Skip to content
ModelListedExternal
Download

Mit B0 Image Segmentation Dominoes v2

This model is a fine-tuned version of nvidia/mit-b0.

Sourcehuggingface.co/DunnBC22/mit-b0-Image_segmentation_Dominoes_v2/tree/5f7220f0a367495ddedd85f1a0216309fa119fec
KindOtherVersionRevision 5f7220f

Model source

Kind
Other
File size
16.0 MB
Version
vRevision 5f7220f
Updated
Sep 15, 2026
Downloads
0
Source
Hugging Face

Source description

mit-b0-Image_segmentation_Dominoes_v2

This model is a fine-tuned version of nvidia/mit-b0.

It achieves the following results on the evaluation set:

  • Loss: 0.1149
  • Mean Iou: 0.9198
  • Mean Accuracy: 0.9515
  • Overall Accuracy: 0.9778
  • Per Category Iou:
    • Segment 0: 0.974110559111975
    • Segment 1: 0.8655745252092782
  • Per Category Accuracy
    • Segment 0: 0.9897833441005461
    • Segment 1: 0.913253525550903

Model description

For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Computer%20Vision/Image%20Segmentation/Dominoes/Fine-Tuning%20-%20Dominoes%20-%20Image%20Segmentation%20with%20LoRA.ipynb

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

Training and evaluation data

Dataset Source: https://huggingface.co/datasets/adelavega/dominoes_raw

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0005
  • 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: 25

Training results

Training LossEpochStepValidation LossMean IouMean AccuracyOverall AccuracyPer Category Iou Segment 0Per Category Iou Segment 1Per Category Accuracy Segment 0Per Category Accuracy Segment 1
0.04611.0860.12330.91500.95270.97620.97219678540319230.85786191722510590.98690826334644980.9184139264010376
0.07082.01720.13660.91720.94900.97710.97328218530931640.86110087881650830.98984736007517470.9082362492748777
0.0483.02580.12600.91990.95340.97770.97401181740142710.86582418442338720.98883925530040530.9179240730467295
0.05354.03440.11840.92000.95200.97780.9741424447921980.86587110640233690.98962911845891820.9142864290038782
0.01855.04300.12960.91820.94770.97750.97377156950131290.86271082921678070.99104187466964230.904378218719681
0.0366.05160.14100.92130.95380.97820.97450024084430080.86806735819225540.98926775121865270.9182967669045321
0.03767.06020.14510.92060.95500.97790.97414557439060730.86697032373672140.98830046396899040.9216576612178001
0.01868.06880.13800.91750.94960.97720.97336168524685840.86164663501922370.98970435191166970.9094762400541087
0.01629.07740.14590.92180.95390.97830.97468406498520510.86889301490008040.9894552769131380.9182917005479264
0.016910.08600.14670.91910.95020.97760.97390866009128140.86421879781933320.99011957479297590.9102564589713776
0.010211.09460.15490.91910.95240.97750.97376964999310410.86442473316091530.98897897456980090.915789237032027
0.020412.010320.15020.92150.95270.97830.9746395960783760.86829649160212730.9899029776237740.9155653673995151
0.026813.011180.14130.91940.95050.97770.97400205318558340.86471993761360.990116990661890.9107963425971664
0.016614.012040.15840.91730.95180.97700.97311544757379290.86142760325425780.98841428319727490.9152366875147241
0.015915.012900.15630.91700.94920.97700.97318324022539960.86074428583810360.98964568038996890.9087960816798012
0.021116.013760.14350.91500.94810.97640.97252013602758980.85748470004910360.9893233100370.9068449010920532
0.012817.014620.14210.92120.95190.97820.97457898014645040.86773944027947540.99019204792388560.9136255861141298
0.016718.015480.15580.92170.95320.97830.97468119936268790.86864700094846970.98974282022669880.9166850322093621
0.020119.016340.16230.91560.94840.97660.97271847200071180.85843393256952520.98944846420391140.9072695251050635
0.013320.017200.15730.91890.95050.97760.97383205001573030.86402036130691150.98986650613731130.9112263496140702
0.01221.018060.16310.91650.94720.97690.97313442430014820.85978661897962950.99045921184001880.9040137576913626
0.014822.018920.16290.91810.95070.97730.97351624291218350.86272399554891920.98940347683091560.9120129014770962
0.013723.019780.17010.91360.94840.97600.97196818433387510.85526078820283880.98850836906090320.908250815050119
0.014224.020640.16460.91460.94880.97630.97231341977640930.85689184017443420.98874058847712450.9089100747034281
0.015625.021500.16150.91440.94650.97630.97239292597863950.8563453542896240.98984876960122160.9032139066422469

Framework versions

  • Transformers 4.26.1
  • Pytorch 2.0.1
  • Datasets 2.13.1
  • Tokenizers 0.13.3

License Notice

This model is a fine-tuned derivative of a pretrained model. Users must comply with the original model license.

Dataset Notice

This model was fine-tuned on third-party datasets which may have separate licenses or usage restrictions.

Sources

1 source
Hugging FacePrimaryVersion 5f7220f0a367495ddedd85f1a0216309fa119fec
huggingface.co/DunnBC22/mit-b0-Image_segmentation_Dominoes_v2/tree/5f7220f0a367495ddedd85f1a0216309fa119fec

Verified Sep 15

Model artifacts

1 artifact

pytorch_model.bin

bin · 16.0 MB · SHA-256 5da41be1126c…c86e · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeSep 15huggingface.co/DunnBC22/mit-b0-Image_segmentation_Dominoes_v2

--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: mit-b0-Image_segmentation_Dominoes_v2 results: [] datasets: - adelavega/dominoes_raw language: - en metrics: - mean_iou pipeline_tag: image-segmentation --- # mit-b0-Image_segmentation_Dominoes_v2 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0). It achieves the following results on the evaluation set: - Loss: 0.1149 - Mean Iou: 0.9198 - Mean Accuracy: 0.9515 - Overall Accuracy: 0.9778 - Per Category Iou: - Segment 0: 0.974110559111975 - Segment 1: 0.8655745252092782 - Per Category Accuracy - Segment 0: 0.9897833441005461 - Segment 1: 0.913253525550903 ## Model description For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Computer%20Vision/Image%20Segmentation/Dominoes/Fine-Tuning%20-%20Dominoes%20-%20Image%20Segmentation%20with%20LoRA.ipynb ## Intended uses & limitations This model is intended to demonstrate my ability to solve a complex problem using technology. ## Training and evaluation data Dataset Source: https://huggingface.co/datasets/adelavega/dominoes_raw ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - 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: 25 ### Training results | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou Segment 0 | Per Category Iou Segment 1 | Per Category Accuracy Segment 0 | Per Category Accuracy Segment 1| |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------------:|:---------------------:|:-----------------:| | 0.0461 | 1.0 | 86 | 0.1233 | 0.9150 | 0.9527 | 0.9762 | 0.9721967854031923 | 0.8578619172251059 | 0.9869082633464498 | 0.9184139264010376 | | 0.0708 | 2.0 | 172 | 0.1366 | 0.9172 | 0.9490 | 0.9771 | 0.9732821853093164 | 0.8611008788165083 | 0.9898473600751747 | 0.9082362492748777 | | 0.048 | 3.0 | 258 | 0.1260 | 0.9199 | 0.9534 | 0.9777 | 0.9740118174014271 | 0.8658241844233872 | 0.9888392553004053 | 0.9179240730467295 | | 0.0535 | 4.0 | 344 | 0.1184 | 0.92...

NoteSep 15huggingface.co/DunnBC22/mit-b0-Image_segmentation_Dominoes_v2

Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Repo DunnBC22/mit-b0-Image_segmentation_Dominoes_v2