senet

SENet

Squeeze-and-Excitation Networks

Introduction

In this work, the authors focus instead on the channel relationship and propose a novel architectural unit, which the authors term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. The results show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. The authors further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost.[1]

Figure 1. Architecture of SENet [1]

Requirements

mindspore	ascend driver	firmware	cann toolkit/kernel
2.3.1	24.1.RC2	7.3.0.1.231	8.0.RC2.beta1

Quick Start

Preparation

Installation

Please refer to the installation instruction in MindCV.

Dataset Preparation

Please download the ImageNet-1K dataset for model training and validation.

Training

• Distributed Training

It is easy to reproduce the reported results with the pre-defined training recipe. For distributed training on multiple Ascend 910 devices, please run

# distributed training on multiple NPU devices
msrun --bind_core=True --worker_num 8 python train.py --config configs/senet/seresnet50_ascend.yaml --data_dir /path/to/imagenet

For detailed illustration of all hyper-parameters, please refer to config.py.

Note: As the global batch size (batch_size x num_devices) is an important hyper-parameter, it is recommended to keep the global batch size unchanged for reproduction or adjust the learning rate linearly to a new global batch size.

• Standalone Training

If you want to train or finetune the model on a smaller dataset without distributed training, please run:

# standalone training on single NPU device
python train.py --config configs/senet/seresnet50_ascend.yaml --data_dir /path/to/dataset --distribute False

Validation

To validate the accuracy of the trained model, you can use validate.py and parse the checkpoint path with --ckpt_path.

python validate.py -c configs/senet/seresnet50_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt

Performance

Our reproduced model performance on ImageNet-1K is reported as follows.

Experiments are tested on ascend 910* with mindspore 2.3.1 graph mode.

model name	params(M)	cards	batch size	resolution	jit level	graph compile	ms/step	img/s	acc@top1	acc@top5	recipe	weight
seresnet18	11.80	8	64	224x224	O2	90s	51.09	10021.53	72.05	90.59	yaml	weights

Experiments are tested on ascend 910 with mindspore 2.3.1 graph mode.

model name	params(M)	cards	batch size	resolution	jit level	graph compile	ms/step	img/s	acc@top1	acc@top5	recipe	weight
seresnet18	11.80	8	64	224x224	O2	43s	44.40	11531.53	71.81	90.49	yaml	weights

Notes

• top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.

References

[1] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.