yolov5的demo中预测报错

[charming2992]

训练的自己的数据集，CLASSES已经修改了。

Traceback (most recent call last): File "test.py", line 316, in boxes, classes, scores = yolov5_post_process(input_data) File "test.py", line 157, in yolov5_post_process b, c, s = process(input, mask, anchors) File "test.py", line 64, in process col = col.reshape(grid_h, grid_w, 1, 1).repeat(3, axis=-2) ValueError: cannot reshape array of size 64 into shape (80,8,1,1)

[charming2992]

训练的自己的数据集，CLASSES已经修改了。

Traceback (most recent call last): File "test.py", line 316, in boxes, classes, scores = yolov5_post_process(input_data) File "test.py", line 157, in yolov5_post_process b, c, s = process(input, mask, anchors) File "test.py", line 64, in process col = col.reshape(grid_h, grid_w, 1, 1).repeat(3, axis=-2) ValueError: cannot reshape array of size 64 into shape (80,8,1,1)

这个问题大概是toolkit和toolkit2中的这代码部分不一致，修改成toolkit中的就行如下图

[charming2992]

出现了另外一个问题，这个函数输出的boxes有两千多个，没有经过nms，并且classes也大于自己设定的类别数 boxes, classes, scores = yolov5_post_process(input_data)

[nullgogo]

有解决吗，我也遇到了相同问题