Skip to content
ModelListedExternal
Download

Detr Resnet 50 Fine Tuned Loc 2023

> For new projects, consider small-models-for-glam/historic-newspaper-illustrations-yolov11 — a more recent YOLO-based detector for illustrations in historic newspaper pages, faster at inference. This DETR model is...

Sourcehuggingface.co/biglam/detr-resnet-50_fine_tuned_loc-2023/tree/c52fa2408a0575009cb25b79864d2e3898bd102c
KindOtherBase modelfacebook/detr-resnet-50VersionRevision c52fa24

Model source

Kind
Other
File size
159 MB
Base model
facebook/detr-resnet-50
Version
vRevision c52fa24
Updated
Sep 16, 2026
Downloads
21
Tasks
Object detection
Source
Hugging Face

Source description

detr-resnet-50_fine_tuned_loc-2023

For new projects, consider small-models-for-glam/historic-newspaper-illustrations-yolov11 — a more recent YOLO-based detector for illustrations in historic newspaper pages, faster at inference. This DETR model is kept for reproducibility.

This model is a fine-tuned version of facebook/detr-resnet-50 on the loc_beyond_words dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8784

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: 0.0001
  • 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: 100

Training results

Training LossEpochStepValidation Loss
3.7310.16502.6356
2.48750.311002.2348
2.17860.471502.1148
1.98450.622001.8847
1.85070.782501.8331
1.68130.943001.5620
1.56131.093501.5898
1.49661.254001.4161
1.48311.414501.4831
1.45871.565001.3218
1.4331.725501.3529
1.331.886001.2453
1.28422.036501.2956
1.28072.197001.1993
1.17672.347501.1557
1.21342.58001.1393
1.18972.668501.2016
1.17842.819001.1235
1.20162.979501.1378
1.063.1210001.0803
1.11243.2810501.1145
1.11913.4411001.0523
1.08193.5911501.0165
1.11963.7512001.0349
1.05343.9112501.0441
1.03654.0613001.1177
0.98534.2213501.0721
0.99844.3814000.9923
0.98024.5314501.0079
1.044.6915001.0198
1.0984.8415500.9788
1.0795.016001.0291
1.06645.1616500.9691
0.97155.3117000.9380
0.97235.4717501.0164
1.00195.6218001.0064
0.98955.7818501.0364
0.98355.9419000.9848
0.9946.0919500.9353
0.96936.2520000.9425
0.94136.4120500.9173
0.93756.5621000.9663
0.9526.7221500.8951
0.89276.8822000.9099
0.87777.0322500.9238
0.89767.1923000.9715
0.94517.3423500.9373
0.89727.524000.8959
0.93937.6624501.0062
0.97.8125000.8920
0.9157.9725500.8833
0.90188.1226000.8671
0.82728.2826500.9304
0.9438.4427000.8593
0.86678.5927500.8875
0.8718.7528000.8457
0.90238.9128500.8448
0.87339.0629000.8261
0.86869.2229500.8489
0.84129.3830000.8244
0.83859.5330500.8830
0.8919.6931000.8349
0.86929.8431500.8672
0.824710.032000.8811
0.79910.1632500.8784

Framework versions

  • Transformers 4.27.4
  • Pytorch 2.0.0+cu118
  • Datasets 2.11.0
  • Tokenizers 0.13.3

Sources

1 source
Hugging FacePrimaryVersion c52fa2408a0575009cb25b79864d2e3898bd102c
huggingface.co/biglam/detr-resnet-50_fine_tuned_loc-2023/tree/c52fa2408a0575009cb25b79864d2e3898bd102c

Verified Sep 16

Model artifacts

2 artifacts

model.safetensors

safetensors · 159 MB · SHA-256 b04627f8e04a…c120 · Hugging Face

Download

pytorch_model.bin

bin · 159 MB · SHA-256 836b068fca72…42a1 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 16huggingface.co/biglam/detr-resnet-50_fine_tuned_loc-2023

--- license: apache-2.0 library_name: transformers tags: - lam - newspapers datasets: - biglam/loc_beyond_words pipeline_tag: object-detection base_model: facebook/detr-resnet-50 model-index: - name: detr-resnet-50_fine_tuned_loc-2023 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # detr-resnet-50_fine_tuned_loc-2023 > **For new projects**, consider [`small-models-for-glam/historic-newspaper-illustrations-yolov11`](https://huggingface.co/small-models-for-glam/historic-newspaper-illustrations-yolov11) — a more recent YOLO-based detector for illustrations in historic newspaper pages, faster at inference. This DETR model is kept for reproducibility. This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the loc_beyond_words dataset. It achieves the following results on the evaluation set: - Loss: 0.8784 ## 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: 0.0001 - 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: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 3.731 | 0.16 | 50 | 2.6356 | | 2.4875 | 0.31 | 100 | 2.2348 | | 2.1786 | 0.47 | 150 | 2.1148 | | 1.9845 | 0.62 | 200 | 1.8847 | | 1.8507 | 0.78 | 250 | 1.8331 | | 1.6813 | 0.94 | 300 | 1.5620 | | 1.5613 | 1.09 | 350 | 1.5898 | | 1.4966 | 1.25 | 400 | 1.4161 | | 1.4831 | 1.41 | 450 | 1.4831 | | 1.4587 | 1.56 | 500 | 1.3218 | | 1.433 | 1.72 | 550 | 1.3529 | | 1.33 | 1.88 | 600 | 1.2453 | | 1.2842 | 2.03 | 650 | 1.2956 | | 1.2807 | 2.19 | 700 | 1.1993 | | 1.1767 | 2.34 | 750 | 1.1557 | | 1.2134 | 2.5 | 800 | 1.1393 | | 1.1897 | 2.66 | 850 | 1.2016 | | 1.1784 | 2.81 | 900 | 1.1235 | | 1.2016 | 2.97 | 950 | 1.1378 | | 1.06 | 3.12 | 1000 | 1.0803 | | 1.1124 | 3.28 | 1050 | 1.1145 | | 1.1191 | 3.44 | 1100 | 1.0523 | | 1.0819 | 3.59 | 1150 | 1.0165 | | 1.1196 | 3.75 | 1200 | 1.0...

NoteSep 16huggingface.co/biglam/detr-resnet-50_fine_tuned_loc-2023

Source context: 21 downloads · 2 likes · Pipeline object-detection · Library transformers · Repo biglam/detr-resnet-50_fine_tuned_loc-2023