Tengda Han

Same here. Occasionally get the same error. But error disappears if do not use tensorboard

~~Hi, I get the same error message, did you solve it?~~ My Solution: it seems just running out of GPU memory

Maybe later this week or next week, I am still doing some final check. Will let you know in this issue if it's uploaded.

Sorry for the long delay... they have been uploaded now. https://github.com/TengdaHan/CoCLR#pretrained-weights

@June01 The weight in "Kinetics400-pretrained models" are self-supervised trained on K400 only. Hmm, it seems your retrieval result here "1NN=0.5062" is better than what I got with the same model...

@fmthoker No, we didn't. We only used S3D backbone in our experiment.

@thematrixduo I updated the code that fixed an issue that might reduce the training efficiency of the co-training stage. Maybe it's related to UCF101 reproduction: https://github.com/TengdaHan/CoCLR/issues/43

Hi, HTM-370K is ready to download from [the project page](https://www.robots.ox.ac.uk/~vgg/research/tan/index.html#htm-sentencify). We provide two files: 1. YouTube ASR sentences: [sentences, start-timestamps, end-timestamps] for each video, 2. The video IDs in a...