---
base_model: openai/clip-vit-base-patch32
tags:
- generated_from_trainer
model-index:
- name: clip-fine-tuned-satellite-20240821
  results: []
license: mit
datasets:
- blanchon/UC_Merced
metrics:
- accuracy
---


# clip-fine-tuned-satellite

This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on the blanchon/UC_Merced dataset.\
It achieves the following results on the test set:\
-Accuracy: 96.9% \
The original CLIP model achieves 58.8% of accuracy.

## Model description

The model is a fine-tuned version of CLIP.\
30% of the parameters were retrained to achieve a significant increase in accuracy after only 2 epochs.

## Intended uses & limitations

The model is to be used to classify satellite images.\
It was trained on the UC_Merced dataset that comprises 21 classes: agricultural, airplane, baseballdiamond, beach, buildings, chaparral, denseresidential, forest, freeway, golfcourse, harbor, intersection, mediumresidential, mobilehomepark, overpass, parkinglot, river, runway, sparseresidential, storagetanks, tenniscourt

## Training and evaluation data

30% of the parameters trained.\
Evaluated against a test set of 420 images.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.4974        | 1.0   | 20   | 3.0190          |
| 1.3733        | 2.0   | 40   | 2.9588          |


### Framework versions

- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1