aniki

Normalize all class?I think this should be 1 instead of -1

error when testing forward pass

4

when I test forward pass ,I got such error: Traceback (most recent call last): File "darknet_debug.py", line 317, in model = Darknet('cfg/yolov3.cfg') File "darknet_debug.py", line 172, in __init__ self.net_info, self.module_list...

the program is stucked before anything.

1

File "atrous_concat.py", line 159, in out = model(img) File "/home/tensor/anaconda2/envs/py35/lib/python3.5/site-packages/torch/nn/modules/module.py", line 477, in __call__ result = self.forward(*input, **kwargs) File "atrous_concat.py", line 118, in forward c2,c3,c4,c5 = self.backbone(x) File "/home/tensor/anaconda2/envs/py35/lib/python3.5/site-packages/torch/nn/modules/module.py", line...

How can i reproduce the performance in the paper?

1

Thanks for your work and code. I trained the coot on the anet dataset by the default setting, and obtain the performance as follows: INFO vid | 0.574 | 0.839...

when i run train_JPPNet-s2.py.i found that the loss don't convergence,so i want to know how to set learning rate when train the joint model or are there some trick about...

运行DANet报错

2

model : danet backbone : resnet101 dataset : cityscapes num_classes : 19 data_folder : ./dataset base_size : 1024 crop_size : 768 aux : True se_loss : True epoch_num : 1200...

Wonderful Job!

1

This repository solved a lot of problems in my research, thanks.

How extract features from my own images by wenlan?

1

The current test codes are made for sample pictures. Can you release a more convenient code for extracting features for a random picture or provide an api.