README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: plant-seedlings-model-ConvNet-all-train
    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: 0.9171143514965464

plant-seedlings-model-ConvNet-all-train

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: 0.2966
• Accuracy: 0.9171

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: 16
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2313	0.31	100	1.0832	0.6731
0.7221	0.61	200	0.6529	0.7913
0.5858	0.92	300	0.5267	0.8204
0.4257	1.23	400	0.5765	0.8051
0.6183	1.53	500	0.6322	0.7928
0.4392	1.84	600	0.4168	0.8649
0.3589	2.15	700	0.5549	0.8066
0.4259	2.45	800	0.4678	0.8396
0.3705	2.76	900	0.4542	0.8396
0.4609	3.07	1000	0.4723	0.8411
0.2082	3.37	1100	0.3631	0.8803
0.4583	3.68	1200	0.3835	0.8688
0.2218	3.99	1300	0.3913	0.8772
0.3716	4.29	1400	0.3858	0.8818
0.3675	4.6	1500	0.3849	0.8734
0.2602	4.91	1600	0.4080	0.8734
0.2091	5.21	1700	0.3767	0.8818
0.2071	5.52	1800	0.3883	0.8795
0.2426	5.83	1900	0.3557	0.8856
0.2917	6.13	2000	0.3550	0.8872
0.1417	6.44	2100	0.2918	0.9110
0.237	6.75	2200	0.3785	0.8864
0.1372	7.06	2300	0.3106	0.9025
0.161	7.36	2400	0.3809	0.8841
0.2354	7.67	2500	0.3739	0.8949
0.2489	7.98	2600	0.3442	0.8941
0.1962	8.28	2700	0.2875	0.9125
0.3157	8.59	2800	0.2959	0.9163
0.1204	8.9	2900	0.3017	0.9087
0.1272	9.2	3000	0.3380	0.9071
0.1768	9.51	3100	0.3611	0.9033
0.2211	9.82	3200	0.2704	0.9210
0.1213	10.12	3300	0.2813	0.9240
0.0432	10.43	3400	0.2956	0.9179
0.1152	10.74	3500	0.3256	0.9094
0.178	11.04	3600	0.3470	0.9094
0.1427	11.35	3700	0.3221	0.9079
0.1046	11.66	3800	0.2559	0.9286
0.1029	11.96	3900	0.2848	0.9202
0.0459	12.27	4000	0.3051	0.9156
0.1063	12.58	4100	0.2825	0.9225
0.0974	12.88	4200	0.3168	0.9233
0.0923	13.19	4300	0.3134	0.9194
0.0736	13.5	4400	0.2480	0.9325
0.0783	13.8	4500	0.2872	0.9202
0.1444	14.11	4600	0.3011	0.9225
0.1507	14.42	4700	0.2794	0.9271
0.1318	14.72	4800	0.2625	0.9271
0.0931	15.03	4900	0.2914	0.9279
0.074	15.34	5000	0.2826	0.9248
0.1306	15.64	5100	0.2836	0.9240
0.0856	15.95	5200	0.2966	0.9171

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3