Title
Image Regression Model
This model was trained with Image Regression Model Trainer. It takes an image as input and outputs a float value.
from ImageRegression import predict
predict(repo_id='-',image_path='image.jpg')
Dataset
Dataset:
Value Column:
Train Test Split:
Training
Base Model: google/vit-base-patch16-224
Epochs:
Learning Rate:
Usage
Download
git clone https://github.com/TonyAssi/ImageRegression.git
cd ImageRegression
Installation
pip install -r requirements.txt
Import
from ImageRegression import train_model, upload_model, predict
Inference (Prediction)
- repo_id ๐ค repo id of the model
- image_path path to image
predict(repo_id='-',
image_path='image.jpg')
The first time this function is called it'll download the safetensor model. Subsequent function calls will run faster.
Train Model
- dataset_id ๐ค dataset id
- value_column_name column name of prediction values in dataset
- test_split test split of the train/test split
- output_dir the directory where the checkpoints will be saved
- num_train_epochs training epochs
- learning_rate learning rate
train_model(dataset_id='-',
value_column_name='-',
test_split=-,
output_dir='./results',
num_train_epochs=-,
learning_rate=1e-)
The trainer will save the checkpoints in the output_dir location. The model.safetensors are the trained weights you'll use for inference (predicton).
Upload Model
This function will upload your model to the ๐ค Hub.
- model_id the name of the model id
- token go here to create a new ๐ค token
- checkpoint_dir checkpoint folder that will be uploaded
upload_model(model_id='-',
token='YOUR_HF_TOKEN',
checkpoint_dir='./results/checkpoint-940')
Model tree for tonyassi/sales-pred-3
Base model
google/vit-base-patch16-224