Skip to content

Update some PyTorch examples for new API #191

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 10 commits into from
Dec 22, 2022
Merged

Update some PyTorch examples for new API #191

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
a6ad7e1
Update some PyTorch examples for new API
PenghuiCheng Nov 30, 2022
743fb99
Update some PyTorch examples to new API
PenghuiCheng Dec 2, 2022
30b57cd
Change nlp qa pipeline example with new API
PenghuiCheng Dec 3, 2022
f1aa252
Update examples of PyTorch with new APIs
PenghuiCheng Dec 14, 2022
daa2294
Fixed benchmark error and distillation error for nlp question-answering
PenghuiCheng Dec 15, 2022
152f4de
Update examples test config file
PenghuiCheng Dec 16, 2022
8ddfc72
Change benchmark mode to performance
PenghuiCheng Dec 16, 2022
642c2a5
Add num_of_instance for examples benchmark
PenghuiCheng Dec 18, 2022
cd40ec3
Fixed examples test error
PenghuiCheng Dec 21, 2022
225427d
Update README
PenghuiCheng Dec 22, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
27 changes: 5 additions & 22 deletions examples/.config/model_params_pytorch.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,28 +80,15 @@
"model_src_dir": "nlp/huggingface_models/question-answering/quantization/ptq_static/ipex",
"dataset_location": "",
"input_model": "",
"yaml": "conf.yaml",
"strategy": "basic",
"main_script": "run_qa.py",
"batch_size": 8,
"new_benchmark": false
},
"bert_large_ipex":{
"model_src_dir": "nlp/huggingface_models/question-answering/quantization/ptq_static/ipex",
"dataset_location": "",
"input_model": "",
"yaml": "conf.yaml",
"strategy": "basic",
"main_script": "run_qa.py",
"batch_size": 8,
"new_benchmark": false
},
"bert_large_1_10_ipex":{
"model_src_dir": "nlp/huggingface_models/question-answering/quantization/ptq_static/ipex",
"dataset_location": "/tf_dataset/pytorch/squad/dev-v1.1.json",
"input_model": "/tf_dataset/pytorch/bert_large_ipex",
"yaml": "conf.yaml",
"strategy": "basic",
"batch_size": 8,
"new_benchmark": false
},
"resnet50_gpu": {
"model_src_dir": "image_recognition/torchvision_models/quantization/ptq/gpu/eager/",
Expand Down Expand Up @@ -285,10 +272,8 @@
"model_src_dir": "nlp/huggingface_models/question-answering/quantization/ptq_static/fx",
"dataset_location": "",
"input_model": "",
"yaml": "conf.yaml",
"strategy": "basic",
"main_script": "run_qa.py",
"batch_size": 64,
"new_benchmark": false
},
"bert_large_QNLI": {
"model_src_dir": "nlp/huggingface_models/text-classification/quantization/ptq_static/fx",
Expand Down Expand Up @@ -546,10 +531,8 @@
"model_src_dir": "nlp/huggingface_models/language-modeling/quantization/ptq_static/fx",
"dataset_location": "",
"input_model": "/tf_dataset2/models/pytorch/gpt-j-6B",
"yaml": "conf.yaml",
"strategy": "basic",
"batch_size": 8,
"new_benchmark": false
"main_script": "run_clm.py",
"batch_size": 8
},
"xlm-roberta-base_MRPC": {
"model_src_dir": "nlp/huggingface_models/text-classification/quantization/ptq_static/eager",
Expand Down
6 changes: 3 additions & 3 deletions examples/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -445,7 +445,7 @@ Intel® Neural Compressor validated examples with multiple compression technique
<td>3D-UNet</td>
<td>Image Recognition</td>
<td>Post-Training Static Quantization</td>
<td><a href="./pytorch/image_recognition/3d-unet/quantization/ptq/eager">eager</a></td>
<td><a href="https://github.com/intel/neural-compressor/tree/old_api_examples/examples/pytorch/image_recognition/3d-unet/quantization/ptq/eager">eager</a></td>
</tr>
<tr>
<td>SSD ResNet34</td>
Expand All @@ -463,7 +463,7 @@ Intel® Neural Compressor validated examples with multiple compression technique
<td>YOLOv3</td>
<td>Object Detection</td>
<td>Post-Training Static Quantization</td>
<td><a href="./pytorch/object_detection/yolo_v3/quantization/ptq/eager">eager</a></td>
<td><a href="https://github.com/intel/neural-compressor/tree/old_api_examples/examples/pytorch/object_detection/yolo_v3/quantization/ptq/eager">eager</a></td>
</tr>
<tr>
<td>DLRM</td>
Expand Down Expand Up @@ -493,7 +493,7 @@ Intel® Neural Compressor validated examples with multiple compression technique
<td>BlendCNN</td>
<td>Natural Language Processing</td>
<td>Post-Training Static Quantization</td>
<td><a href="./pytorch/nlp/blendcnn/quantization/ptq/eager">eager</a></td>
<td><a href="https://github.com/intel/neural-compressor/tree/old_api_examples/examples/pytorch/nlp/blendcnn/quantization/ptq/eager">eager</a></td>
</tr>
<tr>
<td>bert-large-uncased-whole-word-masking-finetuned-squad</td>
Expand Down
1 change: 0 additions & 1 deletion examples/pytorch/image_recognition/3d-unet/quantization/ptq/eager/.dockerignore
View file
Open in desktop

This file was deleted.

1 change: 0 additions & 1 deletion examples/pytorch/image_recognition/3d-unet/quantization/ptq/eager/.gitignore
View file
Open in desktop

This file was deleted.

52 changes: 0 additions & 52 deletions examples/pytorch/image_recognition/3d-unet/quantization/ptq/eager/3DUnet_README.md
View file
Open in desktop

This file was deleted.

204 changes: 0 additions & 204 deletions examples/pytorch/image_recognition/3d-unet/quantization/ptq/eager/Makefile
View file
Open in desktop

This file was deleted.

Loading