-
除了时间长度以外，其他好像没有区别。但是zero_shot_prompt放入跨语言生成的功能中，在日语/粤语等方面生成就出现很大问题，比如瞎念。
-
https://github.com/LAION-AI/CLIP_benchmark/blob/main/clip_benchmark/metrics/zeroshot_classification.py#L44
-
Hi, I was wondering if there is a way supported by Python API to run multiple eval benchmarks on multiple models (by passing in a list of models and their respective arguments in the `model_args` argu…
-
Suggested by @mglowacki100 in #3373:
> Hi @Innixma I've checked a couple of parameters locally and think the biggest impact and quite generic could be adding interactions between all features: `hyp…
-
Hey Authors,
Awesome work, could you please provide me with the fewshot/zeroshot eval script to reproduce your VQA/OKVQA/GQA results in Table-1? cc @benbrandt @countably1nfinite @sdtblck @Mayukhdeb…
-
作者您好，
CN-clip是很棒的工作！我在复现voc-2007-classification zero-shot推理的过程中发现最终推理的性能与report的结果无法对齐，下面是我的执行结果，烦请有空是帮看下问题，感谢。
Params:
context_length: 52
datapath: ******/Chinese-CLIP/content/datas…
-
Across a few models and a few BBH tasks, I obtain this error:
```
match = [m for m in match if m][0]
IndexError: list index out of range
```
The full stack trace is below:
```
$ lm_ev…
-
I tried running some CoT zeroshot evaluations, but they both failed. Am I doing something wrong?
### Command for mmlu_flan_cot_zeroshot
```
accelerate launch \
--multi_gpu \
--num_p…
-
Hi there,
I got a question of the following when I tried to run the zeroshot_cls.sh:
File "/content/drive/MyDrive/Colab Notebooks/PointCLIP_V2/zeroshot_cls/datasets/modelnet40.py", line 33, in l…
-
I am working on the virtual try on zeroshot notebook but I could not get the same background as the source image. The output has no background at all. I am using the same prompt as the example.