ExtremeNet

ExtremeNet copied to clipboard

您好，我无法使用README中的链接，请问有下载pre-trained model的其他方法吗？谢谢！

liuj001

Hello , I'm trying to run demo.py but it gives me this error. The environment is given mainly by: - torch 0.4.0 - cuda 8.0.61 - cudnn 7.1.0.2 This is...

pcuevas-ch

File "/data2/yanmengkai/ExtremeNet/nnet/py_factory.py", line 117, in load_params self.model.load_state_dict(params)

5

RuntimeError: Error(s) in loading state_dict for DummyModule: Unexpected key(s) in state_dict: "module.pre.0.bn.num_batches_tracked", "module.pre.1.bn1.num_batches_tracked", "module.pre.1.bn2.num_batches_tracked", "module.pre.1.skip.1.num_batches_tracked", "module.kps.0.up1.0.bn1.num_batches_tracked", "module.kps.0.up1.0.bn2.num_batches_tracked", "module.kps.0.up1.1.bn1.num_batches_tracked", "module.kps.0.up1.1.bn2.num_batches_tracked", "module.kps.0.low1.0.bn1.num_batches_tracked", "module.kps.0.low1.0.bn2.num_batches_tracked", "module.kps.0.low1.0.skip.1.num_batches_tracked", "module.kps.0.low1.1.bn1.num_batches_tracked", "module.kps.0.low1.1.bn2.num_batches_tracked", "module.kps.0.low2.up1.0.bn1.num_batches_tracked", "module.kps.0.low2.up1.0.bn2.num_batches_tracked", "module.kps.0.low2.up1.1.bn1.num_batches_tracked", "module.kps.0.low2.up1.1.bn2.num_batches_tracked", "module.kps.0.low2.low1.0.bn1.num_batches_tracked", "module.kps.0.low2.low1.0.bn2.num_batches_tracked",...

njustymk

Train error

1

when I run tran.py ExtremeNet, the error occurs: Traceback (most recent call last): File "train.py", line 213, in training_dbs = [datasets[dataset](configs["db"], train_split) for _ in range(threads)] File "train.py", line 213,...

wwetnaroh

thanks for your work, it's really great! But I am not sure what ghost box is, could you please show me a example to help me understand it better? thank...

igo312

How to use the pretrained model to train my own data, when the class number is not 80(coco)?

2

How can I use pretraied model to train my own own data, my class number is not 80 like coco, but my own data only have 3 classess. When I...

DataXujing

@xingyizhou while running python gen_coco_extreme_points.py for generating extreme points, I get this error. I tried looking at the exact column where it shows error, but it seams right. Error I...

keravraj20

When I train my own data, I set rand_crop to false. Then when the trained model is tested on the training set, there is no box on the output image,...

ZHR1997

Corner pooling

4

Ever thought about using corner pooling to further improve AP?

zhaopings

What about the test speed on ExtremeNet

1

Could you please provide the test speed info ?

jerrywgz