ir0nt0ad

Fine-tuning pretrained VILBERT on a custom dataset

1

## ❓ Questions and Help Hi, I want to use the Hateful Memes VILBERT checkpoint from the zoo to fine-tune it on my custom dataset. I run the following command,...

https://github.com/USTC-Video-Understanding/I3D_Finetune/blob/c32d90f38f3c031af0850cff757bd155734954ac/finetune.py#L63 It appears that we always call `process_video` with `is_training=True`, and therefore each sample of `test_dataset` has `_CLIP_SIZE`, not `_EACH_VIDEO_TEST_SIZE` frames as we would like to have it. @Rhythmblue @AlexHu123

3.3.5.a

4

"Let x = {{1, 2}, {1, 3}}. Then x ∈ P(A) is true. Let y = {1, 2}. Then y ∈ x and y ⊆ A are both true. Let...

Shouldn't the answer be ∃A∈F(x∈A)∧∀A∈G(x∉A)? Thanks.