mmpretrain/docs/tutorials/pytorch2onnx.md

Pytorch to ONNX (Experimental)

• Tutorial 5: Pytorch to ONNX (Experimental)
  • How to convert models from Pytorch to ONNX
    • Prerequisite
    • Usage
    • Description of all arguments:
  • How to evaluate ONNX models with ONNX Runtime
    • Prerequisite
    • Usage
    • Description of all arguments
    • Results and Models
  • List of supported models exportable to ONNX
  • Reminders
  • FAQs

How to convert models from Pytorch to ONNX

Prerequisite

1. Please refer to install for installation of MMClassification.
2. Install onnx and onnxruntime

pip install onnx onnxruntime==1.5.1

Usage

python tools/deployment/pytorch2onnx.py \
    ${CONFIG_FILE} \
    --checkpoint ${CHECKPOINT_FILE} \
    --output-file ${OUTPUT_FILE} \
    --shape ${IMAGE_SHAPE} \
    --opset-version ${OPSET_VERSION} \
    --dynamic-export \
    --show \
    --simplify \
    --verify \

Description of all arguments:

• config : The path of a model config file.
• --checkpoint : The path of a model checkpoint file.
• --output-file: The path of output ONNX model. If not specified, it will be set to tmp.onnx.
• --shape: The height and width of input tensor to the model. If not specified, it will be set to 224 224.
• --opset-version : The opset version of ONNX. If not specified, it will be set to 11.
• --dynamic-export : Determines whether to export ONNX with dynamic input shape and output shapes. If not specified, it will be set to False.
• --show: Determines whether to print the architecture of the exported model. If not specified, it will be set to False.
• --simplify: Determines whether to simplify the exported ONNX model. If not specified, it will be set to False.
• --verify: Determines whether to verify the correctness of an exported model. If not specified, it will be set to False.

Example:

python tools/deployment/pytorch2onnx.py \
    configs/resnet/resnet18_b16x8_cifar10.py \
    --checkpoint checkpoints/resnet/resnet18_b16x8_cifar10.pth \
    --output-file checkpoints/resnet/resnet18_b16x8_cifar10.onnx \
    --dynamic-export \
    --show \
    --simplify \
    --verify \

How to evaluate ONNX models with ONNX Runtime

We prepare a tool tools/deployment/test.py to evaluate ONNX models with ONNXRuntime or TensorRT.

Prerequisite

• Install onnx and onnxruntime-gpu

  pip install onnx onnxruntime-gpu
  

Usage

python tools/deployment/test.py \
    ${CONFIG_FILE} \
    ${ONNX_FILE} \
    --backend ${BACKEND} \
    --out ${OUTPUT_FILE} \
    --metrics ${EVALUATION_METRICS} \
    --metric-options ${EVALUATION_OPTIONS} \
    --show
    --show-dir ${SHOW_DIRECTORY} \
    --cfg-options ${CFG_OPTIONS} \

Description of all arguments

• config: The path of a model config file.
• model: The path of a ONNX model file.
• --backend: Backend for input model to run and should be onnxruntime or tensorrt.
• --out: The path of output result file in pickle format.
• --metrics: Evaluation metrics, which depends on the dataset, e.g., "accuracy", "precision", "recall", "f1_score", "support" for single label dataset, and "mAP", "CP", "CR", "CF1", "OP", "OR", "OF1" for multi-label dataset.
• --show: Determines whether to show classifier outputs. If not specified, it will be set to False.
• --show-dir: Directory where painted images will be saved
• --metrics-options: Custom options for evaluation, the key-value pair in xxx=yyy format will be kwargs for dataset.evaluate() function
• --cfg-options: Override some settings in the used config file, the key-value pair in xxx=yyy format will be merged into config file.

Results and Models

This part selects ImageNet for onnxruntime verification. ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012.

Model	Config	Metric	PyTorch	ONNXRuntime	TensorRT-fp32	TensorRT-fp16
ResNet	resnet50_b32x8_imagenet.py	Top 1 / 5	76.55 / 93.15	76.49 / 93.22	76.49 / 93.22	76.50 / 93.20
ResNeXt	resnext50_32x4d_b32x8_imagenet.py	Top 1 / 5	77.90 / 93.66	77.90 / 93.66	77.90 / 93.66	77.89 / 93.65
SE-ResNet	seresnet50_b32x8_imagenet.py	Top 1 / 5	77.74 / 93.84	77.74 / 93.84	77.74 / 93.84	77.74 / 93.85
ShuffleNetV1	shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet.py	Top 1 / 5	68.13 / 87.81	68.13 / 87.81	68.13 / 87.81	68.10 / 87.80
ShuffleNetV2	shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet.py	Top 1 / 5	69.55 / 88.92	69.55 / 88.92	69.55 / 88.92	69.55 / 88.92
MobileNetV2	mobilenet_v2_b32x8_imagenet.py	Top 1 / 5	71.86 / 90.42	71.86 / 90.42	71.86 / 90.42	71.88 / 90.40

List of supported models exportable to ONNX

The table below lists the models that are guaranteed to be exportable to ONNX and runnable in ONNX Runtime.

Model	Config	Batch Inference	Dynamic Shape	Note
MobileNetV2	mobilenet_v2_b32x8_imagenet.py	Y	Y
ResNet	resnet18_b16x8_cifar10.py	Y	Y
ResNeXt	resnext50_32x4d_b32x8_imagenet.py	Y	Y
SE-ResNet	seresnet50_b32x8_imagenet.py	Y	Y
ShuffleNetV1	shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet.py	Y	Y
ShuffleNetV2	shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet.py	Y	Y

Notes:

• All models above are tested with Pytorch==1.6.0

Reminders

• If you meet any problem with the listed models above, please create an issue and it would be taken care of soon. For models not included in the list, please try to dig a little deeper and debug a little bit more and hopefully solve them by yourself.

FAQs

• None