PyTorch MobileNetV2

• Model has been optimized with Data Free Quantization + Quantization Aware Training
• Batch norm folding and Data Free Quantization has been applied, this checkpoint does not contain batch norm layers and ReLU6 in model definition MUST be replaced with RELU
• This checkpoint has been evaluated in INT8 - 71.14%

TensorFlow MobilenetV2 1.4

General

Post QAT checkpoint for mobilenetv2-1.4. Quantization was done after Batch Norm folding, with tf quant scheme encodings, and the default configuration file. Note that this checkpoint has Batch Norms folded.

Quantized Accuracy: 74.11%

Quantizer Op Assumptions

In the evaluation script included, we have used the default config file, which configures the quantizer ops with the following assumptions:

• Weight quantization: 8 bits, asymmetric quantization
• Bias parameters are not quantized
• Activation quantization: 8 bits, asymmetric quantization
• Model inputs are not quantized
• Operations which shuffle data such as reshape or transpose do not require additional quantizers

Contents

The tarball contains the following files:
checkpoint – Text file for TensorFlow to find latest checkpoint
model.data-00000-of-00001 model.index model.meta - Model checkpoint and meta files

TensorFlow Efficientnet-lite0

General

Post QAT checkpoint for efficientnet-lite0. Quantization was done after Batch Norm folding, with tf quant scheme encodings, and the default configuration file. Note that this checkpoint has Batch Norms folded.

Quantized Accuracy: 74.99%

Quantizer Op Assumptions

In the evaluation script included, we have used the default config file, which configures the quantizer ops with the following assumptions:

• Weight quantization: 8 bits, asymmetric quantization
• Bias parameters are not quantized
• Activation quantization: 8 bits, asymmetric quantization
• Model inputs are not quantized
• Operations which shuffle data such as reshape or transpose do not require additional quantizers

Contents

The tarball contains the following files:
checkpoint – Text file for TensorFlow to find latest checkpoint
model.data-00000-of-00001 model.index model.meta - Model checkpoint and meta files

PyTorch MobileNetV2SSD-Lite

• Model has been optimized as a pre-processing for post quantization
• Batch norm folding and Adaround has been performed, this checkpoint does not contain batch norm layers
• This checkpoint has been evaluated in INT8 - mAP: 68.60%

PyTorch DeepLabV3+ QAT model

• Model has been optimized with Data Free Quantization + Quantization Aware Training
• Batch norm folding and Data Free Quantization has been applied, this checkpoint does not contain batch norm layers and ReLU6 in model definition MUST be replaced with RELU
• This checkpoint has been evaluated in INT8 - 72.08 mIoU