提交 · 8761ab3d1d35d07d47767fad7fa380ffdeba3da7 · PaddlePaddle / models

27 6月, 2018 1 次提交
- G
  
  Code clean for fast_decoder of Transformer · 4eda2803
  由 guosheng 提交于 6月 26, 2018
  
  4eda2803
20 6月, 2018 2 次提交
- G
  
  Refine comments of batch_size in Transformer · 7da85c6c
  由 guosheng 提交于 6月 20, 2018
  
  7da85c6c
- G
  
  Fix weight sharing in Transformer inference · 99437ee9
  由 guosheng 提交于 6月 20, 2018
  
  99437ee9
19 6月, 2018 1 次提交
- G
  
  Refine Transformer for wmt14_en-de · 34601005
  由 guosheng 提交于 6月 19, 2018
  
  34601005
14 6月, 2018 1 次提交
- G
  Adapt to fill_batch_size_like and make outputs between fast_infer and the... · 07126083
  由 guosheng 提交于 6月 14, 2018
```
Adapt to fill_batch_size_like and make outputs between fast_infer and the original python infer alignment in Transformer
```
  07126083
08 6月, 2018 1 次提交
- G
  
  Make outputs between fast_infer and the original python infer alignment in Transformer · 3e9fccea
  由 guosheng 提交于 6月 08, 2018
  
  3e9fccea
24 5月, 2018 2 次提交
- G
  
  Make Transformer adapt to the latest api of ParallelExecutor · 056f8c48
  由 guosheng 提交于 5月 24, 2018
  
  056f8c48
- G
  
  Make step outputs between fast_infer and the original python infer alignment in Transformer · 82ba5c03
  由 guosheng 提交于 5月 24, 2018
  
  82ba5c03
22 5月, 2018 1 次提交
- G
  
  Make fast decoder run smoothly in Transformer · d963d69e
  由 guosheng 提交于 5月 22, 2018
  
  d963d69e
16 5月, 2018 1 次提交
- G
  
  Add beam search decoder in Transformer · dead21e4
  由 guosheng 提交于 5月 16, 2018
  
  dead21e4
11 5月, 2018 2 次提交
- G
  
  Refine docs of reader in Transformer by following comments · a3ed9b00
  由 guosheng 提交于 5月 11, 2018
  
  a3ed9b00
- G
  
  Refine docs and codes in Transformer by following comments · f0fc20ee
  由 guosheng 提交于 5月 11, 2018
  
  f0fc20ee
09 5月, 2018 1 次提交
- G
  
  Append args related to dict in Transformer · 8aa6740f
  由 guosheng 提交于 5月 09, 2018
  
  8aa6740f
08 5月, 2018 1 次提交
- G
  
  Add reader, ParallelExecutor and refine for Transformer · bca3c03d
  由 guosheng 提交于 5月 08, 2018
  
  bca3c03d
10 4月, 2018 1 次提交
- G
  
  Skip the part batches in Transformer when training · b34e8c0e
  由 guosheng 提交于 4月 10, 2018
  
  b34e8c0e
09 4月, 2018 1 次提交
- G
  
  Refine the pad_idx in Transformer · 91a0b7c6
  由 guosheng 提交于 4月 09, 2018
  
  91a0b7c6
08 4月, 2018 5 次提交
- G
  
  Remove pad_idx in Transformer · d2d973d2
  由 guosheng 提交于 4月 08, 2018
  
  d2d973d2
- G
  
  Avoid predicting <pad> by restricting the size of the final fc_layer in Transformer. · 10de2bf3
  由 guosheng 提交于 4月 08, 2018
  
  10de2bf3
- G
  
  Refine the validation in Transformer. · baa01f6f
  由 guosheng 提交于 4月 08, 2018
  
  baa01f6f
- G
  
  Append the <pad> token to the dict when converting ids to words · afe55c9e
  由 guosheng 提交于 4月 08, 2018
  
  afe55c9e
- G
  
  Increase the batch size in inference config of Transformer · f82f47ca
  由 guosheng 提交于 4月 08, 2018
  
  f82f47ca
04 4月, 2018 7 次提交
- G
  
  Refine the training output in Transformer by following comments · 40c68724
  由 guosheng 提交于 4月 04, 2018
  
  40c68724
- G
  
  Fix the merged conflicts in Transformer inference · 8ca89039
  由 guosheng 提交于 4月 04, 2018
  
  8ca89039
- G
  
  Refine Transformer by following comments · 70f9601b
  由 guosheng 提交于 4月 04, 2018
  
  70f9601b
- G
  
  Refine the training output in Transformer · ef88e63f
  由 guosheng 提交于 4月 04, 2018
  
  ef88e63f
- G
  
  Delete the test code in Transformer · ad1c3857
  由 guosheng 提交于 4月 04, 2018
  
  ad1c3857
- G
  
  Format the ppl output for Transformer · dc6e3748
  由 guosheng 提交于 4月 04, 2018
  
  dc6e3748
- G
  
  Add avg_cost and ppl for Transformer · a7196c88
  由 guosheng 提交于 4月 04, 2018
  
  a7196c88
03 4月, 2018 1 次提交
- G
  
  Refine the inference to output special tokens optionally in Transformer · 27fd97ce
  由 guosheng 提交于 4月 03, 2018
  
  27fd97ce
02 4月, 2018 1 次提交
- G
  
  Replace v2.dataset with dataset in Transformer · 40580c44
  由 guosheng 提交于 4月 02, 2018
  
  40580c44
30 3月, 2018 3 次提交
- G
  
  Replace cross_entropy with softmax_with_cross_entropy in Transformer · f853e70c
  由 guosheng 提交于 3月 30, 2018
  
  f853e70c
- G
  
  Refine Transformer by following comments. · cbd63162
  由 guosheng 提交于 3月 30, 2018
  
  cbd63162
- G
  
  Fix the softmax in Transformer. · bdacb3c6
  由 guosheng 提交于 3月 30, 2018
  
  bdacb3c6
29 3月, 2018 1 次提交
- G
  
  Fix the inference batch_size in Transformer. · ec70ff45
  由 guosheng 提交于 3月 29, 2018
  
  ec70ff45
28 3月, 2018 1 次提交
- G
  
  Decouple the program desc with batch_size in Transformer. · f3c247d3
  由 guosheng 提交于 3月 28, 2018
  
  f3c247d3
21 3月, 2018 1 次提交
- G
  
  Refine the log calculation in Transformer beam search · 6e896b08
  由 guosheng 提交于 3月 21, 2018
  
  6e896b08
20 3月, 2018 1 次提交
- G
  
  Refine Transformer by following comments and fix the target self attention bias in inference. · 6ef54e8e
  由 guosheng 提交于 3月 20, 2018
  
  6ef54e8e
19 3月, 2018 1 次提交
- X
  Add program caching · 82ed8380
  由 Xin Pan 提交于 3月 19, 2018
```
Reduce step time from 0.2 to 0.15
```
  82ed8380
13 3月, 2018 1 次提交
- G
  
  Add inference program for Transformer. · ff80721e
  由 guosheng 提交于 3月 13, 2018
  
  ff80721e
09 3月, 2018 1 次提交
- G
  
  Add initializer for Transformer. · a9159a8d
  由 guosheng 提交于 3月 09, 2018
  
  a9159a8d

PaddlePaddle / models 1 年多 前同步成功

PaddlePaddle / models
1 年多前同步成功