Comments (5)
I found that the code runs normally on faster-rcnn. But if I use the code of fpn, it failed. So I guess the problem happens in fpn.py, but I still can't find out why.
What's more, I used this model to train my personal data, if I changed the data back to origin Voc2007, it works. That's strange. I just changed my personal data into the form of Voc2007.
Here is one of my annotation file:
train
VIRAT_S_000000.mp4_0
C:/Users/Kevin Qian/Downloads/images/train/VIRAT_S_000000.mp4_0.jpg
and here is the annotation file in original voc2007
VOC2007
009962.jpg
The VOC2007 Database
PASCAL VOC2007
flickr
246788553
Tool - Wroclaw
Milosz J.
500
375
3
0
chair
Right
1
0
211
192
324
326
person
Unspecified
1
0
162
72
273
248
person
Right
1
0
250
68
473
312
person
Right
1
0
4
2
253
374
diningtable
Unspecified
1
1
358
216
500
375
from fpn.pytorch.
@KevinQian97 I have encountered with the same problem. Have you found out how to solve it?
from fpn.pytorch.
@KevinQian97 @WangTianYuan did you solve this issue?
from fpn.pytorch.
Have you solved the problem? I got the same error.@KevinQian97 @WangTianYuan
from fpn.pytorch.
Have you solved the problem? I got the same error.@KevinQian97 @WangTianYuan
I found that if you use your own dataset to train the model, if it has dirty data, it will cause Nan values in roi_ level in FPN.py. You can try the following modification methods:
roi_ level[roi_ level < 2] = 2
roi_ level[roi_ level > 5] = 5
To
roi_ level[roi_ level < 2] = 2
roi_ level[roi_ level > 5] = 5
roi_ level[roi_ level!=roi_ level]=5
from fpn.pytorch.
Related Issues (20)
- TypeError: 'list' object is not callable
- How to load the Images into the network?
- Nan
- irq/133-nvidia error
- Have somebody used ROI pooling successfully?I have some errors
- TypeError: load() got an unexpected keyword argument 'encoding'
- Where I can crop the image then send it into backbone
- bbox_outside_weights normalized incorrectly (anchor_target_layer_fpn.py:136)
- There was a bug when I continued to train the model. RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #4 'other' HOT 1
- about rpn_loss_box is zero
- from model.utils.cython_bbox import bbox_overlaps HOT 1
- train on my dataset HOT 1
- torch.log(torch.sqrt(h * w) / 224.0) in fpn.py HOT 1
- roi pooling
- Conversion to TensorRT
- train with multi gpus can not work
- Why is the result not as good as faster-rcnn? Have you modified the code?
- Does it support PyTorch1.0 or higher? HOT 1
- sh make.sh 编译不通过
- ImportError:/fpn.pytorch-master/lib/model/nms/_ext/nms/_nms.so: undefined symbol: __cudaPopCallConfiguration HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fpn.pytorch.