cancer-Vit

laiagdla/cancer-Vit

cancer-Vit is a image classification model from laiagdla. 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

15% of all-time downloads

All-time downloads

Public

Parameters

85.8M

343 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors343 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Dec 1, 2023
Updated: Dec 1, 2023
SHA: 9c67a1ac

Base models

google/vit-base-patch16-224-in21k

Spaces

laiagdla/cancer-Vit-classification

Model card

From the Hugging Face model README

model

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1898
Accuracy: 0.9243

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2732	0.1	100	0.3969	0.8461
0.2784	0.21	200	0.3714	0.8579
0.301	0.31	300	0.3504	0.8376
0.2372	0.42	400	0.3391	0.8812
0.3136	0.52	500	0.2559	0.8967
0.3517	0.62	600	0.4141	0.8397
0.3312	0.73	700	0.3043	0.8841
0.2515	0.83	800	0.2541	0.9062
0.2854	0.93	900	0.2561	0.9006
0.2594	1.04	1000	0.2681	0.9020
0.177	1.14	1100	0.3406	0.8773
0.2717	1.25	1200	0.2266	0.9171
0.2197	1.35	1300	0.2080	0.9236
0.155	1.45	1400	0.2048	0.9236
0.2657	1.56	1500	0.2037	0.9256
0.118	1.66	1600	0.2616	0.9096
0.1823	1.77	1700	0.2158	0.9241
0.2175	1.87	1800	0.2159	0.9182
0.143	1.97	1900	0.1898	0.9243
0.1051	2.08	2000	0.2308	0.9226
0.1963	2.18	2100	0.2354	0.9205
0.0524	2.28	2200	0.2298	0.9282
0.097	2.39	2300	0.2495	0.9241
0.0744	2.49	2400	0.2493	0.9194
0.0744	2.6	2500	0.2429	0.9323
0.0345	2.7	2600	0.2587	0.9252
0.0097	2.8	2700	0.2284	0.9265
0.0775	2.91	2800	0.2242	0.9321
0.0634	3.01	2900	0.2314	0.9286
0.0109	3.12	3000	0.2203	0.9338
0.0039	3.22	3100	0.2575	0.9358
0.0139	3.32	3200	0.2570	0.9356
0.0358	3.43	3300	0.2630	0.9335
0.0347	3.53	3400	0.2633	0.9358
0.0408	3.63	3500	0.2591	0.9335
0.041	3.74	3600	0.2613	0.9367
0.004	3.84	3700	0.2587	0.9370
0.0389	3.95	3800	0.2535	0.9373

Framework versions

Transformers 4.35.0
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.14.1

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Created: Dec 1, 2023
Updated: Dec 1, 2023