Comments (1)
Hi,
The current implementation supports a number of data augmentations, including random resizing and random crops.
If I understand it correctly, the mozaic data augmentation that you pointed out is very similar (if not equivalent) to doing random resize on each image. Indeed, in the same mini-batch, we can have images of different resolutions, and it can be customized, so that a very large image could be in the same minibatch as a very small image.
Since the utilization of RandomSizeCrop, all the labels associated to an image may be cropped. (So this repo supports training with no targets in an image?
🤔️ )
Yes, that's correct, we support feeding training images without any annotations (which generally happens with random crops).
I believe I've answered your questions, and as such I'm closing the issue, but let us know if you have further questions.
from detr.
Related Issues (20)
- Possible t-SNE visualization
- Problem about weight initialization using DDP HOT 1
- DETR table detection to ONNX HOT 9
- Issue on DETR colab example with a picture from coco 2017 val5k HOT 1
- why pred_logits and pred_boxes use "outputs_class[-1] and outputs_coord[-1]" rather than "outputs_class and outputs_coord"
- inference code HOT 1
- Why class_error always = 100 when training HOT 7
- ValueError in generalized_box_iou for conditional detr object detector HOT 1
- Removing class weights for Instance Segmentation HOT 3
- How to visualize mAP for each class?
- Is there any way to get the coordinates(polygon shape returns)?
- How to export onnx with dynamic_axes?
- How to draw box predictions on all images
- How to draw the Fig7?
- Does anynone know the performance of DETR without Transformer part (only with ResNet)? HOT 3
- what is the output size of transformer encoder and decoder? HOT 2
- How to get loss and mAP curves?
- .cpu() operation as bottleneck in training
- Question about gradient backpropagation to object queries.
- Q: Encoder
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 detr.