-
I have trained 10000 on ucf101-rgb and 20000 on ucf101-flow,but I get the acc of two streams just 96.5,what's the problem
-
Hello, I download your pretrained model resnext-101-kinetics-ucf101_split1.pt and want to test it directly on ucf101, But I get 0 accuracy. What should be the problem? Should I still finetuning it bef…
-
Why is magvitv2 different from the description in the paper? Am I understanding it wrong?
-
while excecuting python evaluate_video_ucf101_split1.py
File "evaluate_video_ucf101_split1.py", line 107, in
net.load_checkpoint(epoch=args.load_epoch)
File "../train/model.py", line 62, i…
-
@feichtenhofer Hi, The dataset cannot be download from the link you give. Could you please check the link. Thanks for your attention.
-
为什么classInd.txt类别索引是从1开始，但是生成的ucf101_train_split_1_rawframes.txt和ucf101_train_split_1_videos.txt类别索引却是从0开始，这样训练的话不会有问题么？一个文件标签从1开始，另两个从0开始。
![image](https://user-images.githubusercontent.com/32315802…
qq-tt updated
9 months ago
-
Hi, thanks for your great job.
I got a comparable result on ucf101-split1 after loading ucf101_rgb.pth weights. Strangely, I got 100% accuracy on split2 and split3 respectively. All the results were …
-
Hi, May I know what parameters are you used for finetuning on UCF101 and JHMDB? Like learning rate, momentum, weight_decay, and steps. Thanks
-
Thank you for sharing caffe2pytorch code and trained models, but I have two questions.
1. Which dataset is used in training each model you provide? I think each model is trained by different datas…
-
Great video worker, I'm sorry, but due to machine problems, I want to implement this model on the UCF101 data set. Do you have any good Suggestions? Thank you.