Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification (TPAMI 2022)
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
IAMGGKK opened this issue 10 months ago · comments
我使用pt2onnx.py将pth转换为onnx,但法线转换出的模型文件最后的slice层(Slice_61)的start(-328)和end(9223372036854775807)都是奇怪的数,能帮忙分析一下吗?多谢!
修改model_culane.py中forward()中‘exist_col’的代码,从-self.dim4改为1+2+3:1+2+3+4即可