pablojrios
commited on
Commit
•
233d794
1
Parent(s):
9d0bb1b
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: segformer-b0-finetuned-segments-sidewalk-2
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# segformer-b0-finetuned-segments-sidewalk-2
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.6110
|
18 |
+
- Mean Iou: 0.1367
|
19 |
+
- Mean Accuracy: 0.1875
|
20 |
+
- Overall Accuracy: 0.6881
|
21 |
+
- Per Category Iou: [nan, 0.4358992825292338, 0.7376212533796545, 0.0, 0.02621246785982382, 0.00043211553703970075, nan, 8.015736841193088e-05, 0.0, 0.0, 0.5772424406028427, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.5033973978720222, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6694084376012885, 0.36677387384992766, 0.7828643395512115, 0.0, 0.0, 0.0, 0.0]
|
22 |
+
- Per Category Accuracy: [nan, 0.7389109053459296, 0.9324628469379894, 0.0, 0.02623033308234139, 0.0004332220803205606, nan, 8.024933685852042e-05, 0.0, 0.0, 0.8439578372191763, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.8847599631606713, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.9401313327814339, 0.38739120652321696, 0.8720917833707338, 0.0, 0.0, 0.0, 0.0]
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 6e-05
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 4
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 1
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
|
53 |
+
| 1.9298 | 0.5 | 100 | 1.7681 | 0.1199 | 0.1738 | 0.6593 | [nan, 0.40090810552182926, 0.7239864361905679, 0.0, 0.0017647225539722043, 0.00039874720019120934, nan, 0.0001017888855199896, 0.0, 0.0, 0.5266858358368541, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.4982673421879428, 0.0, 0.00013373579730320418, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6162371375150854, 0.06163531325154459, 0.7657580090286384, 0.0, 0.0, 0.00018678310951226077, 0.0] | [nan, 0.7294785690321806, 0.9040101249330418, 0.0, 0.001765437619648865, 0.00039998860566583264, nan, 0.0001019383468202827, 0.0, 0.0, 0.8602156135201492, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.8580331196294607, 0.0, 0.00013373747781887638, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.9448016748237693, 0.06210387463397946, 0.852450875265527, 0.0, 0.0, 0.0001871709770030242, 0.0] |
|
54 |
+
| 2.0284 | 1.0 | 200 | 1.6110 | 0.1367 | 0.1875 | 0.6881 | [nan, 0.4358992825292338, 0.7376212533796545, 0.0, 0.02621246785982382, 0.00043211553703970075, nan, 8.015736841193088e-05, 0.0, 0.0, 0.5772424406028427, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.5033973978720222, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6694084376012885, 0.36677387384992766, 0.7828643395512115, 0.0, 0.0, 0.0, 0.0] | [nan, 0.7389109053459296, 0.9324628469379894, 0.0, 0.02623033308234139, 0.0004332220803205606, nan, 8.024933685852042e-05, 0.0, 0.0, 0.8439578372191763, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, 0.8847599631606713, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.9401313327814339, 0.38739120652321696, 0.8720917833707338, 0.0, 0.0, 0.0, 0.0] |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.21.1
|
60 |
+
- Pytorch 1.12.1
|
61 |
+
- Datasets 2.4.0
|
62 |
+
- Tokenizers 0.12.1
|