CoOp

CoOp copied to clipboard

How to visualize classification results?

1

Hi, Kaiyang! Thanks for your great work! I used your code to test my own dataset, but could only get a series of metrics like accuracy and f1-score. I want...

Ezio77

**Hello, thanks for your work, it's interesting! but iam trouble with follow code** `x = x[torch.arange(x.shape[0]), tokenized_prompts.argmax(dim=-1)] @ self.text_projection` in CoOp.py Class TextEncode->Function forward() **I am curious about the self.text_projection....

OxInsky

I applied the CoOp method to the CIFAR-100 dataset, but the results were not satisfactory. I'd like to inquire about possible reasons for this. If you have already implemented it,...

gaof-p

When I change the code , the result will dropp considerably！

1

Thanks for your great work！ The previous issue has been solved， but I find a new issue. If I change the code (https://github.com/KaiyangZhou/CoOp/blob/ff61507c790454bce7c5052c3ac39e60772f1f89/trainers/coop.py#L248) as self.register_model("model", self.model, self.optim, self.sched). The result...

Zhangwenyao1

Hi, Thank you for the very nice repo! I have a question regarding the number of runs you use to generate your results as it is not very clear in...

ybendou

Hi, can you add the cifar10/100 dataset file if you already have it? Thanks

GauriGupta19

Stanford Cars dataset download

2

Thanks for your great work! However, it seems that the official download link of the StandfordCars (https://ai.stanford.edu/~jkrause/cars/car_devkit.tgz) is now offline. Can you please provide other download links that I can...

llcllc1997

I want to reproduction lpclip experiment. extract feature by `sh feat_extractor.sh`. I met the following questions, 1. How should I set the option `num-shot`? I should use the option `--num-shot`...

laohuijiadezhu

train own dataset

1

Can you elaborate on the steps of few-shot's own dataset?

Miaonika

A problem related to DG

1

djddskkekk