PyTorch EfficientNet Lite0 W8A8 and W4A8 per channel quantsim model

These are the PyTorch EfficientNet Lite W8A8 and W4A8 per channel quantsim model checkpoints:

1. Original FP32 model is transformed to a new FP32 model by model validate->model preparer -> model validate
2. Batch Norm folding and Adaround has been applied on the transformed model
3. Adaround has been optimized with 4-bit width OR 8-bit width and "tf_enhanced" quant scheme
4. Quantization evaluated with "tf" quant scheme in 8 bit width activation quantization

PyTorch Deeplab V3+ W8A8 and W4A8 per channel quantsim model

This is the PyTorch Deeplab V3+ W8A8 OR W4A8 per channel QuantSim model weights file and encodings file

1. Cross Layer Equalization and Adaround has been applied on the original model
2. Adaround has been optimized with 8-bit OR 4-bit width width, and "tf_enhanced" quant scheme
3. Quantization evaluated with "tf_enhanced" quant scheme in 8 bit width activation quantization

PyTorch Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution (XLSR) model

The release provides the model checkpoint tarballs for different variations of the PyTorch-based Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution (XLSR) model. Each model tarball corresponds to a given scaling_factor (release_xlsr_<scaling_factor>x.tar.gz). Each tarball contains the following:

• checkpoint_float32.pth.tar - full-precision model with the highest validation accuracy on the DIV2k dataset
• checkpoint_int8.pth - quantized model with the highest validation accuracy obtained with Quantization-aware Training using AIMET
• checkpoint_int8.encodings - Encodings for the quantized models

PyTorch Super-Efficient Super Resolution (SESR) model

The release provides the model checkpoint tarballs for different variations of the PyTorch-based PyTorch Super-Efficient Super Resolution (SESR) model. Each model tarball corresponds to a given scaling_factor (release_sesr_<config_name>_<scaling_factor>x.tar.gz). Each tarball contains the following:

• checkpoint_float32.pth.tar - full-precision model with the highest validation accuracy on the DIV2k dataset
• checkpoint_int8.pth - quantized model with the highest validation accuracy obtained with Quantization-aware Training using AIMET
• checkpoint_int8.encodings - Encodings for the quantized models

PyTorch Anchor-based PlainNet Model (ABPN)

The release provides the model checkpoint tarballs for different variations of the PyTorch-based Anchor-based PlainNet Model (ABPN). Each model tarball corresponds to a given num_channels and scaling_factor (release_abpn_<num_channels>_<scaling_factor>x.tar.gz). Each tarball contains the following:

• checkpoint_float32.pth.tar - full-precision model with the highest validation accuracy on the DIV2k dataset
• checkpoint_int8.pth - quantized model with the highest validation accuracy obtained with Quantization-aware Training using AIMET
• checkpoint_int8.encodings - Encodings for the quantized models

PyTorch EfficientNet Lite

This is the PyTorch EfficientNet Lite optimized checkpoint

1. Batch Norm folding and Adaround has been applied on the original model
2. Adaround has been optimized with 8-bit width and "tf_enhanced" quant scheme
3. Quantization evaluated with "tf_enhanced" quant scheme in 8 bit width weight & activation quantization

TensorFlow SSD MobileNet v2

fake quant removed ssd mobilenet_v2 quantized 300x300 coco 2019 01 03

PyTorch SRGAN MMSR

The model was from an older version of mmediting which was called mmsr. It is not publicly available anymore so we release the model here.

srgan_mmsr_MSRGANx4.gz

A forked version is found here. No model file available just the script.

Pytorch Pose Estimation Model

The tarball file contains a compressed PyTorch pose estimation model.

Tensorflow Pose Estimation Model Checkpoint

This contains the model checkpoint for optimized Tensorflow pose estimation model.