| Training Techniques | Polynomial Learning Rate Decay, Weight Decay, SGD with Momentum, Label Smoothing |
|---|---|
| Architecture | 1x1 Convolution, Batch Normalization, Convolution, Grouped Convolution, Global Average Pooling, ResNeXt Block, Residual Connection, ReLU, Max Pooling, Softmax |
| ID | cspresnext50 |
| SHOW MORE |
CSPResNeXt is a convolutional neural network where we apply the Cross Stage Partial Network (CSPNet) approach to ResNeXt. The CSPNet partitions the feature map of the base layer into two parts and then merges them through a cross-stage hierarchy. The use of a split and merge strategy allows for more gradient flow through the network.
To load a pretrained model:
import timm
m = timm.create_model('cspresnext50', pretrained=True)
m.eval()
Replace the model name with the variant you want to use, e.g. cspresnext50. You can find the IDs in the model summaries at the top of this page.
You can follow the timm recipe scripts for training a new model afresh.
@misc{wang2019cspnet,
title={CSPNet: A New Backbone that can Enhance Learning Capability of CNN},
author={Chien-Yao Wang and Hong-Yuan Mark Liao and I-Hau Yeh and Yueh-Hua Wu and Ping-Yang Chen and Jun-Wei Hsieh},
year={2019},
eprint={1911.11929},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
Image Classification
| BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
|---|---|---|---|---|
| ImageNet | cspresnext50 | Top 1 Accuracy | 80.05% | # 98 |
| Top 5 Accuracy | 94.94% | # 98 |
