Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning from natural language supervision. , CLIP jointly trains an image encoder and a text encoder to predict the correct pairings of a batch of (image, text) training examples. At test time the learned text encoder synthesizes a zero-shot linear classifier by embedding the names or descriptions of the target dataset’s classes.
cd multimodal/Language-Image_Pre-Training/clip/pytorch
pip3 install ftfy regex tqdm pytorch torchvision
Download CIFAR100
python3 clip/zero_shot_prediction_top5.py
python3 clip/zero_shot_prediction_top1.py
python3 clip/Linear_probe_evaluation.py
metric | BI-V100 |
---|---|
accuracy(%) | 86.74 |
metric | BI-V100 |
---|---|
accuracy(%) | 61.71 |
metric | BI-V100 |
---|---|
accuracy(%) | 80.01 |
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》