Edit model card

plant-seedlings-model-ConvNet

This model is a fine-tuned version of facebook/convnext-tiny-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2410
  • Accuracy: 0.9522

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: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.494 0.8 100 0.4274 0.8828
0.246 1.6 200 0.2878 0.8930
0.1042 2.4 300 0.2227 0.9172
0.0174 3.2 400 0.2208 0.9299
0.0088 4.0 500 0.3197 0.9185
0.0078 4.8 600 0.2555 0.9357
0.0013 5.6 700 0.2599 0.9427
0.0068 6.4 800 0.3072 0.9312
0.0007 7.2 900 0.2217 0.9484
0.0004 8.0 1000 0.2551 0.9401
0.0003 8.8 1100 0.2321 0.9478
0.0002 9.6 1200 0.2329 0.9484
0.0002 10.4 1300 0.2322 0.9478
0.0002 11.2 1400 0.2342 0.9478
0.0002 12.0 1500 0.2348 0.9490
0.0001 12.8 1600 0.2358 0.9490
0.0001 13.6 1700 0.2368 0.9497
0.0001 14.4 1800 0.2377 0.9510
0.0001 15.2 1900 0.2384 0.9516
0.0001 16.0 2000 0.2391 0.9516
0.0001 16.8 2100 0.2397 0.9522
0.0001 17.6 2200 0.2401 0.9522
0.0001 18.4 2300 0.2406 0.9522
0.0001 19.2 2400 0.2409 0.9522
0.0001 20.0 2500 0.2410 0.9522

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3
Downloads last month
7
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Evaluation results