Add PT2E cv&llm example (#1853)

Signed-off-by: Kaihui-intel <[email protected]>
intel · Jun 14, 2024 · b401b02 · b401b02
1 parent e470f6c
commit b401b02
Show file tree

Hide file tree

Showing 11 changed files with 926 additions and 54 deletions.
diff --git a/docs/3x/PT_StaticQuant.md b/docs/3x/PT_StaticQuant.md
@@ -1,6 +1,5 @@
 PyTorch Static Quantization
 ========================================
-
 1. [Introduction](#introduction)
 2. [Get Started](#get-started) \
     2.1 [Static Quantization with IPEX Backend](#static-quantization-with-ipex-backend) \
@@ -9,6 +8,7 @@ PyTorch Static Quantization
         2.1.3 [Model Examples](#model-examples) \
     2.2 [Static Quantization with PT2E Backend](#static-quantization-with-pt2e-backend) \
         2.2.1 [Usage Sample with PT2E](#usage-sample-with-pt2e)
+        2.2.2 [Model Examples with PT2E](#model-examples-with-pt2e)
 
 
 ## Introduction
@@ -102,3 +102,7 @@ opt_model = torch.compile(q_model)
 ```
 
 > Note: The `set_local` of `StaticQuantConfig` will be supported after the torch 2.4 release.
+
+#### Model Examples with PT2E
+
+Users could refer to [cv examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/cv/static_quant) and [llm examples](https://github.com/intel/neural-compressor/blob/master/examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/static_quant/pt2e) on how to quantize a new model.
diff --git a/examples/.config/model_params_pytorch_3x.json b/examples/.config/model_params_pytorch_3x.json
@@ -1,53 +1,67 @@
-{
-    "pytorch": {
-      "gpt_j_ipex":{
-        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/static_quant",
-        "dataset_location": "",
-        "input_model": "",
-        "main_script": "run_clm_no_trainer.py",
-        "batch_size": 1
-      },
-      "gpt_j_ipex_sq":{
-        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/smooth_quant",
-        "dataset_location": "",
-        "input_model": "",
-        "main_script": "run_clm_no_trainer.py",
-        "batch_size": 1
-      },
-      "llama2_7b_ipex":{
-        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/static_quant",
-        "dataset_location": "",
-        "input_model": "",
-        "main_script": "run_clm_no_trainer.py",
-        "batch_size": 1
-      },
-      "llama2_7b_ipex_sq":{
-        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/smooth_quant",
-        "dataset_location": "",
-        "input_model": "",
-        "main_script": "run_clm_no_trainer.py",
-        "batch_size": 1
-      },
-      "opt_125m_ipex":{
-        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/static_quant",
-        "dataset_location": "",
-        "input_model": "",
-        "main_script": "run_clm_no_trainer.py",
-        "batch_size": 8
-      },
-      "opt_125m_ipex_sq":{
-        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/smooth_quant",
-        "dataset_location": "",
-        "input_model": "",
-        "main_script": "run_clm_no_trainer.py",
-        "batch_size": 8
-      },
-      "dlrm_ipex": {
-        "model_src_dir": "recommendation/dlrm/static_quant/ipex",
-        "dataset_location": "/mnt/local_disk3/dataset/dlrm/dlrm/input",
-        "input_model": "/mnt/local_disk3/dataset/dlrm/dlrm/dlrm_weight/tb00_40M.pt",
-        "main_script": "dlrm_s_pytorch.py",
-        "batch_size": 16384
-      }
-    }
-}
+{
+    "pytorch": {
+      "gpt_j_ipex":{
+        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/static_quant",
+        "dataset_location": "",
+        "input_model": "",
+        "main_script": "run_clm_no_trainer.py",
+        "batch_size": 1
+      },
+      "gpt_j_ipex_sq":{
+        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/smooth_quant",
+        "dataset_location": "",
+        "input_model": "",
+        "main_script": "run_clm_no_trainer.py",
+        "batch_size": 1
+      },
+      "llama2_7b_ipex":{
+        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/static_quant",
+        "dataset_location": "",
+        "input_model": "",
+        "main_script": "run_clm_no_trainer.py",
+        "batch_size": 1
+      },
+      "llama2_7b_ipex_sq":{
+        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/smooth_quant",
+        "dataset_location": "",
+        "input_model": "",
+        "main_script": "run_clm_no_trainer.py",
+        "batch_size": 1
+      },
+      "opt_125m_ipex":{
+        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/static_quant",
+        "dataset_location": "",
+        "input_model": "",
+        "main_script": "run_clm_no_trainer.py",
+        "batch_size": 8
+      },
+      "opt_125m_ipex_sq":{
+        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/smooth_quant",
+        "dataset_location": "",
+        "input_model": "",
+        "main_script": "run_clm_no_trainer.py",
+        "batch_size": 8
+      },
+      "dlrm_ipex": {
+        "model_src_dir": "recommendation/dlrm/static_quant/ipex",
+        "dataset_location": "/mnt/local_disk3/dataset/dlrm/dlrm/input",
+        "input_model": "/mnt/local_disk3/dataset/dlrm/dlrm/dlrm_weight/tb00_40M.pt",
+        "main_script": "dlrm_s_pytorch.py",
+        "batch_size": 16384
+      },
+      "resnet18_pt2e_static":{
+        "model_src_dir": "cv/static_quant",
+        "dataset_location": "/tf_dataset/pytorch/ImageNet/raw",
+        "input_model": "",
+        "main_script": "main.py",
+        "batch_size": 1
+      },
+      "opt_125m_pt2e_static":{
+        "model_src_dir": "nlp/huggingface_models/language-modeling/quantization/static_quant/pt2e",
+        "dataset_location": "",
+        "input_model": "",
+        "main_script": "run_clm_no_trainer.py",
+        "batch_size": 1
+      }
+    }
+}
diff --git a/examples/3.x_api/pytorch/cv/static_quant/README.md b/examples/3.x_api/pytorch/cv/static_quant/README.md
@@ -0,0 +1,27 @@
+# ImageNet Quantization
+
+This implements quantization of popular model architectures, such as ResNet on the ImageNet dataset.
+
+## Requirements
+
+- Install requirements
+- `pip install -r requirements.txt`
+- Download the ImageNet dataset from http://www.image-net.org/
+  - Then, move and extract the training and validation images to labeled subfolders, using [the following shell script](extract_ILSVRC.sh)
+
+## Quantizaiton
+
+To quant a model and validate accaracy, run `main.py` with the desired model architecture and the path to the ImageNet dataset:
+
+```bash
+python main.py -a resnet18 [imagenet-folder with train and val folders] -q -e
+```
+
+
+## Use Dummy Data
+
+ImageNet dataset is large and time-consuming to download. To get started quickly, run `main.py` using dummy data by "--dummy". Note that the loss or accuracy is useless in this case.
+
+```bash
+python main.py -a resnet18 --dummy -q -e
+```
diff --git a/examples/3.x_api/pytorch/cv/static_quant/extract_ILSVRC.sh b/examples/3.x_api/pytorch/cv/static_quant/extract_ILSVRC.sh
@@ -0,0 +1,80 @@
+#!/bin/bash
+#
+# script to extract ImageNet dataset
+# ILSVRC2012_img_train.tar (about 138 GB)
+# ILSVRC2012_img_val.tar (about 6.3 GB)
+# make sure ILSVRC2012_img_train.tar & ILSVRC2012_img_val.tar in your current directory
+#
+#  Adapted from:
+#  https://github.com/facebook/fb.resnet.torch/blob/master/INSTALL.md
+#  https://gist.github.com/BIGBALLON/8a71d225eff18d88e469e6ea9b39cef4
+# 
+#  imagenet/train/
+#  ├── n01440764
+#  │   ├── n01440764_10026.JPEG
+#  │   ├── n01440764_10027.JPEG
+#  │   ├── ......
+#  ├── ......
+#  imagenet/val/
+#  ├── n01440764
+#  │   ├── ILSVRC2012_val_00000293.JPEG
+#  │   ├── ILSVRC2012_val_00002138.JPEG
+#  │   ├── ......
+#  ├── ......
+#
+#
+# Make imagnet directory
+#
+mkdir imagenet
+#
+# Extract the training data:
+#
+# Create train directory; move .tar file; change directory
+mkdir imagenet/train && mv ILSVRC2012_img_train.tar imagenet/train/ && cd imagenet/train
+# Extract training set; remove compressed file
+tar -xvf ILSVRC2012_img_train.tar && rm -f ILSVRC2012_img_train.tar
+#
+# At this stage imagenet/train will contain 1000 compressed .tar files, one for each category
+#
+# For each .tar file: 
+#   1. create directory with same name as .tar file
+#   2. extract and copy contents of .tar file into directory
+#   3. remove .tar file
+find . -name "*.tar" | while read NAME ; do mkdir -p "${NAME%.tar}"; tar -xvf "${NAME}" -C "${NAME%.tar}"; rm -f "${NAME}"; done
+#
+# This results in a training directory like so:
+#
+#  imagenet/train/
+#  ├── n01440764
+#  │   ├── n01440764_10026.JPEG
+#  │   ├── n01440764_10027.JPEG
+#  │   ├── ......
+#  ├── ......
+#
+# Change back to original directory
+cd ../..
+#
+# Extract the validation data and move images to subfolders:
+#
+# Create validation directory; move .tar file; change directory; extract validation .tar; remove compressed file
+mkdir imagenet/val && mv ILSVRC2012_img_val.tar imagenet/val/ && cd imagenet/val && tar -xvf ILSVRC2012_img_val.tar && rm -f ILSVRC2012_img_val.tar
+# get script from soumith and run; this script creates all class directories and moves images into corresponding directories
+wget -qO- https://raw.githubusercontent.com/soumith/imagenetloader.torch/master/valprep.sh | bash
+#
+# This results in a validation directory like so:
+#
+#  imagenet/val/
+#  ├── n01440764
+#  │   ├── ILSVRC2012_val_00000293.JPEG
+#  │   ├── ILSVRC2012_val_00002138.JPEG
+#  │   ├── ......
+#  ├── ......
+#
+#
+# Check total files after extract
+#
+#  $ find train/ -name "*.JPEG" | wc -l
+#  1281167
+#  $ find val/ -name "*.JPEG" | wc -l
+#  50000
+#