Comments (2)
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 dataset, if I changed the dataset back to original 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 cascade-rcnn_pytorch.
This project is not that stable. If your regression generates an bbox that is totally out of the image, the code will collapse like that. The algorithm is unstable while training.
from cascade-rcnn_pytorch.
Related Issues (20)
- here is a bug. it should not be sum_fg[i] but min(num_fg, sum_fg[i])
- None
- Seems like a big problem HOT 1
- how to speed up training process HOT 1
- Can you share your trained model in other cloud storage, like baiduyun? Thanks
- 段错误(吐核)
- rpn_box: 0.0000 HOT 1
- Do the three stages of Cascade RCNN share the same set of parameters?
- sh make.sh error HOT 2
- KeyError: 'boxes' HOT 2
- ImportError: torch.utils.ffi is deprecated. Please use cpp extensions instead. HOT 4
- Does anyone try this code on COCO dataset? HOT 1
- IndexError: Indexing a Tensor with a torch.cuda.LongTensor triggers index_select semantics, and thus we expect a vector, but the indexing Tensor passed has 0 dimensions
- sh make.sh error
- Has anyone successfully run this program HOT 3
- torch version problem HOT 2
- [solution of errors]'the dim of decoded rois' and'illegal memory acecess'
- RuntimeError: The size of tensor a (900) must match the size of tensor b (300) at non-singleton dimension 1
- Traceback (most recent call last): File "trainval_net.py", line 263, in <module> im_data = im_data.cuda() File "/root/miniconda3/lib/python3.6/site-packages/torch/_utils.py", line 66, in _cuda return new_type(self.size()).copy_(self, async) File "/root/miniconda3/lib/python3.6/site-packages/torch/cuda/__init__.py", line 266, in _lazy_new _lazy_init() File "/root/miniconda3/lib/python3.6/site-packages/torch/cuda/__init__.py", line 85, in _lazy_init torch._C._cuda_init() RuntimeError: cuda runtime error (38) : no CUDA-capable device is detected at /opt/conda/conda-bld/pytorch_1511286954179/work/torch/lib/THC/THCGeneral.c:70
- can't find model.utils.cython_bbox HOT 3
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 cascade-rcnn_pytorch.