metadata

license: apache-2.0
base_model: microsoft/resnet-152
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: resnet-152-finetuned-cassava-leaf-disease
    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: 0.7397196261682243

resnet-152-finetuned-cassava-leaf-disease

This model is a fine-tuned version of microsoft/resnet-152 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.7961
Accuracy: 0.7397

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: 5e-05
train_batch_size: 480
eval_batch_size: 480
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 1920
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
7.309	0.98	10	7.0088	0.0028
6.9946	1.95	20	6.4363	0.0061
6.4082	2.93	30	5.5840	0.0673
5.6018	4.0	41	4.1884	0.3687
4.5652	4.98	51	3.3123	0.4640
3.6106	5.95	61	2.7918	0.5136
2.9184	6.93	71	2.3762	0.5636
2.3775	8.0	82	1.9163	0.6084
2.0119	8.98	92	1.7038	0.6299
1.7519	9.95	102	1.5220	0.6411
1.4995	10.93	112	1.3828	0.6575
1.3648	12.0	123	1.2715	0.6668
1.2357	12.98	133	1.2040	0.6692
1.1606	13.95	143	1.1249	0.6785
1.0793	14.93	153	1.0600	0.6897
1.0332	16.0	164	1.0160	0.6935
0.9724	16.98	174	0.9706	0.7047
0.9349	17.95	184	0.9524	0.7075
0.895	18.93	194	0.9210	0.7093
0.8913	20.0	205	0.9007	0.7168
0.8519	20.98	215	0.8672	0.7229
0.8434	21.95	225	0.8432	0.7252
0.8346	22.93	235	0.8307	0.7304
0.8019	24.0	246	0.8154	0.7308
0.8001	24.98	256	0.8121	0.7327
0.7813	25.95	266	0.8036	0.7341
0.7845	26.93	276	0.8025	0.7383
0.7635	28.0	287	0.7934	0.7444
0.7782	28.98	297	0.7910	0.7421
0.7634	29.27	300	0.7961	0.7397

Framework versions

Transformers 4.37.2
Pytorch 2.2.1
Datasets 2.18.0
Tokenizers 0.15.1