Comments (3)
- The coco data set has 91 categories, but only 80 categories are used, so with this mapping relationship, the purpose is to sort from 0 to 79
- Start from "0" (it is essential to start from 0 to accommodate caption/grounding data).
- https://github.com/longzw1997/Open-GroundingDino/blob/main/data_format.md
- If I define the label_list in cfg_odvg.py, is it okay to set the label_map in the json file to null? You need to check where it is used in the code and then replace it one by one. This is okay. How to use it depends entirely on how you modify the code.
from open-groundingdino.
When using custom data, how should 'id_map' be defined? check v3det2odvg.py, this script is used for custom datasets in coco format.
from open-groundingdino.
- The coco data set has 91 categories, but only 80 categories are used, so with this mapping relationship, the purpose is to sort from 0 to 79
- Start from "0" (it is essential to start from 0 to accommodate caption/grounding data).
- https://github.com/longzw1997/Open-GroundingDino/blob/main/data_format.md
- If I define the label_list in cfg_odvg.py, is it okay to set the label_map in the json file to null? You need to check where it is used in the code and then replace it one by one. This is okay. How to use it depends entirely on how you modify the code.
from open-groundingdino.
Related Issues (20)
- Errors of distributed training HOT 3
- Simple questions regarding fine-tuning the model on custom data. HOT 1
- Training-Data-Prep HOT 1
- The impact of the order of elements (i.e., text) within "cat_list" used in model evaluation HOT 1
- Discrepency between the model's predictions and the confidence scores HOT 1
- Usage of arguement " --options text_encoder_type=/path/to/bert-base-uncased" HOT 1
- 请问如何解决向Grounding-Dino无法输入一个batch的数据? HOT 2
- Can i train on windows? HOT 1
- how much memories we need to finetune? HOT 1
- pre-training HOT 3
- Evaluate HOT 1
- Tokenizer decoder makes up class names during inference HOT 3
- IndexError: index 909 is out of bounds for dimension 0 with size 900 HOT 5
- Label_list HOT 4
- Detection task with one class custom dataset, 15epoch is not enough? HOT 2
- 请问一下训练的时候是没有使用swin_T_224_1k的预训练权重吗? HOT 1
- 关于文本不同 导致的 训练精度差异的问题 HOT 1
- Predicted labels HOT 10
- about train dataset questions 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 open-groundingdino.