狸追

Results 8 comments of 狸追

I also met this problem.Did you slove it? Thanks! @CorvusCorax

@CorvusCorax today I sloved it. replace tf.split(3, 3, rgb_scaled) with tf.split(rgb_scaled, 3, 3) .

I also meet this error. @centerseed Did you solve it。

@Peilin-Yang I train my own model on widerface dataset. It only contains 2 classes: Background (0) and the face object (1). But I have a big problem: ![image](https://github.com/chenweiqian/image/blob/master/one.png?raw=true) I don‘t...

@Peilin-Yang what's your loss? My loss is always above 5 and mAP is close to zero. Is my dataset wrong?

@Peilin-Yang Thanks for your answer!

I also have this problem. Total loss is above 6.0 for long time.

My mAP is close to zero。What mAP values did you achieve?