maxmustermann/DeepLearningExamples
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity
922 commits 6 branches 0 tags 118 MiB
Commit graph

922 commits

This branch
This branch
All branches
Author SHA1 Message Date
nv-kkudrynski 6f20c0823a
Merge pull request #735 from NVIDIA/pribalta-fix-unetind-readme 
[UNetInd] Add --gpus flag to docker run
 2020-11-02 15:25:40 +01:00
Pablo Ribalta Lorenzo 81e86366f3 Add --gpus flag to docker run 
Signed-off-by: Pablo Ribalta Lorenzo <pribalta@nvidia.com>
 2020-11-02 14:31:31 +01:00
Dabi Ahn fd32b990ac [CUDA-Optimized/FastSpeech] 
- support for PyTorch 1.7 and TensorRT 7.2
- limit sample audio file length
 2020-11-02 21:17:00 +08:00
alvarognvidia 2af0f03eed
Update README.md 2020-11-01 20:35:30 -08:00
nv-kkudrynski 475256f71d
Merge pull request #731 from NVIDIA/gh/release 
[FastPitch/PyT] updated checkpoints, multispeaker and text processing
 2020-10-30 18:01:05 +01:00
kkudrynski bec82593f5 [FastPitch/PyT] updated checkpoints, multispeaker and text processing 2020-10-30 15:06:02 +01:00
nv-kkudrynski 03c5a9fd9b
Merge pull request #728 from NVIDIA/gh/release 
[BERT/TF] TRT int8 and Triton
 2020-10-29 19:58:23 +01:00
kkudrynski 36a6985ebc [BERT/TF] TRT int8 and Triton 2020-10-29 19:56:24 +01:00
nv-kkudrynski e159774d3e
Merge pull request #722 from NVIDIA/gh/release 
[ELECTRA/TF2] Pretraining and other updates
 2020-10-26 12:23:03 +01:00
kkudrynski 96e1700988 [ELECTRA/TF2] Pretraining and other updates 2020-10-26 12:19:47 +01:00
Szymon Migacz 533f7444ae
[TXL/PyT] Fixed issue with AMP training together with gradient accumulation (#720) 2020-10-23 15:46:58 -07:00
nv-kkudrynski 8cbac004b5
Merge pull request #719 from NVIDIA/gh/release 
[FastPitch/PyT] Adding notebooks
 2020-10-21 17:36:41 +02:00
kkudrynski b2c72b284f [FastPitch/PyT] Adding notebooks 2020-10-21 17:31:40 +02:00
nv-kkudrynski d1b185459b
Merge pull request #718 from NVIDIA/gh/release 
[ConvNets/Pyt] Pretrained weights usage guidelines
 2020-10-21 17:24:37 +02:00
kkudrynski 9061083098 [ConvNets/Pyt] Pretrained weights usage guidelines 2020-10-21 17:19:07 +02:00
nv-kkudrynski 0a120b2a1e
Merge pull request #715 from alvarognvidia/master 
updating features in the main readme
 2020-10-15 08:59:46 +02:00
alvarognvidia 3cf3a5c637 commit on 'master' 2020-10-15 04:57:22 +00:00
nv-kkudrynski ac059022a5
Merge pull request #714 from NVIDIA/gh/release 
[ConvNets/Pyt] Triton Deployment
 2020-10-14 20:48:18 +02:00
kkudrynski f217ab11a4 [COnvNets/Pyt] Triton Deployment 2020-10-14 20:43:50 +02:00
GrzegorzKarchNV 70f247fc34
Merge pull request #700 from KsenijaS/fix_div 
Fix integer division in Waveglow
 2020-10-07 22:04:39 +02:00
nv-kkudrynski e76b90017e
Merge pull request #692 from NVIDIA/unetmed_add_nccl_to_known_issues 
Add info about NCCL issue in 2.7.5 (20.06)
 2020-10-07 13:07:40 +02:00
nv-kkudrynski b1ce24a54f
Merge pull request #677 from GrzegorzKarchNV/convai-update 
updated convai
 2020-10-07 13:03:48 +02:00
gkarch 385d81eed0 a few fixes 2020-10-07 13:01:21 +02:00
gkarch 550123fbbc updated convai 2020-10-07 11:39:45 +02:00
nv-kkudrynski 0b27e359a5
Merge pull request #708 from NVIDIA/gh/release 
[FastPitch/PyT] Updating for 20.08
 2020-09-30 13:29:00 +02:00
kkudrynski d057babe5c [FastPitch/PyT] Updating for 20.08 2020-09-30 13:23:05 +02:00
Ksenija Stanojevic 421c83952c fix div 2020-09-24 21:13:07 -07:00
byshiue b2e89e6e80
[FT] FasterTransformer 3.0 Release (#696) 
[FT] feat: Add FasterTransformer v3.0

1. Add supporting of INT8 quantization of cpp and TensorFlow op.
2. Provide the tools to quantize the model.
3. Fix the bugs that cmake 3.15 and 3.16 cannot build this project. 
4. Deprecate the FasterTransformer v1
 2020-09-23 10:03:37 +08:00
byshiue 66d18913a1
Merge branch 'master' into master 2020-09-20 13:45:11 +08:00
nv-kkudrynski 94518be547
Merge pull request #693 from hXl3s/RN50/ngc-checkpoint-update 
[ConvNets/PyT] Fixed distributed checkpoint loading
 2020-09-18 13:03:46 +02:00
Łukasz Pierścieniewski 72f40b825a Fixed distributed checkpoint loading 2020-09-18 12:28:49 +02:00
Michał Marcinkiewicz 751bca168d
Update README.md 2020-09-18 10:27:26 +02:00
Sharath T S a74236afd4
[BERT/PyT] remove redundant section (#690) 2020-09-16 17:06:29 -07:00
Rajeev Rao aacbda693a
Update Jasper sample to TensorRT 7.1.3.4 (#687) 2020-09-15 22:58:04 +02:00
Sharath T S 482fe9ac8a
[BERT/PyT] fix onnx export (#689) 2020-09-15 12:44:10 -07:00
kkudrynski 437b950d5b Fixed links in readme 2020-09-14 23:58:38 +02:00
Szymon Migacz 6b82d3acb3
[TXL/PyT] Minor update for PyTorch Transformer-XL (#688) 2020-09-14 14:42:57 -07:00
nv-kkudrynski 152d0c0344
Merge pull request #684 from gpauloski/bert_pytorch_fix 
[BERT/PyT] Fix dataloader typo
 2020-09-11 18:40:26 +02:00
nv-kkudrynski 49e387c788
Merge pull request #633 from andabi/master 
remove pretrained aligns and update readme accordingly.
 2020-09-11 13:26:17 +02:00
nv-kkudrynski 1402e9403e
Update CUDA-Optimized/FastSpeech/README.md 
Co-authored-by: alancucki <alancucki@users.noreply.github.com>
 2020-09-11 13:23:41 +02:00
nv-kkudrynski cf54b787ae
fixed link 2020-09-10 15:48:54 +02:00
Greg Pauloski 7a4c42501c [BERT/PyT] Fix dataloader typo 2020-09-09 11:28:31 -05:00
kkudrynski 5d36b4fd2f Fixing hyperlinks 2020-09-08 16:10:32 +02:00
nv-kkudrynski 323005c443
Merge pull request #676 from NVIDIA/gh/release 
[DLRM/PyT] Triton updates
 2020-09-08 12:10:28 +02:00
kkudrynski 21fcdd6fcf [DLRM/PyT] Triton updates 2020-09-07 16:19:47 +02:00
Sharath T S 8588e9834c
[BERT/PyT] specify GPU for triton (#666) 2020-09-01 22:07:36 -07:00
Sharath T S 5cc03caa15
[BERT/PyT] Update pretrained checkpoint links (#660) 
* Update pretrained checkpoint links

* update link
 2020-08-21 13:34:05 -07:00
nv-kkudrynski 0e6cfbd0a1
Merge pull request #659 from hXl3s/RN50/readme-update 
[ConvNets/TF] Document synthetic dataset options
 2020-08-20 16:45:53 +02:00
Łukasz Pierścieniewski 8bd6dd14d3 Document synthetic dataset options 2020-08-20 16:21:50 +02:00
Sharath T S 446c878878
[ELECTRA/TF2] Update inference latency (#657) 
* Update inference latency

* Fix inference perf numbers

* Fix latency computation
 2020-08-19 20:43:44 -07:00