CoOp
CoOp copied to clipboard
KaiyangZhou
Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)
Hi, thanks for this great works! When reading the source code of CoOp，I have an question about 'token_prefix' and 'token_suffix' in PromptLearner class. How to under this two variables? ...
Thank you for your nice work! However, I encountered some issues when I try to run it. I haven't been able to solve this error for a long time so...
Could you please include a zeroshot script to run the inference for base2new class setting ?
Ms. Zhou: Hello! I am a beneficiary of your CoOp library and a fan of yours. When I download imagenet to my local disk, imagenet/images/train contains folders with categories and...
I would like to ask how long is the experimental period for coop training on imagenet?thanks you！
Hello, I followed the cocoop project, and occured the error above. My progress was as follows. 1. Env setup: following setups from dassl page and cocoop page 2. Dataset and...
CoCoOp provides the train and test commands in the Base-to-novel generalization scenario, but they are not found in CoOp. How should I test CoOp in the Base-to-novel generalization scenario? Which...
CSC (class-specific context) will generate context for every class: ```python # CoOp.py # random initialization if cfg.TRAINER.COOP.CSC: print("Initializing class-specific contexts") ctx_vectors = torch.empty(n_cls, n_ctx, ctx_dim, dtype=dtype) ``` 1. If I...
Hi! I tried to reproduce your work under the Dassl framework as stated in README. However, in some of the training cases, my program cannot exit normally after finishing the...
Hi, I created a conda environment with pytorch=1.11.0. When I train coop, it gives this error:  I found it refers to the TextEncoder.text_projection. The gradient of TextEncoder is already...
Metadata
Owner
Metadata
Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)