EasyCV

EasyCV copied to clipboard

java 中如何使用机器学习平台训练的模型

1

如题：想在JAVA中使用训练的模型进行图像预测，但是不知道该如何使用，还请指点下

OnceCrazyer

liaogulou

Will ConvMAE's imagenet pre training parameters be provided

2

**Describe the feature** Feature description **Motivation** A clear and concise description of the motivation of the feature. Ex1. It is inconvenient when [....]. Ex2. There is a recent paper [....],...

linxuewu

1. designer分类组件的resnet50支持jit导出 2. class_list支持文件读取

tuofeilunhifi

# Welcome update to OpenMMLab 2.0 I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial...

vansin

Can the form of data set only be TFrecord? Can we use other forms？

3

wujiekd

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

Jiabei-prog

feature: export head for moby

1

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

yang-ruixin

请问如何得到自监督MoBY算法最终predictor的输出结果，直接用于以图搜图

1

**Describe the feature** 作者您好，当前推理时只能得到backbone的输出或者projector_q的输出，我希望可以得到最终predictor的输出，直接用于以图搜图。 在模型导出时，当前将MoBY导出为一个分类模型，舍弃了MoBY的head（即predictor），添加了一个dummy classification head。 我也可以自己实现，但是因为EasyCV包了很多层，可以实现的方式比较多，你们会官方来实现吗，或者给些建议，最elegant的实现方式。 如果我实现了可以pull request吗？ 谢谢

yang-ruixin

export方式和eval方式测得的结果差异巨大

1

eval方式top1分类准确率如图  将模型导出后，同样的数据进行预测，准确率10%都不到 使用ResNet50

August-us