metadata
license: apache-2.0
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: ConvNext-base-chesapeake-land-cover-v0
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9918582375478927
widget:
- src: >-
https://imgs.mongabay.com/wp-content/uploads/sites/20/2020/04/07204605/amazon_coca_01.jpg
example_title: Tree Canopy
- src: >-
https://images.ctfassets.net/nzn0tepgtyr1/4tyavnFHhmNuVky1ISq51k/64aaf596f6b8ee12d0f0e898679c8f4f/Hero_Image.jpg?w=1024&h=710&fl=progressive&q=50&fm=jpg&bg=transparent
example_title: Low Vegetation
- src: >-
https://outline-prod.imgix.net/20170228-YxGtsv8J0ePP0rXcnle2?auto=format&q=60&w=1280&s=27916f48ed9226c2a2b7848de8d7c0d1
example_title: Impervious Surfaces
- src: >-
https://clarity.maptiles.arcgis.com/arcgis/rest/services/World_Imagery/MapServer/tile/15/11883/10109
example_title: Water
ConvNext-base-chesapeake-land-cover-v0
This model is a fine-tuned version of facebook/convnext-base-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0269
- Accuracy: 0.9919
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0076 | 3.45 | 300 | 0.0269 | 0.9919 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2