Yindong-Zhang
Yindong-Zhang
same issue,installing takes a long time because stupid downloading tensorflow
the same wondering about world modeling? It's seems to be a tricky claim.
+1, continue finetuning is a common way for industrial application
the installing guide is ugly, i spend hours debugging and still fails
same question
Can separate inference solve the problem. It comes to me that some interference between each prompts may cause the problem.@taofuyu
One text prompt may interfere the inference process of the other, you can refer to the text-guided CSPlayer in the paper. I would also like use the prompt tuning technic,...
@taofuyu any update?in case you don't notice the answer above.
A modified dependency in toml: requires = ["setuptools","wheel"] dependencies = [ "wheel", "torch==1.11.0", "transformers", "tokenizers", "numpy", "opencv-python>=4.9.0", "supervision==0.19.0", ] and install all mm package with mim foreahead like this: export...
i use code from huggingface and get owlv2-base-patch16-ensemble around 46.5 on odinw13, which seems normal but owlv2-large performance is really pool.