-
Notifications
You must be signed in to change notification settings - Fork 188
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
## Describe your changes Add resnet_ptq_qnn.json and imagenet.py, use imagenet validation images to test accuracy and latency while run on QNN/cpu device ## Checklist before requesting a review - [ ] Add unit tests for this change. - [x] Make sure all tests can pass. - [x] Update documents if necessary. - [x] Lint and apply fixes to your code by running `lintrunner -a` - [ ] Is this a user-facing change? If yes, give a description of this change to be included in the release notes. - [x] Is this PR including examples changes? If yes, please remember to update [example documentation](https://github.com/microsoft/Olive/blob/main/docs/source/examples.md) in a follow-up PR. ## (Optional) Issue link 
- Loading branch information
1 parent
5748965
commit 59effd4
Showing
4 changed files
with
208 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,74 @@ | ||
| # ------------------------------------------------------------------------- | ||
| # Copyright (c) Microsoft Corporation. All rights reserved. | ||
| # Licensed under the MIT License. | ||
| # -------------------------------------------------------------------------- | ||
| from logging import getLogger | ||
| from pathlib import Path | ||
|
|
||
| import numpy as np | ||
| import torchvision.transforms as transforms | ||
| from torch import from_numpy | ||
| from torch.utils.data import Dataset | ||
|
|
||
| from olive.data.registry import Registry | ||
|
|
||
| logger = getLogger(__name__) | ||
|
|
||
|
|
||
| class ImagenetDataset(Dataset): | ||
| def __init__(self, data): | ||
| self.images = from_numpy(data["images"]) | ||
| self.labels = from_numpy(data["labels"]) | ||
|
|
||
| def __len__(self): | ||
| return min(len(self.images), len(self.labels)) | ||
|
|
||
| def __getitem__(self, idx): | ||
| return {"input": self.images[idx]}, self.labels[idx] | ||
|
|
||
|
|
||
| @Registry.register_post_process() | ||
| def imagenet_post_fun(output): | ||
| return output.argmax(axis=1) | ||
|
|
||
|
|
||
| preprocess = transforms.Compose( | ||
| [ | ||
| transforms.Resize(256), | ||
| transforms.CenterCrop(224), | ||
| transforms.ToTensor(), | ||
| transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), | ||
| ] | ||
| ) | ||
|
|
||
|
|
||
| @Registry.register_pre_process() | ||
| def dataset_pre_process(output_data, **kwargs): | ||
| cache_key = kwargs.get("cache_key") | ||
| cache_file = None | ||
| if cache_key: | ||
| cache_file = Path(f"./cache/data/{cache_key}.npz") | ||
| if cache_file.exists(): | ||
| with np.load(Path(cache_file)) as data: | ||
| return ImagenetDataset(data) | ||
|
|
||
| size = kwargs.get("size", 256) | ||
| labels = [] | ||
| images = [] | ||
| for i, sample in enumerate(output_data): | ||
| if i >= size: | ||
| break | ||
| image = sample["image"] | ||
| label = sample["label"] | ||
| image = image.convert("RGB") | ||
| image = preprocess(image) | ||
| images.append(image) | ||
| labels.append(label) | ||
|
|
||
| result_data = ImagenetDataset({"images": np.array(images), "labels": np.array(labels)}) | ||
|
|
||
| if cache_file: | ||
| cache_file.parent.resolve().mkdir(parents=True, exist_ok=True) | ||
| np.savez(cache_file, images=np.array(images), labels=np.array(labels)) | ||
|
|
||
| return result_data |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,126 @@ | ||
| { | ||
| "input_model": { | ||
| "type": "HfModel", | ||
| "model_path": "microsoft/resnet-50", | ||
| "task": "image-classification", | ||
| "io_config": { | ||
| "input_names": [ "input" ], | ||
| "input_shapes": [ [ 1, 3, 224, 224 ] ], | ||
| "output_names": [ "output" ] | ||
| } | ||
| }, | ||
| "systems": { | ||
| "qnn_system": { | ||
| "type": "LocalSystem", | ||
| "accelerators": [ { "device": "npu", "execution_providers": [ "QNNExecutionProvider" ] } ] | ||
| } | ||
| }, | ||
| "data_configs": [ | ||
| { | ||
| "name": "quantize_data_config", | ||
| "type": "HuggingfaceContainer", | ||
| "user_script": "imagenet.py", | ||
| "load_dataset_config": { | ||
| "data_name": "imagenet-1k", | ||
| "split": "validation", | ||
| "streaming": true, | ||
| "trust_remote_code": true | ||
| }, | ||
| "pre_process_data_config": { "type": "dataset_pre_process", "size": 256, "cache_key": "imagenet256" }, | ||
| "post_process_data_config": { "type": "imagenet_post_fun" } | ||
| } | ||
| ], | ||
| "evaluators": { | ||
| "common_evaluator": { | ||
| "metrics": [ | ||
| { | ||
| "name": "accuracy", | ||
| "type": "accuracy", | ||
| "data_config": "quantize_data_config", | ||
| "sub_types": [ | ||
| { | ||
| "name": "accuracy_score", | ||
| "priority": 1, | ||
| "metric_config": { "task": "multiclass", "num_classes": 1001 } | ||
| } | ||
| ], | ||
| "user_config": { | ||
| "inference_settings": { | ||
| "onnx": { | ||
| "session_options": { | ||
| "extra_session_config": { "session.disable_cpu_ep_fallback": "1" } | ||
| }, | ||
| "execution_provider": "QNNExecutionProvider", | ||
| "provider_options": [ { "backend_path": "QnnHtp.dll" } ] | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "name": "latency_qnn", | ||
| "type": "latency", | ||
| "data_config": "quantize_data_config", | ||
| "sub_types": [ | ||
| { "name": "avg", "priority": 2 }, | ||
| { "name": "p75" }, | ||
| { "name": "p90" }, | ||
| { "name": "p99" } | ||
| ], | ||
| "user_config": { | ||
| "inference_settings": { | ||
| "onnx": { | ||
| "session_options": { | ||
| "extra_session_config": { "session.disable_cpu_ep_fallback": "1" } | ||
| }, | ||
| "execution_provider": "QNNExecutionProvider", | ||
| "provider_options": [ { "backend_path": "QnnHtp.dll" } ] | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "name": "latency_cpu", | ||
| "type": "latency", | ||
| "data_config": "quantize_data_config", | ||
| "sub_types": [ | ||
| { "name": "avg", "priority": 3 }, | ||
| { "name": "p75" }, | ||
| { "name": "p90" }, | ||
| { "name": "p99" } | ||
| ], | ||
| "user_config": { | ||
| "inference_settings": { "onnx": { "execution_provider": "CPUExecutionProvider" } } | ||
| } | ||
| } | ||
| ] | ||
| } | ||
| }, | ||
| "passes": { | ||
| "conversion": { | ||
| "device": "cpu", | ||
| "type": "OnnxConversion", | ||
| "target_opset": 17, | ||
| "save_as_external_data": true, | ||
| "all_tensors_to_one_file": true, | ||
| "dynamic": false, | ||
| "use_dynamo_exporter": false | ||
| }, | ||
| "QNNPreprocess": { "type": "QNNPreprocess", "fuse_layernorm": true }, | ||
| "OnnxQuantization": { | ||
| "type": "OnnxQuantization", | ||
| "data_config": "quantize_data_config", | ||
| "activation_type": "QUInt16", | ||
| "weight_type": "QUInt8", | ||
| "calibrate_method": "MinMax", | ||
| "quant_preprocess": true, | ||
| "prepare_qnn_config": true | ||
| } | ||
| }, | ||
| "host": "qnn_system", | ||
| "target": "qnn_system", | ||
| "evaluator": "common_evaluator", | ||
| "cache_dir": "cache", | ||
| "clean_cache": true, | ||
| "output_dir": "models/resnet_ptq_qnn", | ||
| "evaluate_input_model": false | ||
| } |