Mahdiyar Moghadam
Mahdiyar Moghadam
in data/io/DOTA/????? what should i put??? how should i put dota dataset pls show as tree
i made new sampler just like libra sampling in `rbbox_head` with using `rbbox_base_sampler.py` and i got lower ap seperatly i used orginal libra sampling in `bbox_head` but i got lower...
hi @csuhan in detector config you put this: `assert neck['type'] == 'ReFPN', 'ReDet only supports ReFPN neck'` i think its for using this fpn for extracting the `re_resnet50` but can...
hi @csuhan and tnx very much for answering i want to train [ReDet_re50_refpn_3x_hrsc2016](https://github.com/csuhan/ReDet/blob/master/configs/ReDet/ReDet_re50_refpn_3x_hrsc2016.py) my env is colab tesla t4 and use pytorch 1.1 in training i got this error: File...
hi & tnx for your codes in ReDet/configs/DOTA/ you put many configs that can use for dota v1 (task1 , task2) but for testing...we need .pth epoch checkpoints. 1. is...
hi @csuhan thanx for your implementation but i have one **important** error **everywhere** here and in [AerialDetection](https://github.com/dingjiansw101/AerialDetection) both one: 1. i use prepare_dota1 and got dota1_1024 folder and `.json` files...
i test hrsc2016 and got the pkl but for evaluating a get this error classname: ship Traceback (most recent call last): File "/content/ReDet/DOTA_devkit/hrsc2016_evaluation.py", line 307, in main() File "/content/ReDet/DOTA_devkit/hrsc2016_evaluation.py", line...
i upload the nms resaults and get this: mAP: 0.3745174540144275 ap of each class: plane:0.5300541025955471, baseball-diamond:0.27181818181818185, bridge:0.43130126717635453, ground-track-field:0.14171122994652408, small-vehicle:0.24575509050331162, large-vehicle:0.25701370866991136, ship:0.7015457849808598, tennis-court:0.5453346126169345, basketball-court:0.3152847152847153, storage-tank:0.09090909090909091, soccer-ball-field:0.18932806324110674, roundabout:0.1655011655011655, harbor:0.6844767188033766, swimming-pool:0.6143607552420431, helicopter:0.4333673229272884 why...
how can i get more evaluating without DOTA server(its just give AP):i need to get more like recall precision curve or APs APm ,... after training it gives log.json file...