Comments (4)
Actually, they are the same...
from moc-detector.
Sorry, I didn't catch you... Please correct me if I made some mistakes.
Images are resized from original_h, original_w
to input_w, input_h
.
If the tube gt bboxes are resized to the same ratio, then they should modified by the following code
gt_bbox[ilabel][itube][:, 0] = gt_bbox[ilabel][itube][:, 0] / original_w * input_w
gt_bbox[ilabel][itube][:, 1] = gt_bbox[ilabel][itube][:, 1] / original_h * input_h
gt_bbox[ilabel][itube][:, 2] = gt_bbox[ilabel][itube][:, 2] / original_w * input_w
gt_bbox[ilabel][itube][:, 3] = gt_bbox[ilabel][itube][:, 3] / original_h * input_h
However, in the Sampler code, the gt tube bboxes are modified
gt_bbox[ilabel][itube][:, 0] = gt_bbox[ilabel][itube][:, 0] / original_w * output_w
gt_bbox[ilabel][itube][:, 1] = gt_bbox[ilabel][itube][:, 1] / original_h * output_h
gt_bbox[ilabel][itube][:, 2] = gt_bbox[ilabel][itube][:, 2] / original_w * output_w
gt_bbox[ilabel][itube][:, 3] = gt_bbox[ilabel][itube][:, 3] / original_h * output_h
# aka
gt_bbox[ilabel][itube][:, 0] = gt_bbox[ilabel][itube][:, 0] / original_w * input_w // self.opt.down_ratio
gt_bbox[ilabel][itube][:, 1] = gt_bbox[ilabel][itube][:, 1] / original_h * input_h // self.opt.down_ratio
gt_bbox[ilabel][itube][:, 2] = gt_bbox[ilabel][itube][:, 2] / original_w * input_w // self.opt.down_ratio
gt_bbox[ilabel][itube][:, 3] = gt_bbox[ilabel][itube][:, 3] / original_h * input_h // self.opt.down_ratio
from moc-detector.
We calculate the loss on the final feature map whose shape is (output_h, output_w ). So we resize gt tubes into this shape. After inputing the raw images into the network, they will have the same resize ratios with gt tubes. In the inference process, we will resize the prediction tubes to the original shape(original_h, original_w) in normal_moc_det.
from moc-detector.
Thanks for your reply, Got it now
from moc-detector.
Related Issues (20)
- the standard of pkl HOT 4
- FLOPs analysis HOT 3
- Confused about the `sample_cuboids` constraints HOT 2
- model for K7 RGB + FLOW COCO on UCF101-24
- How to pretrain an optical flow model on COCO? HOT 7
- train on the one gpu error HOT 9
- Import Error HOT 13
- Reproduction of paper results HOT 1
- how to infer with only rgb model? HOT 1
- training problem HOT 4
- about branch construction HOT 2
- Some questions about spatial-temporal action detection HOT 1
- more details about 3D CNN
- Inference with flow model HOT 2
- DCNv2 HOT 5
- Disable cudnn batch normalization HOT 1
- Why ninput = 5 when input modality is flow? HOT 1
- How to interpret the 3-channel in jpg image of optical flow?
- undefined symbol: __cudaRegisterFatBinaryEnd. HOT 4
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 moc-detector.