FCOS
FCOS copied to clipboard
tianzhi0549
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
High AP on pretrained weight ```FCOS_imprv_R_50_FPN_1x.pth``` with default test command ``` python tools/test_net.py --config-file configs/fcos/fcos_imprv_R_50_FPN_1x.yaml MODEL.WEIGHT FCOS_imprv_R_50_FPN_1x.pth TEST.IMS_PER_BATCH 4 ``` ``` 2020-03-30 01:13:16,982 fcos_core.inference INFO: Start evaluation on coco_2014_minival dataset(40504...
I tried training this model on my own dataset, cls_loss converges fine, but reg_loss always 1.0, and pred_left, pred_right, pred_top, pred_bottom become all zero after 5~10 iteration. Would you please...
https://github.com/tianzhi0549/FCOS/blob/35331f706d21cc22e53376436bd434893d1a8ed2/fcos_core/modeling/rpn/fcos/loss.py#L224 Sorry for asking a stupid question, the way that compute the targets should be 1. gather object_sizes_of_interest to all levels of locations (expanded_object_sizes_of_interest) 2. compute through compute_targets_for_locations() to get...
I really want to know your nms is just simple nms or soft-nms？？
 Could you tell me what's wrong with it
Same,Have you solved the problem? It happens when I'm using dataset extracted from COCO. It seems like some annotations cannot loaded properly in get_sample_region, I log the params: center_x torch.Size([30785,...
Hi, Thanks for open source. When I train the same model, using dcn is nearly twice as long as not using dcn. May I know if that's normal? looking forward...
I trained my dataset and modified the number of categories according to your method, but this problem still appeared. How to solve it? 
Metadata
Owner
Metadata
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)