AI studio上是否有PASSL下项目实现课程或公开项目

[paddlepaddle]

AI studio上是否有PASSL下项目实现课程或公开项目

[firestonelib]

You can try this: https://github.com/PaddlePaddle/PASSL/blob/main/docs/Train_CLIP_model.md
The link includes a demo which using texts to retrieve images.

[wamm0909]

You can try this: https://github.com/PaddlePaddle/PASSL/blob/main/docs/Train_CLIP_model.md
The link includes a demo which using texts to retrieve images.

thanks, and i want to use paddlepaddle/moco v2 (https://github.com/PaddlePaddle/PASSL/blob/main/configs/moco/moco_v2_r50.yaml)to do image similarity matching experiments locally（linux or mac）, can you give me some suggestions

[firestonelib]

First of all, you can download paddle moco v2 model from this link .
Second, you should extract the moco v2 backbone weights following the step 2 in our MoCo doc .
Last but not least, you can run your image similarity matching experiments following our clip demo.

[firestonelib]

AI Studio Project: https://aistudio.baidu.com/aistudio/projectdetail/2332016?_=1630569049096

[wamm0909]

AI Studio Project: https://aistudio.baidu.com/aistudio/projectdetail/2332016?_=1630569049096

buddy, your update is very timely. I have been using the clip demo just now to encounter'' image_input.npy ''(github), which solved this, but it also prompted ValueError: paddle.load can not parse the file:ViT-B-32.pdparams .I am running on a mac.I just want to experiment with moco, it's too torturous

[wamm0909]

AI Studio Project: https://aistudio.baidu.com/aistudio/projectdetail/2332016?_=1630569049096

buddy, your update is very timely. I have been using the clip demo just now to encounter'' image_input.npy ''(github), which solved this, but it also prompted ValueError: paddle.load can not parse the file:ViT-B-32.pdparams .I am running on a mac.I just want to experiment with moco, it's too torturous

paddle version：2.1.2

[firestonelib]

Do you install passl correctively? or download vit-b-32 model?
Make sure the code bellow is running fluently:

pip install passl==0.0.4 -U -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install scikit-image -U -i https://pypi.tuna.tsinghua.edu.cn/simple
wget https://passl.bj.bcebos.com/models/ViT-B-32.pdparams