metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: plant-seedlings-model-ConvNet
    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: 0.9598726114649682

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: 0.2134
Accuracy: 0.9599

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
0.4223	0.8	100	0.2878	0.9140
0.2957	1.6	200	0.2490	0.9204
0.0884	2.4	300	0.2440	0.9293
0.0534	3.2	400	0.2140	0.9350
0.0067	4.0	500	0.1659	0.9554
0.0038	4.8	600	0.1950	0.9548
0.0061	5.6	700	0.1658	0.9618
0.0029	6.4	800	0.1793	0.9599
0.0004	7.2	900	0.2021	0.9592
0.0003	8.0	1000	0.2115	0.9561
0.0004	8.8	1100	0.2106	0.9561
0.0002	9.6	1200	0.1929	0.9605
0.0003	10.4	1300	0.2311	0.9548
0.0002	11.2	1400	0.2091	0.9605
0.0002	12.0	1500	0.2076	0.9586
0.0001	12.8	1600	0.2084	0.9592
0.0002	13.6	1700	0.2094	0.9605
0.0001	14.4	1800	0.2104	0.9592
0.0001	15.2	1900	0.2111	0.9592
0.0001	16.0	2000	0.2117	0.9592
0.0001	16.8	2100	0.2123	0.9592
0.0001	17.6	2200	0.2128	0.9599
0.0001	18.4	2300	0.2131	0.9599
0.0001	19.2	2400	0.2134	0.9599
0.0001	20.0	2500	0.2134	0.9599

Framework versions

Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3