student-resnet18-tiny-imagenet

thethinkmachine/student-resnet18-tiny-imagenet

student-resnet18-tiny-imagenet is a image classification model from thethinkmachine. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

26% of all-time downloads

All-time downloads

Public

Parameters

11.3M

181 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors45.2 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: resnet
Access: Public
Created: Dec 27, 2025
Updated: Dec 27, 2025
SHA: bc6d38ae

Base models

microsoft/resnet-18

Model card

From the Hugging Face model README

student

This model is a fine-tuned version of microsoft/resnet-18 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.0839
Accuracy: 0.4336
Precision: 0.5017
Recall: 0.4336
F1: 0.4223

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: 0.0003
train_batch_size: 8
eval_batch_size: 8
seed: 42
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: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
4.3903	0.012	150	4.2290	0.0146	0.0134	0.0146	0.0083
3.846	0.024	300	3.6356	0.0838	0.0946	0.0838	0.0592
3.3778	0.036	450	3.0217	0.1558	0.2091	0.1558	0.1167
2.9266	0.048	600	2.6267	0.1918	0.2768	0.1918	0.1498
2.7657	0.06	750	2.3280	0.2335	0.3684	0.2335	0.1946
2.6257	0.072	900	2.1951	0.2758	0.3689	0.2758	0.2381
2.4699	0.084	1050	2.3175	0.2424	0.3960	0.2424	0.2101
2.5352	0.096	1200	2.2917	0.2533	0.3728	0.2533	0.2284
2.4032	0.108	1350	2.4920	0.251	0.3818	0.251	0.2225
2.332	0.12	1500	2.3880	0.2639	0.3638	0.2639	0.2324
2.3968	0.132	1650	2.4804	0.2687	0.3862	0.2687	0.2531
2.3922	0.144	1800	2.3411	0.2886	0.4126	0.2886	0.2600
2.3328	0.156	1950	2.2690	0.3191	0.3973	0.3191	0.2896
2.3191	0.168	2100	2.1504	0.3387	0.4172	0.3387	0.3161
2.1208	0.18	2250	2.1226	0.3369	0.4232	0.3369	0.3154
2.2256	0.192	2400	2.0580	0.3629	0.4330	0.3629	0.3372
2.1618	0.204	2550	2.0567	0.3585	0.4509	0.3585	0.3360
2.2237	0.216	2700	2.3808	0.3446	0.4299	0.3446	0.3254
2.0754	0.228	2850	2.2442	0.3718	0.4656	0.3718	0.3529
1.9684	0.24	3000	2.1301	0.3848	0.4569	0.3848	0.3590
2.082	0.252	3150	2.0963	0.3734	0.4557	0.3734	0.3533
2.0737	0.264	3300	2.2619	0.3621	0.4506	0.3621	0.3443
2.0049	0.276	3450	2.3372	0.3748	0.4527	0.3748	0.3542
1.9876	0.288	3600	2.0522	0.4025	0.4759	0.4025	0.3818
1.9218	0.3	3750	2.1785	0.4002	0.4704	0.4002	0.3863
1.9899	0.312	3900	2.3298	0.4059	0.4758	0.4059	0.3852
1.9478	0.324	4050	2.0669	0.4245	0.4732	0.4245	0.4033
1.9293	0.336	4200	2.1866	0.4154	0.4885	0.4154	0.3986
1.8939	0.348	4350	2.1652	0.4159	0.4788	0.4159	0.3944
1.8356	0.36	4500	2.1702	0.4245	0.4706	0.4245	0.4002
1.8724	0.372	4650	2.1267	0.4282	0.4825	0.4282	0.4089
1.7633	0.384	4800	2.1603	0.4262	0.4896	0.4262	0.4065
1.8592	0.396	4950	2.0575	0.4393	0.4837	0.4393	0.4187
1.7407	0.408	5100	2.0839	0.4336	0.5017	0.4336	0.4223

Framework versions

Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 4.4.2
Tokenizers 0.22.1

Task: Image Classification
Library: transformers
Type: resnet
License: apache-2.0
Created: Dec 27, 2025
Updated: Dec 27, 2025