大土土君

@SunlerZRY @pursu i meet the problem too,i use cuda9.0,how do you fix it?

@ganggang233 这套代码支持ctw1500的数据集么？是用opendataset格式？

@ganggang233 我刚把CTW的转换了，可训练loss很奇怪，完全是像没训练一样 021-06-10 14:58:04,225 DBNet.pytorch INFO: [1/1200], [166/1000], global_step: 166, speed: 1.2 samples/sec, acc: 0.1761, iou_shrink_map: 0.1761, loss: 1.0000, loss_shrink_maps: 0.0000, loss_threshold_maps: 0.0000, loss_binary_maps: 1.0000, , lr:0.00037, time:0.80 2021-06-10 14:58:05,026...

@ganggang233 有没有将ctw数据集转为opendata的json格式的代码? 我看是不是我写得不对?

@ganggang233 我感觉是我写ctw的polygon不太对，我的是这样的 gt=line.strip().split(',') x1 = np.int(gt[0]) y1 = np.int(gt[1]) bbox = [np.int(gt[i]) for i in range(4, 32)] bbox = np.asarray(bbox) + ([x1 * 1.0, y1 * 1.0] * 14)#14个点是相对坐标 bbox=bbox.reshape((-1,2)).tolist()...

@zdz1997 是要这样的效果么？ 

@SJLNNU my environment is ubuntu16.04,gcc 5.4.0,get the same error,do you fix it?

I have installed torch7,but it get the same error,so I don't understand why

@SJLNNU I just updated gcc to 6.5 just now,what a pity get the error too...

@SJLNNU you can install gcc-(your gcc version)-plugin-dev,for my ubuntu,is "sudo apt-get install gcc-6-plugin-dev",i fix it.