segformer-b2-finetuned-segments-pv_v1_normalized_p100_4batch

mouadenna/segformer-b2-finetuned-segments-pv_v1_normalized_p100_4batch

segformer-b2-finetuned-segments-pv_v1_normalized_p100_4batch is a image segmentation model from mouadenna. Use it for the image segmentation 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

27.3M

219 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors109 MB · 100%

At a glance

Task: Image Segmentation
Library: transformers
License: other
Model type: segformer
Access: Public
Created: Jul 28, 2024
Updated: Jul 28, 2024
SHA: f87985ce

Base models

nvidia/segformer-b2-finetuned-ade-512-512

Model card

From the Hugging Face model README

segformer-b2-finetuned-segments-pv_v1_normalized_p100_4batch

This model is a fine-tuned version of nvidia/segformer-b2-finetuned-ade-512-512 on the mouadenna/satellite_PV_dataset_train_test_v1 dataset. It achieves the following results on the evaluation set:

Loss: nan
Mean Iou: 0.0
Precision: 1.0

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: 0.0004
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.001
num_epochs: 40
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Precision
0.01	0.9989	229	0.0088	0.8105	0.8817
0.0062	1.9978	458	0.0075	0.8201	0.8726
0.0049	2.9967	687	0.0063	0.8297	0.8867
0.0053	4.0	917	0.0055	0.8425	0.8845
0.0037	4.9989	1146	0.0058	0.8380	0.8823
0.0039	5.9978	1375	0.0211	0.6114	0.9766
0.0037	6.9967	1604	0.3403	0.0	1.0
0.0002	8.0	1834	nan	0.0	1.0
0.0003	8.9989	2063	nan	0.0	1.0
0.0864	9.9978	2292	nan	0.0	1.0
0.0035	10.9967	2521	nan	0.0	1.0
0.0045	12.0	2751	nan	0.0	1.0
0.0039	12.9989	2980	nan	0.0	1.0
0.8023	13.9978	3209	nan	0.0	1.0
0.0041	14.9967	3438	nan	0.0	1.0
7.0711	16.0	3668	nan	0.0	1.0
0.0039	16.9989	3897	nan	0.0	1.0
19.4385	17.9978	4126	nan	0.0	1.0
0.0001	18.9967	4355	nan	0.0	1.0
1.7398	20.0	4585	nan	0.0	1.0
0.2879	20.9989	4814	nan	0.0	1.0
0.0005	21.9978	5043	nan	0.0	1.0
5.8398	22.9967	5272	nan	0.0	1.0
0.0004	24.0	5502	nan	0.0	1.0
0.0002	24.9989	5731	nan	0.0	1.0
0.0016	25.9978	5960	nan	0.0	1.0
0.0034	26.9967	6189	nan	0.0	1.0
0.0004	28.0	6419	nan	0.0	1.0
0.0036	28.9989	6648	nan	0.0	1.0
0.0314	29.9978	6877	nan	0.0	1.0
0.0921	30.9967	7106	nan	0.0	1.0
89.1025	32.0	7336	nan	0.0	1.0
0.0073	32.9989	7565	nan	0.0	1.0
0.0126	33.9978	7794	nan	0.0	1.0
0.0094	34.9967	8023	nan	0.0	1.0
0.0001	36.0	8253	nan	0.0	1.0
4.3987	36.9989	8482	nan	0.0	1.0
0.0005	37.9978	8711	nan	0.0	1.0
0.0202	38.9967	8940	nan	0.0	1.0
0.1612	39.9564	9160	nan	0.0	1.0

Framework versions

Transformers 4.42.3
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.19.1

Task: Image Segmentation
Library: transformers
Type: segformer
License: other
Created: Jul 28, 2024
Updated: Jul 28, 2024