeezenet or etc
- new …