Update README.md
Browse files
README.md
CHANGED
@@ -7,9 +7,28 @@ tags:
|
|
7 |
- transformers
|
8 |
license: apache-2.0
|
9 |
library_name: transformers
|
10 |
-
pipeline_tag: image-
|
|
|
|
|
|
|
11 |
---
|
12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
# Image Regression Model
|
14 |
|
15 |
This repository contains a model for **image regression** tasks, where the goal is to predict a numerical value from an input image. The model fine-tunes the [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) Vision Transformer using PyTorch and 🤗 Hugging Face tools. You can train the model, upload it to the 🤗 Model Hub, and perform inference using a simple API.
|
|
|
7 |
- transformers
|
8 |
license: apache-2.0
|
9 |
library_name: transformers
|
10 |
+
pipeline_tag: image-classification
|
11 |
+
model-index:
|
12 |
+
- name: Image Quality Regression Model
|
13 |
+
results: []
|
14 |
---
|
15 |
|
16 |
+
# Image Quality Regression Model
|
17 |
+
|
18 |
+
This model is trained on the dataset [yigagilbert/image_quality_dataset](https://huggingface.co/datasets/yigagilbert/image_quality_dataset) and performs regression tasks to predict image quality scores.
|
19 |
+
|
20 |
+
## Model Details
|
21 |
+
|
22 |
+
- **Dataset**: yigagilbert/image_quality_dataset
|
23 |
+
- **Target Column**: quality_score
|
24 |
+
- **Test Split**: 20% test data
|
25 |
+
- **Training Epochs**: 3
|
26 |
+
- **Learning Rate**: 5e-5
|
27 |
+
- **Max Value in Dataset**: 54.02
|
28 |
+
|
29 |
+
This model fine-tunes the [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) Vision Transformer using PyTorch and Hugging Face's 🤗 Transformers library. It predicts a numerical score based on the quality of the input image.
|
30 |
+
|
31 |
+
|
32 |
# Image Regression Model
|
33 |
|
34 |
This repository contains a model for **image regression** tasks, where the goal is to predict a numerical value from an input image. The model fine-tunes the [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) Vision Transformer using PyTorch and 🤗 Hugging Face tools. You can train the model, upload it to the 🤗 Model Hub, and perform inference using a simple API.
|