如何去除增强?如efficientnetv2-b0配置文件中train_pipeline可更改为如下
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=192,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
若你的数据集提前已经将shape更改为网络要求的尺寸,那么Resize
操作也可以去除。
2023.12.02
新增Issue中多人提及的输出Train Acc与Val loss
metrics_outputs.csv
保存每周期train_loss, train_acc, train_precision, train_recall, train_f1-score, val_loss, val_acc, val_precision, val_recall, val_f1-score
方便各位绘图2023.08.05
2023.03.07
2022.11.20
2022.11.06
数据集 | 视频教程 | 人工智能技术探讨群 |
---|---|---|
花卉数据集 提取码:0zat |
点我跳转 | 1群:78174903 3群:584723646 |
python tools/single_test.py datas/cat-dog.png models/mobilenet/mobilenet_v3_small.py --classes-map datas/imageNet1kAnnotation.txt
@repo{2020mmclassification,
title={OpenMMLab's Image Classification Toolbox and Benchmark},
author={MMClassification Contributors},
howpublished = {\url{https://github.com/open-mmlab/mmclassification}},
year={2020}
}