-
I built marain-1.6.0 then i get this,and when cmake .. (-- Found NCCL (include: /usr/local/include, library: /usr/local/lib/libnccl.so) , but i can't find ncclGroupStart in nccl.h, the specify info …
-
I built a 1-layer bidirectional RNN with 128 hidden nodes using the `output = tf.nn.bidirectional_dynamic_rnn(forward_cell, backward_cell, inputs, seqlens, tf.float32, is_tuple=True, time_major=True)`…
-
can someone tell me how many hidden layerss exist at this implementaion?
i think that 3 but not sure that i am right.
thanks
-
``` python3
H = hidden.repeat(max_len,1,1).transpose(0,1)
```
change to
``` python3
H = hidden.expand(max_len * hidden.size(0), -1, -1).transpose(0,1)
```
Dose it work ?
-
Hello,
I've been playing around with the DeepSpeech2 network. I am not seeing any speedup from using mixed precision (on a V100 GPU). As I was digging around to understand if this is normal, I foun…
-
Hi,There was nothing wrong when I configured the parameters to train the nematus model on GPU. But when I change the enc-depth from 1 to 2 and dec-depth from 1 to 2, the following error occurs.
I'm…
cong1 updated
6 years ago
-
Hi, I'm testing the speed of Average Attention Network for transformer in online system using marian-server, but marian-server doesn't support Average Attention Network for transformer. It report that…
-
Hi,
I am trying to deploy custom Keras model on Sagemaker. I am following the https://github.com/awslabs/amazon-sagemaker-examples/tree/master/sagemaker-python-sdk/tensorflow_keras_cifar10 example…
-
## Issue description
In `pytorch0.4.0`,
use dropout in multi-LSTM(GRU) when GPU index is not '0', will cause ` RuntimeError: cublas runtime error : resource allocation failed at /pytorch/aten/src/…
-
Just tried installing `g2p-seq2seq`, but both when I `python setup.py install` and try to run the pre-saved model with weights, I get that error :
```
ValueError: Attempt to reuse RNNCell with a…