segformer-b0-scene-parse-150

Abdul-Malik2/segformer-b0-scene-parse-150

segformer-b0-scene-parse-150 is a machine learning model from Abdul-Malik2. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.

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

Downloads · 30 days

15% of all-time downloads

All-time downloads

Public

Parameters

3.8M

75.9 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors15 MB · 98%

At a glance

Library: transformers
License: other
Model type: segformer
Access: Public
Created: Jul 10, 2024
Updated: Jul 10, 2024
SHA: e2ae80c7

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: 2.8675
Mean Iou: 0.0830
Mean Accuracy: 0.1553
Overall Accuracy: 0.4251
Per Category Iou: [0.3597057610822097, 0.3444723083110554, 0.6334161356517982, 0.3976080383212627, 0.37469800131781245, 0.5604704466961906, 0.23988992998711206, 0.12690576810401785, 0.29890176448058714, 0.0, 0.14539640665907227, 0.0, 0.3895866848162356, nan, 0.0, 0.0, 0.0, 0.0, 0.3494325806740212, 0.06402476934172241, 0.2781215871860211, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]
Per Category Accuracy: [0.6924285026724422, 0.9934500051171835, 0.968882368878404, 0.688172159037774, 0.43075369271556624, 0.7035221673273578, 0.9511609840310746, 0.13871477625769882, 0.34856762988968987, 0.0, 0.3711192956323903, 0.0, 0.830179972311952, nan, 0.0, 0.0, nan, 0.0, 0.5454691948219369, 0.258639742816958, 0.31221904372701265, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
3.2363	10.0	200	3.4789	0.0480	0.1134	0.3570	[0.34776362039858744, 0.22716396005487668, 0.48075902292244016, 0.3291210320924504, 0.24404346999556428, 0.18118483487534318, 0.413099381048567, 0.014949604275180951, 0.20976987200081162, 0.0, 0.027225817997434905, 0.0, 0.025186625682203125, nan, 0.0, 0.0, 0.0, 0.0, 0.09577497871340908, 0.0847707420777767, 0.007433562534844824, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]	[0.7201070665619643, 0.9715825742844472, 0.9755631769191628, 0.7526059088849084, 0.48620754955182427, 0.22294909098010116, 0.8791368148467846, 0.015056957540742356, 0.38658412447805224, 0.0, 0.04656335125539447, 0.0, 0.026468455402465556, nan, 0.0, 0.0, nan, 0.0, 0.1051297201482516, 0.41460719308820576, 0.008173273395995096, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]
2.2796	20.0	400	3.0639	0.0729	0.1395	0.4248	[0.4054169729196725, 0.1827672596961913, 0.5600825950640339, 0.3917649962290462, 0.3770419058712594, 0.56305100004092, 0.28967097042898793, 0.03003900819307031, 0.2871440220317861, 0.0, 0.08210268055229296, 0.0, 0.3776770361106769, nan, 0.0, 0.0, nan, 0.0, 0.2258286529981052, 0.032549392718569284, 0.20625110365530638, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]	[0.7545012144905754, 0.9830450653293761, 0.975067568014062, 0.8164821488946918, 0.4290809241257417, 0.8060952827302492, 0.9365386275356063, 0.03032512127323268, 0.38771630969939963, 0.0, 0.16046196068029014, 0.0, 0.4778165996440108, nan, 0.0, 0.0, nan, 0.0, 0.28552398345598107, 0.10998091219610207, 0.2386595831630568, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]
1.8693	30.0	600	2.9826	0.0800	0.1555	0.4292	[0.34912224427270383, 0.37038557245837717, 0.5705390010462278, 0.4289785688354097, 0.3489654511016807, 0.5334485359403492, 0.2814315110845303, 0.0993378788475939, 0.2991825253450139, 0.0, 0.12820534617526172, 0.0, 0.44030637208777146, nan, 0.0, 0.0, 0.0, 0.0, 0.3549159972909399, 0.060302941998560816, 0.2956989247311828, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]	[0.6555687840739897, 0.9850919387302562, 0.9729727943751694, 0.7947680399392854, 0.45938012877161977, 0.7274111972504833, 0.9586016400517912, 0.10303455605821116, 0.3767268421380643, 0.0, 0.3077323321464644, 0.0, 0.771211022480058, nan, 0.0, 0.0, nan, 0.0, 0.523564484073696, 0.25467148884870405, 0.348385778504291, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]
1.9795	40.0	800	2.8947	0.0826	0.1560	0.4229	[0.36000705470562433, 0.3131759444408609, 0.6375650798341606, 0.38137971707978147, 0.3736203543943253, 0.5301140559612703, 0.23101380548969278, 0.14818364565375686, 0.3265423070672859, 0.0, 0.12490542140930325, 0.0, 0.40079814750948417, nan, 0.0, 0.0, 0.0, 0.0, 0.3570486385915219, 0.07022085539292017, 0.2892958748221906, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]	[0.672188869468298, 0.9937911506839968, 0.9694440589708516, 0.6559157188999432, 0.4305643226865295, 0.7569567849401473, 0.9570651704790678, 0.16221998146835995, 0.3965660510625922, 0.0, 0.30989522225736355, 0.0, 0.8044366800711978, nan, 0.0, 0.0, nan, 0.0, 0.5525057742923135, 0.2718253968253968, 0.3324478953821005, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]
1.8599	50.0	1000	2.8675	0.0830	0.1553	0.4251	[0.3597057610822097, 0.3444723083110554, 0.6334161356517982, 0.3976080383212627, 0.37469800131781245, 0.5604704466961906, 0.23988992998711206, 0.12690576810401785, 0.29890176448058714, 0.0, 0.14539640665907227, 0.0, 0.3895866848162356, nan, 0.0, 0.0, 0.0, 0.0, 0.3494325806740212, 0.06402476934172241, 0.2781215871860211, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]	[0.6924285026724422, 0.9934500051171835, 0.968882368878404, 0.688172159037774, 0.43075369271556624, 0.7035221673273578, 0.9511609840310746, 0.13871477625769882, 0.34856762988968987, 0.0, 0.3711192956323903, 0.0, 0.830179972311952, nan, 0.0, 0.0, nan, 0.0, 0.5454691948219369, 0.258639742816958, 0.31221904372701265, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0]

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Library: transformers
Type: segformer
License: other
Created: Jul 10, 2024
Updated: Jul 10, 2024