Comments (7)
Also, several functions are never called in the script, e.g.,:
preprocess_vqa2_to_val_dataset()
preprocess_avsd_to_val_dataset()
resize_image()
Are these functions abandoned, or they are called but not illustrated in the python script?
from macaw-llm.
Also, in preprocess_avsd_to_tensor_dataset(), the audios and frames extracted from videos are actually not utilized. Is this correct?
from macaw-llm.
My last question is regarding the filtering: in preprocess_avsd_to_tensor_dataset(), we don't have a filtering step based on the input text length. In other preprocess functions (for vqa and alpaca), we have filtering steps based on the length of input text without answer. Why we filter based on the input text rather than the full_text? And why the avsd preprocessing don't have a filter step?
from macaw-llm.
Hi, sorry for the late reply. For downloading corresponding files, they are also used in preprocessing steps (vqa and avsd dataset for supervised data and our instruction dataset for unsupervised data). The metadata and raw images/videos of vqa and avsd are used in supervised data whereas only raw images/videos of vqa and avsd are used in unsupervised data with our instruction data. The image_path
is the directory to the coco images.
from macaw-llm.
Also, several functions are never called in the script, e.g.,: preprocess_vqa2_to_val_dataset() preprocess_avsd_to_val_dataset() resize_image()
Are these functions abandoned, or they are called but not illustrated in the python script?
The first two functions are used to process validation dataset for evaluation and inference. The last one is used to resize images as well as video frames.
from macaw-llm.
Also, in preprocess_avsd_to_tensor_dataset(), the audios and frames extracted from videos are actually not utilized. Is this correct?
Usually we do not directly store image pixels in tensor dataset as it would incur significant memory use, instead we keep the index of the image and load it during training.
from macaw-llm.
My last question is regarding the filtering: in preprocess_avsd_to_tensor_dataset(), we don't have a filtering step based on the input text length. In other preprocess functions (for vqa and alpaca), we have filtering steps based on the length of input text without answer. Why we filter based on the input text rather than the full_text? And why the avsd preprocessing don't have a filter step?
This is because when the instruction is longer than the maximum length then no response will be included in the sequence, thus model can not learn how to generate response.
from macaw-llm.
Related Issues (20)
- Missing License File HOT 2
- Question about finetuning all parameters of LLM? HOT 1
- Can I use this in Windows? HOT 1
- which llama tokenizer to use? HOT 1
- Paths for pretrained models
- How many GPU memory needed to finetune the model? HOT 1
- Could you please share the code to generate the instruct data? HOT 1
- What is the pad ID for tokenizer? HOT 1
- How to get the whisper, clip, and llama model used by macaw? HOT 3
- Always have same response HOT 5
- Performance of the model HOT 3
- Data filtering step
- Using pad_token, but it is not set yet.
- Some weights of MM_LLMs were not initialized from the model checkpoint at ./mm_llms_trainer/ and are newly initialized: HOT 1
- please update the demo code?
- How can i run train.sh on only one GPU?
- Deployment of Macaw-LLM
- TypeError: string indices must be integers, not 'str'
- Requirement Versions
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 macaw-llm.