Comments (4)
You can look at the conversion scripts, for example convert_cityperson_to_coco.py to see. In our case, for CityPersons, we only prune based on height >= 50 and not on the visibility, for achieving an overall decent performance across all splits.
from pedestron.
OK, but I wonder if the current data augmentation (particularly the random crop) strategy is suitable in such case. For example, the cropped patch may contain no visible part of a heavily occluded person, which will introduce persons with visibility 0 and cause classification ambiguity.
By the way, I find that the implemented random crop seems to be problematic. The cropped patch satisfies when any bbox has an IoU greater than the min_iou. But in the current implementation, the cropped patch satisfies when all bboxes have IoUs greater than min_iou. See this issue.
from pedestron.
I mean number of severely occluded cases for e.g (vis <40 %) are close to ~10 % in cityPersons and this is randomly cropping so I am not sure how much an impact it would practically have. Moreover, as far as I remember we did see empirically a small gain by incorporating this augmentation. Perhaps you can give it a shot without this augmentation as well.
Regarding the potential bug, we actually over looked it. Support appreciated.
from pedestron.
Yeah. The actual impact of these problems is probably small. Thanks.
from pedestron.
Related Issues (20)
- Installtion has issue HOT 1
- error: identifier "THCudaCheck" is undefined HOT 3
- Demo not workingt HOT 1
- Identifier "THCudaCheck" is undefined HOT 1
- Docker image is not working! HOT 4
- Impact of mean_teacher on the training process HOT 1
- CSP pretrained weights HOT 1
- Reproduce resutls on Caltech dataset HOT 3
- Information regarding the training HOT 1
- Image_scale of Caltech while training HOT 6
- ImportError: /pedestron/tools/../mmdet/ops/dcn/deform_conv_cuda.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E HOT 1
- RuntimeError: Expected cudaMemcpy(&mask_host[0], mask_dev, sizeof(unsigned long long) * boxes_num * col_blocks, cudaMemcpyDeviceToHost) == cudaSuccess to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.) HOT 1
- Training citypersons with all the instances? HOT 1
- Welcome update to OpenMMLab 2.0
- Runtime error - Training with EuroCity persons HOT 1
- Training Caltech using CSP HOT 1
- What's ignore_other_vru in ECP evaluation? HOT 2
- result has no bbox HOT 5
- mmdet/ops/roi_align/src/roi_align_kernel.cu(145): error: identifier "THCudaCheck" is undefined HOT 1
- Update instruction for 2023 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 pedestron.