yolov3 的　loss ，今天終于看完了yolov3-tf2 的源碼

YOLOv3中Loss部分計(jì)算

代碼

#終點(diǎn)的loss= obj_mask * box_loss_scale*sum((px1-tx1)**2+(px2-tx2)**2)#因?yàn)檫@里有obj_mask的存在，只考慮有目標(biāo)點(diǎn)的loss xy_loss = obj_mask * box_loss_scale * \tf.reduce_sum(tf.square(true_xy - pred_xy), axis=-1)wh_loss = obj_mask * box_loss_scale * \tf.reduce_sum(tf.square(true_wh - pred_wh), axis=-1)obj_loss = binary_crossentropy(true_obj, pred_obj)obj_loss = obj_mask * obj_loss + \(1 - obj_mask) * ignore_mask * obj_loss# TODO: use binary_crossentropy insteadclass_loss = obj_mask * sparse_categorical_crossentropy(true_class_idx, pred_class)# 6. sum over (batch, gridx, gridy, anchors) => (batch, 1)xy_loss = tf.reduce_sum(xy_loss, axis=(1, 2, 3))wh_loss = tf.reduce_sum(wh_loss, axis=(1, 2, 3))obj_loss = tf.reduce_sum(obj_loss, axis=(1, 2, 3))class_loss = tf.reduce_sum(class_loss, axis=(1, 2, 3))return xy_loss + wh_loss + obj_loss + class_loss

總結(jié)

以上是生活随笔為你收集整理的YOLOv3中Loss的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。