成功解决but is 0 and 2 (computed from start 0 and end 9223372 over shape with rank 2 and stride-1)

成功解决Exception "unhandled ValueError" Subshape must have computed start >= end since stride is negative, but is 0 and 2 (computed from start 0 and end 9223372036854775807 over shape with rank 2 and stride-1)

目录

解决问题

解决思路

解决方法

解决问题

Exception "unhandled ValueError" Subshape must have computed start >= end since stride is negative, but is 0 and 2 (computed from start 0 and end 9223372036854775807 over shape with rank 2 and stride-1)

解决思路

异常“未处理的ValueError” 子形状必须计算开始>=结束，因为步幅为负数，但为0和2（从开始0和结束9223372036854775807开始计算，在等级为2和步幅为1的形状上）

解决方法

参考文章：https://stackoverflow.com/questions/57558476/training-a-keras-model-yields-multiple-optimizer-errors

修改yolo3/model.py文件的140/141行 :

将

box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))

改为

box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[...,::-1], K.dtype(feats))
box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[...,::-1], K.dtype(feats))