FCOS.Pytorch
FCOS.Pytorch copied to clipboard
VectXmy
fcos implementation in pytorch1.x
When i run the train_voc.py ,found: FileNotFoundError: [Errno 2] No such file or directory: './checkpoints/voc_512x800_loss2.0635.pth' the file has been Missed？
What is the basis of your writing loss.py Is there any improvement or difference compared with the original loss of fcos?
I found that the calculation of ltrb in the code was inconsistent with that in the paper, line 102 and line 104 of the model/loss.py file  What ltrb means...
RuntimeError: Error(s) in loading state_dict for FCOSDetector: size mismatch for fcos_body.fpn.prj_5.weight: copying a param with shape torch.Size([256, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 2048,...
 train_voc.py中未提供预训练权重"./checkpoints/voc_512x800_loss2.0635.pth"。我直接注释掉这行，从头开始训练，60个epoch，结果用demo.py推理图片时啥结果也没有，这是为什么呢？ 希望您能解答一下。 另外，我不太懂如何把官方的FCOS_R_50_FPN_1x.pth转换成自己的，您能否赐教。
In the eval.py file, pred_boxes,pred_classes,pred_scores are sorted before calculating ap. In eval_ap_2d function, zip(gt_single_cls, bbox_single_cls, scores_single_cls) was used. but the sizes of gt_single_cls, bbox_single_cls, scores_single_cls are different. This will make...
Traceback (most recent call last): File "train_voc.py", line 18, in model.load_state_dict(torch.load("./convert_weights/FCOS_R_50_FPN_1x.pth")) File "/root/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 845, in load_state_dict self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for FCOSDetector: Missing key(s) in state_dict:...