Open-source Model of Tomato Leaf Disease Classification with ResNet50 - High-accuracy Classification of Tomato Leaf Disease Images

Tomato Leaf Disease Classification Resnet50

Developed by wellCh4n

A ResNet-50 fine-tuned tomato leaf disease image classification model with 99.56% accuracy

Open Source License:Apache-2.0 #High-precision image classification #Agricultural disease detection #ResNet50 fine-tuning

Downloads 109

Release Time : 12/21/2024

Model Overview

This model is a fine-tuned version of microsoft/resnet-50 on a tomato leaf disease image dataset, specifically designed to identify and classify various diseases in tomato leaves.

Model Features

High accuracy

Achieves 99.56% accuracy on the evaluation set, reliably identifying tomato leaf diseases

Based on ResNet-50

Uses the mature ResNet-50 architecture as the base model, ensuring high stability

Fine-tuned

Trained for 100 epochs with loss reduced to 0.0197

Model Capabilities

Tomato leaf disease image classification

Plant disease recognition

Agricultural image analysis

Use Cases

Agriculture

Tomato disease diagnosis

Helps farmers quickly identify the type of disease affecting tomato leaves

99.56% accuracy

Smart agriculture monitoring

Integrated into agricultural monitoring systems for automatic plant health detection

🚀 tomato-leaf-disease-classification-resnet50

This model is a fine - tuned version of microsoft/resnet - 50 on the wellCh4n/tomato - leaf - disease - image dataset. It can classify tomato leaf diseases effectively. With high accuracy on the evaluation set, it provides a reliable solution for tomato leaf disease identification.

🚀 Quick Start

This model is a fine - tuned version of microsoft/resnet - 50 on the wellCh4n/tomato - leaf - disease - image dataset. It achieves the following results on the evaluation set:

Loss: 0.0197
Accuracy: 0.9956

🔧 Technical Details

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e - 05
train_batch_size: 16
eval_batch_size: 8
seed: 1337
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon = 1e - 08 and optimizer_args = No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 100.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6891	1.0	965	1.6572	0.3488
1.1351	2.0	1930	1.1593	0.7126
0.7767	3.0	2895	0.6135	0.8168
0.7963	4.0	3860	0.3818	0.8796
0.547	5.0	4825	0.2581	0.9302
0.5104	6.0	5790	0.2106	0.9438
0.3997	7.0	6755	0.1579	0.9563
0.2527	8.0	7720	0.1292	0.9604
0.3268	9.0	8685	0.1154	0.9659
0.2595	10.0	9650	0.1018	0.9699
0.2269	11.0	10615	0.0869	0.9743
0.2515	12.0	11580	0.0783	0.9747
0.2604	13.0	12545	0.0710	0.9794
0.2583	14.0	13510	0.0704	0.9783
0.2004	15.0	14475	0.0603	0.9824
0.2552	16.0	15440	0.0565	0.9835
0.2192	17.0	16405	0.0553	0.9846
0.3443	18.0	17370	0.0508	0.9831
0.1954	19.0	18335	0.0530	0.9846
0.2685	20.0	19300	0.0430	0.9864
0.1277	21.0	20265	0.0406	0.9864
0.1388	22.0	21230	0.0404	0.9872
0.2379	23.0	22195	0.0399	0.9875
0.1018	24.0	23160	0.0441	0.9879
0.2155	25.0	24125	0.0364	0.9905
0.1699	26.0	25090	0.0398	0.9875
0.2772	27.0	26055	0.0364	0.9872
0.1669	28.0	27020	0.0369	0.9894
0.0867	29.0	27985	0.0339	0.9901
0.1314	30.0	28950	0.0322	0.9905
0.082	31.0	29915	0.0362	0.9879
0.0393	32.0	30880	0.0332	0.9908
0.0812	33.0	31845	0.0329	0.9905
0.2634	34.0	32810	0.0333	0.9897
0.1581	35.0	33775	0.0337	0.9901
0.168	36.0	34740	0.0298	0.9890
0.0653	37.0	35705	0.0311	0.9905
0.0998	38.0	36670	0.0326	0.9901
0.0947	39.0	37635	0.0288	0.9919
0.1126	40.0	38600	0.0272	0.9916
0.1319	41.0	39565	0.0272	0.9919
0.0446	42.0	40530	0.0283	0.9916
0.2453	43.0	41495	0.0281	0.9919
0.0708	44.0	42460	0.0263	0.9923
0.0441	45.0	43425	0.0262	0.9916
0.0936	46.0	44390	0.0252	0.9919
0.1565	47.0	45355	0.0284	0.9923
0.0404	48.0	46320	0.0263	0.9930
0.0357	49.0	47285	0.0240	0.9930
0.0971	50.0	48250	0.0285	0.9916
0.0582	51.0	49215	0.0251	0.9923
0.048	52.0	50180	0.0257	0.9919
0.1218	53.0	51145	0.0252	0.9930
0.0576	54.0	52110	0.0227	0.9930
0.0723	55.0	53075	0.0227	0.9930
0.1347	56.0	54040	0.0242	0.9941
0.1684	57.0	55005	0.0255	0.9927
0.0525	58.0	55970	0.0250	0.9938
0.1031	59.0	56935	0.0265	0.9923
0.0768	60.0	57900	0.0244	0.9941
0.0416	61.0	58865	0.0207	0.9934
0.1783	62.0	59830	0.0237	0.9941
0.1253	63.0	60795	0.0269	0.9912
0.0448	64.0	61760	0.0236	0.9941
0.0967	65.0	62725	0.0230	0.9934
0.0486	66.0	63690	0.0229	0.9941
0.0442	67.0	64655	0.0256	0.9934
0.0526	68.0	65620	0.0210	0.9945
0.0949	69.0	66585	0.0250	0.9938
0.0674	70.0	67550	0.0228	0.9938
0.1554	71.0	68515	0.0240	0.9941
0.0598	72.0	69480	0.0233	0.9945
0.0632	73.0	70445	0.0218	0.9949
0.0951	74.0	71410	0.0234	0.9945
0.1634	75.0	72375	0.0245	0.9945
0.2039	76.0	73340	0.0222	0.9938
0.0741	77.0	74305	0.0226	0.9949
0.0923	78.0	75270	0.0218	0.9949
0.0351	79.0	76235	0.0230	0.9945
0.1234	80.0	77200	0.0244	0.9934
0.0659	81.0	78165	0.0232	0.9945
0.0393	82.0	79130	0.0210	0.9949
0.053	83.0	80095	0.0205	0.9945
0.0575	84.0	81060	0.0210	0.9945
0.0651	85.0	82025	0.0198	0.9949
0.0875	86.0	82990	0.0210	0.9945
0.1006	87.0	83955	0.0214	0.9949
0.0466	88.0	84920	0.0211	0.9941
0.088	89.0	85885	0.0233	0.9923
0.1162	90.0	86850	0.0197	0.9956
0.0641	91.0	87815	0.0213	0.9949
0.0867	92.0	88780	0.0203	0.9952
0.0305	93.0	89745	0.0212	0.9941
0.1009	94.0	90710	0.0200	0.9956
0.084	95.0	91675	0.0200	0.9960
0.0409	96.0	92640	0.0213	0.9949
0.107	97.0	93605	0.0210	0.9934
0.0558	98.0	94570	0.0206	0.9952
0.0644	99.0	95535	0.0219	0.9949
0.0617	100.0	96500	0.0205	0.9941

Framework versions

Transformers 4.48.0.dev0
Pytorch 2.2.2+cu121
Datasets 3.2.0
Tokenizers 0.21.0

📄 License

This project is licensed under the Apache - 2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご