Deepglobe_segformer_3_400

prnv13/Deepglobe_segformer_3_400

Deepglobe_segformer_3_400 is a machine learning model from prnv13. 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

6% of all-time downloads

All-time downloads

Public

Repo size

209 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin14.9 MB · 100%

At a glance

Library: transformers
License: other
Model type: segformer
Access: Public
Created: Mar 29, 2024
Updated: Mar 29, 2024
SHA: 5cf3a50f

Base models

nvidia/mit-b0

Model card

From the Hugging Face model README

Deepglobe_segformer_3_400

This model is a fine-tuned version of nvidia/mit-b0 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.7188
Mean Iou: 0.4787
Mean Accuracy: 0.6002
Overall Accuracy: 0.8270
Per Category Iou: [0.6299517395035389, 0.8579965667549715, 0.05609795827086041, 0.7364800207464396, 0.535316077547452, 0.5350211742530107, 0.0]
Per Category Accuracy: [0.9063438304928855, 0.918655830242053, 0.06293362989838948, 0.8511005897416815, 0.6186843655274462, 0.8435526450990776, 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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
1.4953	0.25	20	1.6438	0.3034	0.4362	0.7295	[0.4372228066060852, 0.7851195516086454, 0.02767277670705226, 0.5318149141289378, 0.15332072216110113, 0.18882192890212937, 0.0]	[0.9054689287550887, 0.881972966540296, 0.030212967162335593, 0.855402152679511, 0.1546016559161411, 0.22575227044586893, 0.0]
1.1619	0.49	40	1.1145	0.3522	0.4979	0.7453	[0.4963248654368396, 0.7969307673775792, 0.005234675057991406, 0.5334928148352919, 0.40576267255758364, 0.22735397960522108, 0.0]	[0.9263632677194786, 0.8664759596406031, 0.005313323233395412, 0.9408065580353865, 0.4356812098052455, 0.31082581787427777, 0.0]
1.1227	0.74	60	0.8344	0.4328	0.5514	0.8012	[0.559377748191037, 0.833094745127801, 0.01617350405138789, 0.6810331455551815, 0.5222264810642535, 0.4177578560386505, 0.0]	[0.9190514270956751, 0.9199089912495539, 0.016740285242832744, 0.8991225550844304, 0.5349978690495003, 0.5701733759099568, 0.0]
0.9186	0.99	80	0.8410	0.4315	0.5671	0.7981	[0.610435962831109, 0.8248261041118935, 0.01287044797979473, 0.590317136673045, 0.5094678255258223, 0.47235101846741195, 0.0]	[0.8831700349552921, 0.8970489608062372, 0.013270642954328338, 0.9399664246329911, 0.5645757812288003, 0.6713455504003415, 0.0]
1.3163	1.23	100	0.7876	0.4340	0.5585	0.8040	[0.5512733368835496, 0.8404873242788062, 0.013928311212001072, 0.6685287371808809, 0.5155178151904813, 0.44798355714772914, 0.0]	[0.9061603321998727, 0.9229407158322913, 0.014365271974602195, 0.8723671532813903, 0.5859858479347339, 0.6073823083063936, 0.0]
1.0072	1.48	120	0.7143	0.4654	0.5803	0.8279	[0.6290456933460526, 0.8548414682316915, 0.015319296135995817, 0.6898485050535011, 0.519412217733134, 0.5491789992522889, 0.0]	[0.8906250495558662, 0.9439846826240867, 0.01570476015863979, 0.8294264466203112, 0.6039401035306737, 0.7782847364385814, 0.0]
1.0037	1.73	140	0.7418	0.4669	0.5881	0.8238	[0.6374852209379004, 0.8516151187065506, 0.04539433499278664, 0.6791015352123421, 0.5125601555696692, 0.5419419009373415, 0.0]	[0.8948436979663406, 0.928989068607313, 0.0491690469068136, 0.7914770913802412, 0.6247819167700217, 0.8274075815898259, 0.0]
0.8331	1.98	160	0.7708	0.4602	0.6010	0.8148	[0.61646612920421, 0.8431945482344851, 0.029559832548671162, 0.6925368958522767, 0.5197854175542566, 0.519586455316693, 0.0]	[0.9117309779099771, 0.8958172398851775, 0.03212238615858189, 0.914917262843377, 0.6484953254767503, 0.8040762308622557, 0.0]
0.8578	2.22	180	0.6801	0.4823	0.5954	0.8333	[0.6398254047914631, 0.8574983124445581, 0.04405338937855245, 0.7279725707575311, 0.5436762768533776, 0.5633375351596654, 0.0]	[0.8780062570652506, 0.9352013135786893, 0.04717820922310891, 0.8867957701630768, 0.5987970904145536, 0.8214859465526372, 0.0]
0.7435	2.47	200	0.6822	0.4814	0.5994	0.8322	[0.6283252084456665, 0.8600981959587153, 0.04592991298814512, 0.7355128664373006, 0.5428628143906776, 0.5573630881468757, 0.0]	[0.9001945988070346, 0.9301202539919514, 0.04953874805801353, 0.8820072095633354, 0.6198719514239059, 0.8137765082953279, 0.0]
0.8242	2.72	220	0.6634	0.4859	0.5989	0.8355	[0.627805454883537, 0.8613036148884382, 0.05734368620108552, 0.7490310967237723, 0.5390407061468642, 0.5668121927843631, 0.0]	[0.8979554665500735, 0.9377690650548433, 0.06191559475446536, 0.876048855605443, 0.6199629358272637, 0.7987612336682027, 0.0]
1.0752	2.96	240	0.7188	0.4787	0.6002	0.8270	[0.6299517395035389, 0.8579965667549715, 0.05609795827086041, 0.7364800207464396, 0.535316077547452, 0.5350211742530107, 0.0]	[0.9063438304928855, 0.918655830242053, 0.06293362989838948, 0.8511005897416815, 0.6186843655274462, 0.8435526450990776, 0.0]

Framework versions

Transformers 4.31.0
Pytorch 2.0.0+cu117
Datasets 2.10.1
Tokenizers 0.13.3

Library: transformers
Type: segformer
License: other
Created: Mar 29, 2024
Updated: Mar 29, 2024