Comments (4)
mu-cai
commented on June 11, 2024
Hi,
I guess you are referring that how I edit the images. Here is the code https://github.com/WisconsinAIVision/ViP-LLaVA/blob/main/llava/visual_prompt_generator.py
from vip-llava.
ia-gu
commented on June 11, 2024
Sorry, I meant to refer to common data augmentation methods (e.g., HorizontalFlip(), Normalize()).
I supposed to say that https://github.com/WisconsinAIVision/ViP-LLaVA/blob/main/llava/visual_prompt_generator.py does not include them.
from vip-llava.
mu-cai
commented on June 11, 2024
There is no data augmentation.
For each image, there are only two preprocess steps:
- Padding: https://github.com/WisconsinAIVision/ViP-LLaVA/blob/main/llava/train/train.py#L900
- Normalizetion: https://github.com/WisconsinAIVision/ViP-LLaVA/blob/main/llava/train/train.py#L901, which is hidden in the transformers clip encoder.
from vip-llava.
ia-gu
commented on June 11, 2024
I didn't know that.
Thanks!!!
from vip-llava.
Related Issues (16)
- [Question] How to get the VIP-Bench? HOT 4
- [Question] When will the Visual Instruction Tuning data be released? HOT 2
- [Question] Will the code for creating Visual Instruction Tuning dataset be released? HOT 5
- Training Stage
- How to use visual prompts with huggingface? HOT 3
- Can u provide the subset only for ViP except llava mix original? HOT 5
- [Question] On the test set used for inference evaluation HOT 1
- [Discussion] Unable to use the demo HOT 3
- [Issue] Tensor mismatch at Runtime HOT 4
- [Usage] pre-requisites for multi-image and multi-prompt generation HOT 3
- [Question] 请问这个文件怎么找不到了呢？convert_vipbench_for_eval.py HOT 1
- [Question] Can you provide register-specific instruction data with the help of GPT-4V? HOT 2
- [Question] Warning occurred when """model = LlavaLlamaForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, **kwargs)""" in builder.py HOT 2
- [Question] Finetune Stage 2 Model HOT 3
- Release of Projector Weights HOT 2
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 vip-llava.