Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: nvidia/segformer-b3-finetuned-cityscapes-1024-1024
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: route_background_semantic
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# route_background_semantic
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [nvidia/segformer-b3-finetuned-cityscapes-1024-1024](https://huggingface.co/nvidia/segformer-b3-finetuned-cityscapes-1024-1024) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2360
|
| 20 |
+
- Mean Iou: 0.1916
|
| 21 |
+
- Mean Accuracy: 0.2447
|
| 22 |
+
- Overall Accuracy: 0.2962
|
| 23 |
+
- Accuracy Unlabeled: nan
|
| 24 |
+
- Accuracy Découpe: 0.2865
|
| 25 |
+
- Accuracy Reflet météo: 0.0
|
| 26 |
+
- Accuracy Autre réparation: 0.3437
|
| 27 |
+
- Accuracy Glaçage ou ressuage: 0.0386
|
| 28 |
+
- Accuracy Emergence: 0.5549
|
| 29 |
+
- Iou Unlabeled: 0.0
|
| 30 |
+
- Iou Découpe: 0.2515
|
| 31 |
+
- Iou Reflet météo: 0.0
|
| 32 |
+
- Iou Autre réparation: 0.3230
|
| 33 |
+
- Iou Glaçage ou ressuage: 0.0369
|
| 34 |
+
- Iou Emergence: 0.5379
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 6e-05
|
| 54 |
+
- train_batch_size: 4
|
| 55 |
+
- eval_batch_size: 4
|
| 56 |
+
- seed: 1337
|
| 57 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 58 |
+
- lr_scheduler_type: polynomial
|
| 59 |
+
- training_steps: 10000
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Découpe | Accuracy Reflet météo | Accuracy Autre réparation | Accuracy Glaçage ou ressuage | Accuracy Emergence | Iou Unlabeled | Iou Découpe | Iou Reflet météo | Iou Autre réparation | Iou Glaçage ou ressuage | Iou Emergence |
|
| 64 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:----------------:|:---------------------:|:-------------------------:|:----------------------------:|:------------------:|:-------------:|:-----------:|:----------------:|:--------------------:|:-----------------------:|:-------------:|
|
| 65 |
+
| 0.2715 | 1.0 | 2427 | 0.2682 | 0.0521 | 0.0669 | 0.1828 | nan | 0.0813 | 0.0 | 0.2533 | 0.0 | 0.0 | 0.0 | 0.0766 | 0.0 | 0.2362 | 0.0 | 0.0 |
|
| 66 |
+
| 0.2815 | 2.0 | 4854 | 0.2682 | 0.1165 | 0.1436 | 0.1593 | nan | 0.1108 | 0.0 | 0.1982 | 0.0 | 0.4090 | 0.0 | 0.1014 | 0.0 | 0.1916 | 0.0 | 0.4057 |
|
| 67 |
+
| 0.2638 | 3.0 | 7281 | 0.2420 | 0.1664 | 0.2100 | 0.2564 | nan | 0.2346 | 0.0 | 0.3039 | 0.0030 | 0.5085 | 0.0 | 0.2128 | 0.0 | 0.2854 | 0.0030 | 0.4973 |
|
| 68 |
+
| 0.2703 | 4.0 | 9708 | 0.2333 | 0.1941 | 0.2475 | 0.3074 | nan | 0.2843 | 0.0 | 0.3612 | 0.0446 | 0.5473 | 0.0 | 0.2512 | 0.0 | 0.3383 | 0.0429 | 0.5320 |
|
| 69 |
+
| 0.2197 | 4.1203 | 10000 | 0.2360 | 0.1916 | 0.2447 | 0.2962 | nan | 0.2865 | 0.0 | 0.3437 | 0.0386 | 0.5549 | 0.0 | 0.2515 | 0.0 | 0.3230 | 0.0369 | 0.5379 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.46.1
|
| 75 |
+
- Pytorch 2.3.0
|
| 76 |
+
- Datasets 3.1.0
|
| 77 |
+
- Tokenizers 0.20.3
|