Fida Mohammad Thoker
Fida Mohammad Thoker
Hi Laura, did you add the pre-trained models yet?
@taxuezcy Did you train st-gcn on PKUMMD dataset?
@pedro-abreu can you share them with me. Email address [email protected]
@XiaoCode-er can you send the hdf5 files to [email protected] or share a google drive link Thanks and regards Fida
Did you pretrain any other architectures like R(2+1)D-18 on Kinetics 400.
@sunilhoho Thanks for sharing the models at such quick notice, do you any checkpoints for Kinetics-400 VIT-B which was trained for more than 200 epochs, we want to use the...
@leexinhao thanks for the reply, after evaluating with wise ft = True, indeed the results are better: MSRVTT: txt_r1 txt_r5 txt_r10 txt_r_mean img_r1 img_r5 img_r10 img_r_mean r_mean msrvtt_1k_test/ 42.0 65.7...
@Andy1621 Thanks for the quick response, are you referring to the scripts in InternVideo/InternVideo2/multi_modality/scripts/evaluation/clip/zero_shot, if so, it seems they are for evaluating InternVideo2 clip. Would the scripts and code work...
@Andy1621 Thanks for you quick response, will try that to reproduce the results.
@Andy1621 I tried to do zero-shot eval on msrvtt-1k with scrpts from [here](https://github.com/OpenGVLab/InternVideo/blob/main/InternVideo1/Pretrain/ViCLIP/exp/exp_pretrain_ViCLIP/zs_msrvtt_1k/run_clip_pretrained.sh) However, I am getting the following errors File "tasks/retrieval.py", line 15, in Traceback (most recent call last):...