Can dispatching batches with different src_len degrade performance in synchronous training
|
|
4
|
1104
|
August 22, 2017
|
OpenCL instead of CUDA
|
|
3
|
1625
|
August 18, 2017
|
Gradient checking
|
|
2
|
1120
|
August 16, 2017
|
Adaptive Learning in OpenNMT
|
|
10
|
2335
|
August 4, 2017
|
How to use multi-GPU parallel training with an old commit on Feb 23
|
|
1
|
988
|
July 25, 2017
|
-train_from and train_from_state_dict
|
|
3
|
1272
|
June 30, 2017
|
Add support for distributed training on multiple CPU only nodes
|
|
1
|
1667
|
June 28, 2017
|
Can we use language translation model for Hindi to English translation?
|
|
1
|
1315
|
June 27, 2017
|
outputs.backward(gradOutput)
|
|
6
|
1836
|
June 22, 2017
|
What's the difference between model.zero_grad() and optim.zero_grad()
|
|
1
|
7685
|
June 21, 2017
|
Need a proper understanding of the preprocess step
|
|
4
|
2791
|
June 12, 2017
|
Having issue while preprocessing the data
|
|
0
|
1206
|
June 10, 2017
|
Different RNN architecture for each layer of Encoder
|
|
2
|
2265
|
June 8, 2017
|
Further Memory Optimization
|
|
0
|
1095
|
June 1, 2017
|
Coding environment for the framework
|
|
1
|
820
|
May 26, 2017
|
Validating trained model
|
|
6
|
1448
|
May 16, 2017
|
Efficient implementation for training with uneven batch
|
|
2
|
1153
|
April 7, 2017
|
CUDA translation support
|
|
4
|
2281
|
March 22, 2017
|
GPU offloading in CTranslate
|
|
0
|
1539
|
March 17, 2017
|
How to get flatten parameters, gradient of Encoder & Decoder? (Encoder:getParameters() work?)
|
|
1
|
1104
|
March 14, 2017
|
Comparing OpenNMT and PyOpenNMT efficiency
|
|
0
|
2021
|
February 24, 2017
|
Changing training criteria of Seq2Seq model
|
|
1
|
1466
|
March 6, 2017
|
Adding biased decoding
|
|
3
|
1288
|
March 5, 2017
|
Attention on a specific word in the context
|
|
27
|
6805
|
February 23, 2017
|
How should I choose parameters?
|
|
0
|
967
|
February 18, 2017
|
Performance analysis number
|
|
1
|
1770
|
January 26, 2017
|
Improving the gpuid option
|
|
4
|
2056
|
January 18, 2017
|
Model specification
|
|
0
|
860
|
December 23, 2016
|
Remove factored-geneartion from Beam Search
|
|
0
|
803
|
December 23, 2016
|
Training.lua as a library
|
|
0
|
834
|
December 23, 2016
|