Hugging Face's logo

gabryland
/
segformer-b0-scene-parse-150

Transformers
PyTorch
mobilenet_v2
Generated from Trainer
Inference Endpoints
Model card Files Community
segformer-b0-scene-parse-150 / README.md
gabryland's picture
gabryland
End of training
120b821
preview code
|
raw
history blame
No virus
16.5 kB
metadata
license: other
base_model: nvidia/mit-b0
tags:
  - generated_from_trainer
datasets:
  - scene_parse_150
model-index:
  - name: segformer-b0-scene-parse-150
    results: []

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: 3.4665
  • Mean Iou: 0.0596
  • Mean Accuracy: 0.1359
  • Overall Accuracy: 0.4392
  • Per Category Iou: [0.4369308289136906, 0.5390531861708264, 0.7806619522280952, 0.25341104919885854, 0.5939211557701883, 0.21029731689630166, 0.03775321846661953, 0.0, 0.0, 0.0, 0.0, 0.002723446397623174, 0.12626911992906228, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan]
  • Per Category Accuracy: [0.8276826426182997, 0.7252631639463956, 0.8762896838835232, 0.9514163715892522, 0.908369101786115, 0.9991596638655462, 0.970954356846473, nan, 0.0, 0.0, 0.0, 0.003452685421994885, 0.12703793741775765, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 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, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan]

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: 5

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Per Category Iou Per Category Accuracy
4.1138 1.0 20 3.5923 0.0459 0.1223 0.4089 [0.35723370295933743, 0.5162530695362255, 0.726180424243145, 0.24500030028226533, 0.569993262578118, 0.16459880769603163, 0.03380835149201125, 0.0, 0.0, 0.0, 5.4562177498558e-05, 0.0022205357393821853, 0.003557853796517281, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] [0.6474820143884892, 0.743315262071622, 0.8271451083447344, 0.6372891064361591, 0.9229621530778376, 1.0, 0.9628386624359287, nan, 0.0, 0.0, 5.459494450813854e-05, 0.0027551732155312717, 0.0035907843968151303, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 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, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan]
3.6347 2.0 40 3.5674 0.0555 0.1351 0.4366 [0.37577073102588626, 0.507346436067792, 0.7429683161481081, 0.23907579531108764, 0.5818840703737301, 0.14949183233655108, 0.046892337670538776, 0.0, 0.0, 0.0, 0.0006549043761645994, 0.003635267747829199, 0.2393301269552407, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] [0.8858445637855913, 0.6725728839089117, 0.8940619228876276, 0.8160279108519058, 0.8927399987586477, 0.9851260504201681, 0.9515499145716377, nan, 0.0, 0.0, 0.0006551393340976625, 0.004487328528249244, 0.24638133684234004, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 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, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan]
3.3739 3.0 60 3.4325 0.0540 0.1343 0.4345 [0.3931353314298779, 0.5473345728972985, 0.5605308184651546, 0.27310002437997294, 0.5805699150469913, 0.23971139505824499, 0.042515474233820315, 0.0, 0.0, 0.0, 0.00012465330798716072, 0.004730406108308634, 0.11034163340023379, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] [0.7492197791062924, 0.7192496306218775, 0.8786557035070371, 0.9624557383878358, 0.9209401811419486, 0.9994957983193278, 0.9644251891628021, nan, 0.0, 0.0, 0.00012478844459003097, 0.0056033480585910254, 0.11158195240537949, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 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, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan]
2.7294 4.0 80 3.5095 0.0588 0.1365 0.4391 [0.4367203759211508, 0.5260393891311319, 0.766558679562061, 0.24752678821217544, 0.5941136782621366, 0.1820021152342852, 0.03941723696794307, 0.0, 0.0, 0.0, 0.0, 0.0030525762452389953, 0.14415391768326433, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] [0.8451970817712028, 0.726171517928493, 0.8782357801769096, 0.9559987502603624, 0.8954948460006971, 0.9978151260504202, 0.9682694654625336, nan, 0.0, 0.0, 0.0, 0.003847942338990932, 0.145214889488592, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 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, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan]
3.7789 5.0 100 3.4665 0.0596 0.1359 0.4392 [0.4369308289136906, 0.5390531861708264, 0.7806619522280952, 0.25341104919885854, 0.5939211557701883, 0.21029731689630166, 0.03775321846661953, 0.0, 0.0, 0.0, 0.0, 0.002723446397623174, 0.12626911992906228, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan] [0.8276826426182997, 0.7252631639463956, 0.8762896838835232, 0.9514163715892522, 0.908369101786115, 0.9991596638655462, 0.970954356846473, nan, 0.0, 0.0, 0.0, 0.003452685421994885, 0.12703793741775765, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 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, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, 0.0, nan, nan]

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3