yyfyan

xception load issue

6

when I load the xception model,I meet: model_name = 'xception' # could be fbresnet152 or inceptionresnetv2 model = pretrainedmodels.__dict__[model_name](num_classes=1000, pretrained='imagenet') model.eval() the error msgs: RuntimeError: Error(s) in loading state_dict for...

the result?

4

Hi,Good job. I used your trained model, VOC12_scenes_16000.pth, to test,But get the lower mIou 66.35%，not get your mIou result. 

best job. I have two problem: 1) I have a machine and mutil-GPU, can use the distribute training code? 2) the deeperlab use topK and balanced ,the code only use...

a problem of run main.py

1

when I run the main.py.I get the problem. 

I noticed that SENet used two 1*1Conv after global pool.But In the GENet's Parameter-free version,it not use the 1*1Conv after global pool. And the two module look very similar. So...

model

1

Can you provide more models,such as modified ResNet that 7x7Conv convert to 3 3x3Conv.

Can you source the full code, includeing training and testing.

feature matching?

28

how to use the LIFT do the match?0.0

Input size

2

When training, the input size that you used?

problem

1

你好，代码中的 K_1(1) = size(img1,2); K_2(1) = K_1(1) + (K_max(1) - K_1(1))/2; 这部分是什么意思？ 还有论文中，针对APAP的： For each pixel in the non-overlapping regions, the transformation is computed as a weighted linear combination ofthe...