FariMOT训练记录

问题1&＃xff0c;加载模型时类别不一致导致的权重部分加载&＃xff0c;设置好自己的类别就行&＃xff0c;只训练人就只设置 1&＃xff0c;

opt.heads &＃61; {&＃39;hm&＃39;: 1,
&＃39;wh&＃39;: 2 if not opt.cat_spec_wh else 2 * opt.num_classes,
&＃39;id&＃39;: opt.reid_dim}


Skip loading parameter hm.2.weight, required shapetorch.Size([80, 256, 1, 1]), loaded shapetorch.Size([1, 256, 1, 1]). If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.
Skip loading parameter hm.2.bias, required shapetorch.Size([80]), loaded shapetorch.Size([1]). If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.


问题2&＃xff1a;加载模型时类别不一致导致的权重部分加载&＃xff0c;加载

‘./models/ctdet_coco_dla_2x.pth&＃39;

模型本身就没有id这部分权重&＃xff0c;所以作为预训练模型加载进去的&＃xff0c;FairMOT模型是有这部分的

No param id.0.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.
No param id.0.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.
No param id.2.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.
No param id.2.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you have correctly specified --arch xxx or set the correct --num_classes for your own dataset.


问题3&＃xff0c;更改训练数据集时&＃xff0c;需要在/home/cody/PycharmProjects/FairMOT/src/data/ 修改对应的训练文件列表&＃xff0c;

训练的格式&＃xff1a;0 1 0.177778 0.195573 0.0981481 0.131771

类别&＃xff0c;ID&＃xff0c;x_center,y_center,w,h(坐标均是归一化之后的)