segformer-b1-finetuned-segments-pv-augx3
This model is a fine-tuned version of mouadenna/segformer-b1-finetuned-segments-pv on the mouadenna/satellite_PV_dataset_train_test dataset. It achieves the following results on the evaluation set:
- Loss: 0.0157
- Mean Iou: 0.8465
- Precision: 0.9113
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Mean Iou | Precision |
---|---|---|---|---|---|
0.0038 | 1.0 | 10998 | 0.0083 | 0.8036 | 0.8867 |
0.0001 | 2.0 | 21996 | 0.0073 | 0.8363 | 0.8992 |
0.003 | 3.0 | 32994 | 0.0089 | 0.8086 | 0.8877 |
0.0044 | 4.0 | 43992 | 0.0098 | 0.8356 | 0.9120 |
0.0085 | 5.0 | 54990 | 0.0103 | 0.8363 | 0.8955 |
0.0025 | 6.0 | 65988 | 0.0097 | 0.8295 | 0.9055 |
0.0 | 7.0 | 76986 | 0.0135 | 0.8148 | 0.9072 |
0.0 | 8.0 | 87984 | 0.0106 | 0.8300 | 0.9011 |
0.0033 | 9.0 | 98982 | 0.0133 | 0.8357 | 0.9160 |
0.0022 | 10.0 | 109980 | 0.0128 | 0.8407 | 0.9197 |
0.0019 | 11.0 | 120978 | 0.0150 | 0.8455 | 0.9136 |
0.0017 | 12.0 | 131976 | 0.0115 | 0.8430 | 0.9191 |
0.0024 | 13.0 | 142974 | 0.0126 | 0.8470 | 0.9171 |
0.0029 | 14.0 | 153972 | 0.0155 | 0.8385 | 0.9127 |
0.0024 | 15.0 | 164970 | 0.0145 | 0.8430 | 0.9085 |
0.0029 | 16.0 | 175968 | 0.0148 | 0.8408 | 0.8980 |
0.0038 | 17.0 | 186966 | 0.0168 | 0.8471 | 0.9170 |
0.002 | 18.0 | 197964 | 0.0154 | 0.8437 | 0.9115 |
0.0024 | 19.0 | 208962 | 0.0167 | 0.8458 | 0.9276 |
0.0017 | 20.0 | 219960 | 0.0157 | 0.8465 | 0.9113 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 15
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for mouadenna/segformer-b1-finetuned-segments-pv-augx3
Base model
nvidia/segformer-b1-finetuned-ade-512-512
Finetuned
this model