dehuli

I already know, but currently there is one thing that is unclear to me, what is ablation. pkl

感谢您的答复，我目前是做clip预训练的，也是希望能够让clip兼具俩种能力，全局和局部，我按照您论文里面的方案，在yffc15m训练一个vit-32的模型，发现在图文检索的表现不如baseline，所以就想前来请教一下。 ---Original--- From: "Size Wu ***@***.***> Date: Sat, Mar 2, 2024 15:19 PM To: ***@***.***>; Cc: ***@***.******@***.***>; Subject: Re: [wusize/CLIPSelf] performance of Zero-shot Classification and Zero-shot Cross-Modal Retrieval (Issue #11)...

想咨询下您，微调后的模型，在我说的那俩个任务表现情况具体是多少呢 ---Original--- From: "Size Wu ***@***.***> Date: Sat, Mar 2, 2024 15:19 PM To: ***@***.***>; Cc: ***@***.******@***.***>; Subject: Re: [wusize/CLIPSelf] performance of Zero-shot Classification and Zero-shot Cross-Modal Retrieval (Issue #11)...

我是在yffcm跑的clip，这个数据集跑出的结果都比较差，vit-b-32，微调后.掉了一半 ---Original--- From: "Size Wu ***@***.***> Date: Sun, Mar 3, 2024 18:40 PM To: ***@***.***>; Cc: ***@***.******@***.***>; Subject: Re: [wusize/CLIPSelf] performance of Zero-shot Classification and Zero-shot Cross-Modal Retrieval (Issue #11)...

多谢，可能是我参数设置不对 ---Original--- From: "Size Wu ***@***.***> Date: Sun, Mar 3, 2024 18:40 PM To: ***@***.***>; Cc: ***@***.******@***.***>; Subject: Re: [wusize/CLIPSelf] performance of Zero-shot Classification and Zero-shot Cross-Modal Retrieval (Issue #11)...

感谢 ---Original--- From: "Size Wu ***@***.***> Date: Sun, Mar 3, 2024 18:57 PM To: ***@***.***>; Cc: ***@***.******@***.***>; Subject: Re: [wusize/CLIPSelf] performance of Zero-shot Classification and Zero-shot Cross-Modal Retrieval (Issue #11)...

请问，微调flow matching模型时候，采样率是多少hz