Skip to content

Latest commit

 

History

History

inception_v1

Folders and files

NameName
Last commit message
Last commit date

parent directory

..

model

model

 
 

README.md

README.md

 
 

README.md

Inception v1

Model Download Download (with sample test data) ONNX version Opset version Top-1 accuracy (%)
Inception-1 28 MB 29 MB 1.1 3
Inception-1 28 MB 29 MB 1.1.2 6
Inception-1 28 MB 29 MB 1.2 7
Inception-1 28 MB 29 MB 1.3 8
Inception-1 28 MB 29 MB 1.4 9
Inception-1 27 MB 25 MB 1.9 12 67.23
Inception-1-int8 10 MB 9 MB 1.9 12 67.24
Inception-1-qdq 7 MB 5 MB 1.12 12 67.21

Compared with the fp32 Inception-1, int8 Inception-1's Top-1 accuracy drop ratio is -0.01% and performance improvement is 1.26x.

Note

The performance depends on the test hardware. Performance data here is collected with Intel® Xeon® Platinum 8280 Processor, 1s 4c per instance, CentOS Linux 8.3, data batch size is 1.

Description

Inception v1 is a reproduction of GoogLeNet.

Dataset

ILSVRC2012

Source

Caffe2 Inception v1 ==> ONNX Inception v1 ONNX Inception v1 ==> Quantized ONNX Inception v1

Model input and output

Input

data_0: float[1, 3, 224, 224]

Output

prob_1: float[1, 1000]

Pre-processing steps

Post-processing steps

Sample test data

random generated sampe test data:

  • test_data_0.npz
  • test_data_1.npz
  • test_data_2.npz
  • test_data_set_0
  • test_data_set_1
  • test_data_set_2

Results/accuracy on test set

Quantization

Inception-1-int8 and Inception-1-qdq are obtained by quantizing fp32 Inception-1 model. We use Intel® Neural Compressor with onnxruntime backend to perform quantization. View the instructions to understand how to use Intel® Neural Compressor for quantization.

Environment

onnx: 1.9.0 onnxruntime: 1.8.0

Prepare model

wget https://github.com/onnx/models/raw/main/vision/classification/inception_and_googlenet/inception_v1/model/inception-v1-12.onnx

Model quantize

Make sure to specify the appropriate dataset path in the configuration file.

bash run_tuning.sh --input_model=path/to/model \  # model path as *.onnx
                   --config=inception_v1.yaml \
                   --data_path=/path/to/imagenet \
                   --label_path=/path/to/imagenet/label \
                   --output_model=path/to/save

References

Contributors

License

MIT