Fighting-JJ
Fighting-JJ
And the tricks you have tried to prove the accuracy. ![default](https://user-images.githubusercontent.com/17001854/53931273-75300500-40cf-11e9-830f-206e04606c2c.png) the accuracy that i achieve. i just want to know is there any promotion can be done?
Due to the read.me , Glow can only be build on MacOs and Linuxs.
在yolo_head函数中: box_wh = tf.exp(predictions[..., 2:4]) * anchors_tensor / input_shape[::-1] 在yolo_loss函数中: raw_true_wh = tf.log(tf.where(tf.equal(y_true[index][..., 2:4] / anchors[anchor_mask[index]] * input_shape[::-1], 0), tf.ones_like(y_true[index][..., 2:4]), y_true[index][..., 2:4] / anchors[anchor_mask[index]] * input_shape[::-1])) ... wh_loss =...
When click the link : https://github.com/azadis/AdobeFontDropper#mc-gan-traintest it turns out to be 404.