SlowFastNetworks

SlowFastNetworks copied to clipboard

result in ucf101

13

I trained the model in ucf101, after 70 epoch, the top 1 accuracy is 73.3%, the top 5 accuracy is 95.7% in training data, is this a normal result?

qichenghan666

Bad performence on custom datasets

2

thanks for your work. When i train it on my datasets,after 100 epoch,it only get 35% top1-acc.My datasets has 7 classses,and i use the default config as u provided,What are...

mokiki1

Is the video in train and validation the same？

wangpanpan666

about inference

2

can you give me an example code about how to detect a single video, and get its result? thank you very much!

yangjinghit

Quetion about the inplane

2

Thanks for sharing the code of your implementation, but i have a question about follow line, why should we do this operation in slow path? https://github.com/r1ch88/SlowFastNetworks/blob/251a97a37a6b6ffb4ae15b1225689c16bef75687/lib/slowfastnet.py#L179 Thanks for your reply!...

Tylerjoe

I am studing your code.But I have some problem.In the article, the video of input size is 64*224*224.In your code,it is 8*112*112.This is just the the simple implementation about the...

zkyunqi

I feel puzzle about my resault, have you ever met yet? just share my resault, and talk about the reason  

Jump20

Excuse me,could I ask you about that only verification method, how to test on ucf101?

Tian-Iris

Hi, I want to create a confusion matrix to see which actions could be related in UCF dataset. I know it sounds trivial, but I am trying to get the...

ivaxi0s

shizishen