JackieWu
JackieWu
辛苦了～ 有时间我也看看怎样去优化
需要链接opengl的动态库或者静态库
我不记得windows上怎么配置了
Hi @SomnusQue , thanks for your attention to our work! Is the code of TinyCLIP latest? It is a bug which is triggered on PyTorch 2.x. We have fixed the...
@SomnusQue I fixed the bug in Jan. 11, 2024 (https://github.com/microsoft/Cream/pull/218/files#diff-2c756c8b8b99609dee1b59ce4dcfaf773aa9afbc84e093e03e3e0de653fa0124R28). You can visualize the loss curve in wandb. The loss is normal if it is decreasing : )
@SomnusQue No code change required. It is also available to set the environmental variable `WANDB_MODE=offline`. The wandb log will be saved as a file. Then run `wandb sync ` to...
Sorry that I did not test TensorBoard yet. The training data in the provided script is synthetic. They should be replaced with the following command: ```bash --train-data \ --dataset-type webdataset...
@SomnusQue Please refer to the document https://github.com/mlfoundations/open_clip?tab=readme-ov-file#data
Did you mean the evaluation code for the benchmark? 1. Flickr30k and MSCOCO retrieval Retrieval: https://github.com/salesforce/BLIP/blob/main/train_retrieval.py 2. section 4.4 Transfer Learning Results Zero shot, linear probe: https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC
Hi @giginho83 , thanks for your attention to our work! You can refer to the evaluation script: https://github.com/microsoft/Cream/blob/main/TinyCLIP/docs/EVALUATION.md#for-auto-weight-inference-checkpoint I may update the inference code for auto inheritance.