finetuned-Leukemia-cell

JorgeGIT/finetuned-Leukemia-cell

finetuned-Leukemia-cell is a image classification model from JorgeGIT. 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

1% of all-time downloads

All-time downloads

2.9K

Public

Parameters

27.8M

2.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors111 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: convnext
Access: Public
Created: Nov 30, 2023
Updated: Dec 3, 2023
SHA: aab16b4d

Base models

facebook/convnext-tiny-224

Datasets

imagefolder

Spaces

filmm/leukemia

Model card

From the Hugging Face model README

finetuned-Leukemia-cell

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: 0.1128
Accuracy: 0.9850

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: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 300
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3182	2.94	100	0.2301	0.9211
0.2223	5.88	200	0.3411	0.8910
0.1695	8.82	300	0.1168	0.9624
0.0579	11.76	400	0.1632	0.9511
0.1184	14.71	500	0.4665	0.8346
0.0575	17.65	600	0.1563	0.9586
0.1087	20.59	700	0.2023	0.9511
0.1164	23.53	800	0.2283	0.9398
0.1144	26.47	900	0.1130	0.9624
0.1821	29.41	1000	0.1155	0.9737
0.0882	32.35	1100	0.0760	0.9850
0.1099	35.29	1200	0.0894	0.9737
0.053	38.24	1300	0.1248	0.9699
0.0489	41.18	1400	0.1081	0.9774
0.065	44.12	1500	0.1694	0.9549
0.037	47.06	1600	0.1060	0.9699
0.0281	50.0	1700	0.0892	0.9737
0.0394	52.94	1800	0.1680	0.9624
0.0828	55.88	1900	0.1404	0.9774
0.0663	58.82	2000	0.1683	0.9662
0.0698	61.76	2100	0.1517	0.9624
0.0938	64.71	2200	0.1031	0.9737
0.0324	67.65	2300	0.1251	0.9812
0.0713	70.59	2400	0.1597	0.9662
0.059	73.53	2500	0.1455	0.9699
0.0404	76.47	2600	0.0924	0.9624
0.0526	79.41	2700	0.0853	0.9812
0.0439	82.35	2800	0.0815	0.9850
0.0485	85.29	2900	0.1192	0.9774
0.0498	88.24	3000	0.0958	0.9737
0.0181	91.18	3100	0.1351	0.9699
0.0226	94.12	3200	0.1458	0.9774
0.1115	97.06	3300	0.1453	0.9737
0.0349	100.0	3400	0.1257	0.9812
0.0246	102.94	3500	0.1405	0.9662
0.0084	105.88	3600	0.0666	0.9887
0.0174	108.82	3700	0.1419	0.9662
0.0432	111.76	3800	0.2027	0.9662
0.0164	114.71	3900	0.0671	0.9812
0.0223	117.65	4000	0.0722	0.9850
0.012	120.59	4100	0.1285	0.9699
0.0143	123.53	4200	0.1102	0.9812
0.0254	126.47	4300	0.1139	0.9812
0.018	129.41	4400	0.1056	0.9737
0.0011	132.35	4500	0.1097	0.9774
0.08	135.29	4600	0.1425	0.9662
0.0292	138.24	4700	0.0871	0.9812
0.0248	141.18	4800	0.1082	0.9699
0.0064	144.12	4900	0.0644	0.9850
0.0115	147.06	5000	0.0912	0.9812
0.052	150.0	5100	0.0927	0.9850
0.0103	152.94	5200	0.1129	0.9774
0.0185	155.88	5300	0.1250	0.9699
0.0185	158.82	5400	0.1226	0.9737
0.0002	161.76	5500	0.1146	0.9812
0.0249	164.71	5600	0.1945	0.9737
0.0165	167.65	5700	0.1875	0.9586
0.0028	170.59	5800	0.1045	0.9774
0.0044	173.53	5900	0.1279	0.9774
0.0078	176.47	6000	0.0967	0.9774
0.0093	179.41	6100	0.1450	0.9812
0.0261	182.35	6200	0.0815	0.9850
0.0218	185.29	6300	0.1586	0.9699
0.1184	188.24	6400	0.1481	0.9812
0.0011	191.18	6500	0.1698	0.9737
0.0131	194.12	6600	0.2247	0.9662
0.0156	197.06	6700	0.1205	0.9812
0.007	200.0	6800	0.1864	0.9699
0.015	202.94	6900	0.1684	0.9774
0.0032	205.88	7000	0.0835	0.9850
0.0017	208.82	7100	0.1174	0.9812
0.0397	211.76	7200	0.1926	0.9662
0.0015	214.71	7300	0.1646	0.9699
0.0046	217.65	7400	0.1520	0.9774
0.0193	220.59	7500	0.1436	0.9812
0.0474	223.53	7600	0.1747	0.9737
0.001	226.47	7700	0.1647	0.9812
0.0005	229.41	7800	0.1992	0.9699
0.0119	232.35	7900	0.1545	0.9699
0.0153	235.29	8000	0.2018	0.9662
0.0106	238.24	8100	0.1798	0.9774
0.0012	241.18	8200	0.1896	0.9774
0.0	244.12	8300	0.1500	0.9812
0.0339	247.06	8400	0.1890	0.9662
0.0016	250.0	8500	0.1410	0.9812
0.0003	252.94	8600	0.1341	0.9812
0.001	255.88	8700	0.1209	0.9850
0.0071	258.82	8800	0.1191	0.9812
0.0	261.76	8900	0.0960	0.9887
0.0016	264.71	9000	0.1063	0.9850
0.0048	267.65	9100	0.1583	0.9737
0.0026	270.59	9200	0.1473	0.9774
0.0006	273.53	9300	0.1325	0.9812
0.0226	276.47	9400	0.1214	0.9812
0.0075	279.41	9500	0.1399	0.9812
0.0047	282.35	9600	0.1291	0.9850
0.0	285.29	9700	0.1117	0.9812
0.0001	288.24	9800	0.1137	0.9850
0.0001	291.18	9900	0.1117	0.9850
0.0	294.12	10000	0.1061	0.9850
0.0	297.06	10100	0.1129	0.9850
0.0057	300.0	10200	0.1128	0.9850

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

Task: Image Classification
Library: transformers
Type: convnext
License: apache-2.0
Created: Nov 30, 2023
Updated: Dec 3, 2023