EfficientNet B0 (IxRT)

Model Description

EfficientNet B0 is a convolutional neural network architecture that belongs to the EfficientNet family, which was introduced by Mingxing Tan and Quoc V. Le in their paper "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks." The EfficientNet family is known for achieving state-of-the-art performance on various computer vision tasks while being more computationally efficient than many existing models.

Supported Environments

Model Preparation

Prepare Resources

Pretrained model: https://download.pytorch.org/models/efficientnet_b0_rwightman-3dd342df.pth

Dataset: https://www.image-net.org/download.php to download the validation dataset.

Install Dependencies

# Install libGL
## CentOS
yum install -y mesa-libGL
## Ubuntu
apt install -y libgl1-mesa-glx

pip3 install -r requirements.txt

Model Conversion

python3 export_onnx.py --origin_model /path/to/efficientnet_b0_rwightman-3dd342df.pth --output_model efficientnet_b0.onnx

Model Inference

export DATASETS_DIR=/path/to/imagenet_val/

FP16

# Accuracy
bash scripts/infer_efficientnet_b0_fp16_accuracy.sh
# Performance
bash scripts/infer_efficientnet_b0_fp16_performance.sh

INT8

# Accuracy
bash scripts/infer_efficientnet_b0_int8_accuracy.sh
# Performance
bash scripts/infer_efficientnet_b0_int8_performance.sh

Model Results