MT-magic-puddle-87

AmineAllo/MT-magic-puddle-87

MT-magic-puddle-87 is a object detection model from AmineAllo. Use it when you need objects located in an image. It is set up for transformers.

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

Downloads · 30 days

1% of all-time downloads

All-time downloads

788

Public

Repo size

4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin115 MB · 100%

At a glance

Task: Object Detection
Library: transformers
Model type: table-transformer
Access: Public
Created: Oct 23, 2023
Updated: Oct 24, 2023
SHA: a9bc5101

Base models

Model card

From the Hugging Face model README

MT-magic-puddle-87

This model is a fine-tuned version of toobiza/table-transformer-stellar-vortex-81 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1979
Loss Ce: 0.0000
Loss Bbox: 0.0275
Cardinality Error: 1.0
Giou: 96.9810

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: 1e-05
train_batch_size: 4
eval_batch_size: 4
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	Loss Bbox	Cardinality Error	Giou
0.4142	0.12	50	0.2543	0.0350	1.0	96.0232
0.2876	0.24	100	0.2384	0.0329	1.0	96.2958
0.2522	0.36	150	0.2250	0.0311	1.0	96.5247
0.2324	0.48	200	0.2360	0.0327	1.0	96.3714
0.1855	0.6	250	0.2155	0.0296	1.0	96.6185
0.2339	0.72	300	0.2184	0.0302	1.0	96.6205
0.2416	0.85	350	0.2034	0.0279	1.0	96.8059
0.213	0.97	400	0.2072	0.0286	1.0	96.7959
0.2173	1.09	450	0.2089	0.0287	1.0	96.7273
0.2038	1.21	500	0.2239	0.0311	1.0	96.5835
0.1789	1.33	550	0.2235	0.0312	1.0	96.6211
0.159	1.45	600	0.2111	0.0293	1.0	96.7661
0.1629	1.57	650	0.2071	0.0286	1.0	96.7952
0.2541	1.69	700	0.2016	0.0280	1.0	96.9076
0.1917	1.81	750	0.2017	0.0279	1.0	96.8974
0.1642	1.93	800	0.2058	0.0283	1.0	96.7995
0.1598	2.05	850	0.1913	0.0263	1.0	96.9992
0.1551	2.17	900	0.1958	0.0269	1.0	96.9452
0.1698	2.29	950	0.2028	0.0281	1.0	96.8889
0.1414	2.42	1000	0.2063	0.0287	1.0	96.8551
0.1605	2.54	1050	0.1988	0.0276	1.0	96.9509
0.1929	2.66	1100	0.2085	0.0290	1.0	96.8305
0.1563	2.78	1150	0.2031	0.0282	1.0	96.9069
0.1263	2.9	1200	0.2004	0.0278	1.0	96.9343
0.1588	3.02	1250	0.2031	0.0282	1.0	96.8919
0.2023	3.14	1300	0.1986	0.0276	1.0	96.9607
0.1434	3.26	1350	0.1981	0.0275	1.0	96.9762
0.1436	3.38	1400	0.1995	0.0278	1.0	96.9637
0.1208	3.5	1450	0.1996	0.0278	1.0	96.9668
0.1371	3.62	1500	0.1993	0.0277	1.0	96.9602
0.1585	3.74	1550	0.1983	0.0275	1.0	96.9670
0.1356	3.86	1600	0.1980	0.0275	1.0	96.9826
0.1306	3.99	1650	0.1979	0.0275	1.0	96.9810

Framework versions

Transformers 4.33.2
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.13.3

Task: Object Detection
Library: transformers
Type: table-transformer
Created: Oct 23, 2023
Updated: Oct 24, 2023