Image preprocessing

[seann999]

The readme says to scale the RGB values between -1 and 1. Does this mean x/128.0-1.0, where x is an uint8 image?
I'm more used to seeing normalizing images with mean and std, so I want to make sure.

[zekun-li]

I have the same question. However when I do x/128. - 1. on the sample data, the result doesn't match with the given .npy

[egg347]

@zekun-li Hi, the provided *.npy file has shape (1, num_frames, 224, 224, 3), I wonder what "1" refers to? And what's its value?

[zekun-li]

@egg347 That dimension corresponds to batch size.

[egg347]

@zekun-li Thanks a lot! Have you solved your problem above? It seems that the sample data firstly rescale to [-1,1](videos to videos),and secondly rescale to [0,1](videos to *.npy file).
By the way, I'm confused about the output of the sample. According to the "evalutate_sample.py", it prints Norm of logits、out_predictions[index]、out_logits[index]、kinetics_classes[index])。So what Norm of logits and out_logits[index] can be used for?
With no offense, are you Chinese? Your id looks like a Chinese name. Would you please leave me your EMAIL or your WECHAT id if you don't mind? It comforts me to communicate in Chinese.

[TianjiPang]

@zekun-li I also have the same problem on preprocessing. No matter rescaling the image on R, G, B channel individually or across RGB channals, the results all can't match with the given .npy. Have you solved the problem?

[vivoutlaw]

@zekun-li @egg347 @TianjiPang @seann999 : Hi guys, were you able to resolve the scaling. If yes, would you mind sharing what you did. Thanks

[seann999]

I think I simply did what I first guessed, x/128.0-1.0.

[vivoutlaw]

@seann999: I did the same too, I hope the extracted feature are alright.

[bryanyzhu]

@zekun-li @seann999 @vivoutlaw @TianjiPang @egg347 I saw many people use x/128.0-1.0 as image normalization. But I still have doubts . For example, if I apply this kind of preprocessing to my frames extracted from v_CricketShot_g04_c01.mp4, the prediction result I get is robot dancing. I tried many videos, none of the prediction is correct.

So when you say your result doesn't match with the given .npy, do you mean the prediction is totally wrong (as in my case), or the prediction is correct (just the softmax score distribution is different)? Thank you very much. Looking forward to your reply.