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

59 commits

Author SHA1 Message Date
maggiezha
387f700c4c
add Intel Optimization for PyTorch 
Intel's optimization for PyTorch on CPU are added, you need to set "export OMP_NUM_THREADS=num physical cores" based on your CPU's core number
 2020-05-07 15:57:07 +10:00
maggiezha
150f877e19
adding CPU optimization 
export OMP_NUM_THREADS=num physical cores
export KMP_BLOCKTIME=0
export KMP_AFFINITY=granularity=fine,compact,1,0
https://software.intel.com/content/www/us/en/develop/articles/maximize-tensorflow-performance-on-cpu-considerations-and-recommendations-for-inference.html
 2020-05-07 15:51:45 +10:00
GrzegorzKarchNV
67a7d9c4eb
Merge pull request #482 from maggiezha/cpu-run 
Cpu run
 2020-05-06 21:27:26 +02:00
maggiezha
acf833f7e4
adding support for --cpu-run 2020-05-06 21:57:05 +10:00
maggiezha
3a6b667118
adding support for --cpu-run 2020-05-06 21:52:49 +10:00
maggiezha
342c4710fc
adding support for --cpu-run 2020-05-06 21:48:43 +10:00
maggiezha
0e986cc1f0
adding support for --cpu-run 2020-05-06 21:46:45 +10:00
maggiezha
ca43a1b1e5
adding support for --cpu-run 2020-05-06 21:42:43 +10:00
gkarch
d0d4df70a1 constant batch in TensorRT engine build 2020-05-06 13:01:08 +02:00
maggiezha
a4ce69a5a7
add support for --cpu-run 2020-05-06 20:58:45 +10:00
maggiezha
9268095bb1
add support for --cpu-run 2020-05-06 20:57:10 +10:00
maggiezha
3a11f10bfe
add support for --cpu-run 2020-05-06 20:50:59 +10:00
gkarch
b0ab215441 fixed trt inference 2020-04-27 16:05:33 +02:00
gkarch
063de87218 fixing trt tests 2020-04-20 17:01:35 +02:00
gkarch
1f7950aa9d fixed alerts from https://lgtm.com/projects/g/NVIDIA/DeepLearningExamples/rev/pr-8d221f6760830499933042c03fcd83605adbd98e 2020-04-03 18:28:20 +02:00
GrzegorzKarchNV
00ca1c4bcf
Update README.md 2020-04-03 13:44:16 +02:00
Przemek Strzelczyk
5e3b487b89 [Tacotron2/PyT] custom TensorRT backend on TensorRT Inference Server; Conversional AI demo; fixed checkpoints loading; fixed FP16 export to TensorRT 2020-04-02 17:18:26 +02:00
Rajeev Rao
4f42950e36 Initialize CUDA state before loading TRT engines in Tacotron sample 2020-03-03 09:56:54 -08:00
Przemek Strzelczyk
77a1bb917a [Tacotron2/PyT] Updates: better perf, better trt7 support, new logging, bug fixes 2020-02-28 15:36:14 +01:00
gkarch
480f1f9811 update perf table for taco2 trt 2019-12-18 11:45:17 +01:00
Rajeev Rao
42555b734b Minor README cleanup for TRT Tacotron2 example 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2019-12-17 14:33:59 -08:00
gkarch
e5bd631f77 fixed trt table 2019-12-17 16:54:41 +01:00
gkarch
684678086a fixed speedup factor 2019-12-17 16:51:22 +01:00
gkarch
82518bad2d fixed speedup in trt readme 2019-12-17 16:49:44 +01:00
gkarch
5dbb6c5b91 updated perf scripts 2019-12-17 16:48:08 +01:00
gkarch
3634315318 fixed tabs 2019-12-16 18:31:29 +01:00
gkarch
2992264d3a updated Tacotron2: included trt, new dllogger 2019-12-16 18:29:08 +01:00
nvpstr
7d772b8bc9
Merge pull request #299 from cschaefer26/tacotron2-fix-val-lo 
Fixed wrong val loss being logged
 2019-11-19 10:16:21 +01:00
Christian Schäfer
f0eede6bf8
Update train.py 
fixed logged val loss
 2019-11-15 09:46:46 +01:00
gkarch
09706537d2 updated tacotron2 trtis readme 2019-11-14 15:24:14 +01:00
GrzegorzKarchNV
4e00153ab5 added TRTIS demo to Tacotron2 (#281) 
* added TRTIS demo

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md
 2019-11-06 19:46:35 +01:00
maggiezha
075bca5742 update readme of notebook (#229) 
* updating notebook
* updating wav files
* updating examples
 2019-10-01 19:41:26 +02:00
maggiezha
c13e5f6704
Update README.md 
move requirements from notebook to readme
 2019-09-19 13:36:36 +10:00
maggiezha
6cbd0fa2a4
Update README.md 2019-09-19 13:31:17 +10:00
Przemek Strzelczyk
02b49acead [Tacotron2] Added denoiser and inference stats, fixed typos 2019-09-10 16:22:53 +02:00
gkarch
b8027d8914 added jupyter notebook 2019-09-03 18:40:29 +02:00
Krzysztof Kudrynski
ab85e6cc3d Updating Tacotron2_pyt (BatchNorm init fix), Resnet_tf (cosine LR), 
Transformer_pyt (bugfix)
 2019-08-13 15:01:10 +02:00
gkarch
b56f72bcd9 fixed audio 2019-07-30 15:01:15 +02:00
Grzegorz Karch
d0c6294695 removed cudnn-benchmark from tacotron2 perf command lines in the readme 2019-07-24 01:08:20 -07:00
Grzegorz Karch
7e5013fff9 fixed script names in the readme 2019-07-24 00:30:07 -07:00
Grzegorz Karch
bb7a4ac630 updated container version in the readme, changed order of benchmarking scripts 2019-07-23 15:50:02 -07:00
Grzegorz Karch
6c42c20948 updated readme, number of epochs in training scripts 2019-07-23 15:43:24 -07:00
Grzegorz Karch
87accc3073 updated performance benchmark command lines in the readme 2019-07-23 15:26:54 -07:00
Grzegorz Karch
25b3f2678a fixed inference results 2019-07-23 14:29:58 -07:00
Grzegorz Karch
979e291848 updated to 19.07 version 2019-07-23 12:45:37 -07:00
Przemek Strzelczyk
a644350589 Updating models and adding BERT/PyT 
Tacotron2+Waveglow/PyT
* AMP support
* Data preprocessing for Tacotron 2 training
* Fixed dropouts on LSTMCells

SSD/PyT
* script and notebook for inference
* AMP support
* README update
* updates to examples/*

BERT/PyT
* initial release

GNMT/PyT
* Default container updated to NGC PyTorch 19.05-py3
* Mixed precision training implemented using APEX AMP
* Added inference throughput and latency results on NVIDIA Tesla V100 16G
* Added option to run inference on user-provided raw input text from command line

NCF/PyT
* Updated performance tables.
* Default container changed to PyTorch 19.06-py3.
* Caching validation negatives between runs

Transformer/PyT
* new README
* jit support added

UNet Medical/TF
* inference example scripts added
* inference benchmark measuring latency added
* TRT/TF-TRT support added
* README updated

GNMT/TF
* Performance improvements

Small updates (mostly README) for other models.
 2019-07-16 21:13:08 +02:00
Przemek Strzelczyk
0663b67c1a Updating models 2019-07-08 22:51:28 +02:00
nvpstr
f89dcca19d
Merge pull request #89 from GrzegorzKarchNV/readme-epochs 
changed number of epochs in train scripts; removed number of epochs f…
 2019-07-01 11:44:01 +02:00
Grzegorz Karch
d7c20e5bfc fixed batches for mixed precision and fp32, added info when no input is provided for inference, added units to expected training time 2019-06-27 01:48:46 -07:00
Grzegorz Karch
7eb5eece14 changed number of epochs in train scripts; removed number of epochs from readme for the audio samples 2019-06-26 08:57:23 -07:00