huangleiBuaa / XBNBlock

This project is the PyTorch implementation of our CVPR 2022 paper:

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Requirements and Dependency

  • Install PyTorch with CUDA (for GPU). (Experiments are validated on python 3.8.11 and pytorch 1.7.0)
  • (For visualization if needed), install the dependency visdom by:
pip install visdom

Experiments

Here, we provide the code for reproducing the main experiments on ImageNet datasets.

1. Prepare the dataset:

Download the ImageNet-1K datasets, and put it in the dir: ./data/imageNet/ or you can specify your datapath by changing --dataset-root=/your-data-path

2. Run scripts of experiments:

We provide the scripts in ./experiments/, including the experiments on the ResNet, ResNeXt, Mobilenet-V2 and ShuffleNet-V2 .

3. Results of object detection for COCO:

We provide the codes in ./ObjectDetection/, based on the mask-rcnn codebase

4.Pre-trained models:

ResNet-50-XBNBlock-standard_train, ResNet-50-XBNBlock-advanced_train, [ResNeXt-50-XBNBlock-advanced_train

About

This project is the PyTorch implementation of our CVPR 2022 paper:

License:BSD 2-Clause "Simplified" License


Languages

Language:Python 80.7%Language:Cuda 14.6%Language:C++ 2.3%Language:C 1.2%Language:Shell 1.1%