Downloads · 30 days
0
BLIP_fine_tune
datnguyentien204/BLIP_fine_tune
BLIP_fine_tune is a machine learning model from datnguyentien204. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This implementation applies the BLIP pre-trained model to solve the icon domain task.
Access
Public
Updated May 16, 2024
Repo size
260 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.zip260 MB · 100%
At a glance
- Access
- Public
- Created
- May 15, 2024
- Updated
- May 16, 2024
- SHA
- 6f4677fb
Model card
From the Hugging Face model README
Visual Question Answering using BLIP pre-trained model!
This implementation applies the BLIP pre-trained model to solve the icon domain task.
 | |
|---|---|
| How many dots are there? | 36 |
Description
**Note: The test dataset does not have labels. I evaluated the model via Kaggle competition and got 96% in accuracy manner. Obviously, you can use a partition of the training set as a testing set.
Create data folder
Copy all data following the example form You can download data here
Install requirements.txt
pip install -r requirements.txt
Run finetuning code
python finetuning.py
Run prediction
python predicting.py
- Created
- May 15, 2024
- Updated
- May 16, 2024