QiqLiang
QiqLiang
@Chilicyy hi, i got the same error when finetuning my yolov6n model, it is P5 model and its training mode is repopt. i want to use fuse_ab when finetuning(but my...
> Hi @QiqLiang If you want to use fuse_ab, please make sure there's the initiation of anchor in the config file, otherwise you can add the line `anchors_init=[[10,13, 19,19, 33,23],...
Thanks for answering! Could you please further supply the code link to show where they are thrown away? im kind of confused about it and want to see the corresponding...
hi, i got the similar error when pruning my yolov6 model: module2node[param].pruning_dim = dim KeyError: Parameter containing: tensor([0., 1., 2., 3., 4., 5., 6., 7., 8., 9., 10., 11., 12.,...
> For overriding kwargs, we need keys to have _ instead of - > > Change `model.detection.n-classes=103` to `model.detection.n_classes=103` I used this code: PYTHONWARNINGS="ignore" cvnets-train \ --common.config-file config/detection/ssd_coco/coco-ssd-mobilevitv2-1.75.yaml \ --common.results-loc...
> Are these weights pretrained on MS-COCO? Yes. I downloaded from model zoo(MS-COCO). The link is: https://docs-assets.developer.apple.com/ml-research/models/cvnets-v2/detection/mobilevitv2/coco-ssd-mobilevitv2-1.75.pt
Hi, I got the same problem when validating my models, have you solved it?
> 我一台机器上有两块GPU，能不能像darknet一样全部利用上？ Hello 请问你解决了吗
所以如果我是coco80类数据集的话，num_classes参数应该设置为81吗？
我的cls_score只包含了前景的80类得分，没有背景的得分，如果我把背景的得分直接都设置为0，会有影响吗？