You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
# classification loss (crossentropy)
# 1. compute max conf across batch for hard negative mining
loss_class = tf.where(mask_neg,
1 - class_pred[:, 0][..., tf.newaxis], 0)
請問,這裏的 分類損失 為什麽是這樣的計算的?要是檢測的目標不僅僅是人臉,而是多個目標(比如,人臉和行人等)是否要做相應的修改?
The text was updated successfully, but these errors were encountered: