Relation_Networks-pytorch icon indicating copy to clipboard operation
Relation_Networks-pytorch copied to clipboard

AttributerError:module 'model' has no attribute 'resnet101'

Open crystalruo opened this issue 7 years ago • 6 comments

When I run the train.py file after I modified the config.py file,there is a AttributerError:module 'model' has no attribute 'resnet101'.If it's convenient ,piease tell me how to solve it.Thank you!

crystalruo avatar Nov 01 '18 12:11 crystalruo

same problem. I don't find the resnet101 definition in the whole code

chensonglu avatar Jan 10 '19 03:01 chensonglu

I meet the same problem,Have you solved this problem? Does this model come from torchvision.models..resnet101 or the author's own definition? in model.py? Can you helpe me?Thank you

shajie17 avatar Jul 10 '19 01:07 shajie17

@shajie17 No, I think it's a bug.

chensonglu avatar Jul 10 '19 06:07 chensonglu

@chensonglu
Have you successfully run the relation-networks-for-object-pytorch code? Why do I run code based on vgg16 network and get a much lower map value than the faster-rcnn code without relation?

puyiwen avatar Nov 08 '19 07:11 puyiwen

I meet the same problem,Have you solved this problem? Does this model come from torchvision.models..resnet101 or the author's own definition? in model.py? Can you helpe me?Thank you

The reason is that this is an uncompleted code. The experiments.py can run, train.py need to be modified. But I think the Relation-Module was not added in the FasterRCNN. You can see the line 66 in model.py, n_realtions = 0. And when I change it to 2, the code cannot run more. Do u notice this problem?

JuggerNau avatar Apr 03 '20 14:04 JuggerNau

@chensonglu Have you successfully run the relation-networks-for-object-pytorch code? Why do I run code based on vgg16 network and get a much lower map value than the faster-rcnn code without relation?

I meet the same problem, got the lower map value than faster-rcnn code without relation.Haved you figured out this problem?

wsx66848 avatar Apr 13 '20 13:04 wsx66848