segformer-b0-scene-parse-150

ichigoDifuku/segformer-b0-scene-parse-150

segformer-b0-scene-parse-150 is a machine learning model from ichigoDifuku. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.

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

Downloads · 30 days

9% of all-time downloads

All-time downloads

Public

Parameters

3.8M

888 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors15 MB · 97%

At a glance

License: other
Model type: segformer
Access: Public
Created: Sep 4, 2024
Updated: Sep 4, 2024
SHA: b2ddb601

Base models

nvidia/mit-b0

Datasets

scene_parse_150

Model card

From the Hugging Face model README

segformer-b0-scene-parse-150

This model is a fine-tuned version of nvidia/mit-b0 on the scene_parse_150 dataset. It achieves the following results on the evaluation set:

Loss: 3.1233
Mean Iou: 0.0499
Mean Accuracy: 0.1002
Overall Accuracy: 0.4411
Per Category Iou: [0.48558573747771877, 0.13040346143692588, 0.9710373374855027, 0.35917887889695804, 0.0, 0.45950935394480524, 0.0, 0.03469888477930799, 0.14258438038925844, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.012871409962161157, 0.00034894270360806757, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]
Per Category Accuracy: [0.8242440823423323, 0.8852976913730255, 0.9952386581553576, 0.9823774713471163, nan, 0.5796817673875851, nan, 0.03478226494157777, 0.28032290615539857, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.01971402783715738, 0.009380863039399626, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]

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: 6e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
2.7421	1.0	20	3.3833	0.0463	0.0951	0.4139	[0.5042443160472232, 0.05850488171016955, 0.8878082320584848, 0.3552059557553269, 0.0, 0.4974007656659279, 0.0, 0.0033347828296804143, 0.10203485541816766, nan, 0.0, 0.0, 0.0, nan, 0.00024932681759250023, 0.0, nan, 0.0, 0.0, 0.001161751563896336, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]	[0.7513188848470885, 0.9163122721749696, 0.9921519951664171, 0.9314398624508411, nan, 0.6103084423611317, nan, 0.0033347828296804143, 0.16920282542885973, nan, 0.0, nan, 0.0, nan, 0.00025600655376777645, 0.0, nan, 0.0, 0.0, 0.0012350957199182937, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]
3.338	2.0	40	3.1824	0.0462	0.0946	0.4332	[0.4686670326604448, 0.13915730032570722, 0.9648828898840046, 0.3274356365713295, 0.0, 0.4190856605515857, 0.0, 0.027812371447731, 0.09790729038808323, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 3.951632024025923e-05, 0.0012555534093104115, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]	[0.8435733274776226, 0.8578675577156744, 0.9947986444952321, 0.9834918033414642, nan, 0.4892109453031517, nan, 0.027872685276693794, 0.13039354187689203, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 4.750368153531899e-05, 0.024390243902439025, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]
2.8348	3.0	60	3.2355	0.0479	0.0989	0.4308	[0.4977587888816171, 0.09677729869319446, 0.9652496798975673, 0.3337000632188886, 0.0, 0.4557538169132082, 0.0, 0.022702263454603938, 0.16553768864913834, nan, 0.0, 0.0, 0.0, nan, 8.51032789077602e-05, 0.0, nan, 0.0, 0.0, 0.0005362313659600329, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]	[0.7980985739304478, 0.8856622114216282, 0.9901752173798828, 0.9884163083061771, nan, 0.5406592102530632, nan, 0.022719443393402722, 0.3245206861755802, nan, 0.0, nan, 0.0, nan, 8.960229381872175e-05, 0.0, nan, 0.0, 0.0, 0.0007125552230297848, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]
2.9176	4.0	80	3.0589	0.0482	0.0988	0.4382	[0.4815405728526445, 0.120691916707657, 0.9705470746080861, 0.348264306570234, 0.0, 0.45544011136441587, 0.0, 0.03298657094071039, 0.1403600808116887, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0036486576956550848, 0.0, nan, 0.0, 0.00011733708812015317, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]	[0.8235601161302631, 0.8944106925880924, 0.9928941077573752, 0.9833692651152817, nan, 0.5581135471365988, nan, 0.033056987795993746, 0.2537840565085772, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.005177901287349769, 0.0, nan, 0.0, 0.00011874561450855509, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]
2.1008	5.0	100	3.1233	0.0499	0.1002	0.4411	[0.48558573747771877, 0.13040346143692588, 0.9710373374855027, 0.35917887889695804, 0.0, 0.45950935394480524, 0.0, 0.03469888477930799, 0.14258438038925844, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.012871409962161157, 0.00034894270360806757, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]	[0.8242440823423323, 0.8852976913730255, 0.9952386581553576, 0.9823774713471163, nan, 0.5796817673875851, nan, 0.03478226494157777, 0.28032290615539857, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.01971402783715738, 0.009380863039399626, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan]

Framework versions

Transformers 4.38.1
Pytorch 2.2.1+cu118
Datasets 2.17.1
Tokenizers 0.15.2

Type: segformer
License: other
Created: Sep 4, 2024
Updated: Sep 4, 2024