giuseppemartino
commited on
Commit
•
1adee0d
1
Parent(s):
4c272fc
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
base_model: nvidia/mit-b0
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: model1
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# model1
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.3138
|
19 |
+
- Mean Iou: 0.0868
|
20 |
+
- Mean Accuracy: 0.1217
|
21 |
+
- Overall Accuracy: 0.2285
|
22 |
+
- Accuracy Background: nan
|
23 |
+
- Accuracy Ship: 0.1353
|
24 |
+
- Accuracy Small-vehicle: 0.0001
|
25 |
+
- Accuracy Tennis-court: 0.7306
|
26 |
+
- Accuracy Helicopter: nan
|
27 |
+
- Accuracy Basketball-court: 0.0
|
28 |
+
- Accuracy Ground-track-field: 0.0
|
29 |
+
- Accuracy Swimming-pool: 0.0
|
30 |
+
- Accuracy Harbor: 0.5786
|
31 |
+
- Accuracy Soccer-ball-field: 0.0
|
32 |
+
- Accuracy Plane: 0.0
|
33 |
+
- Accuracy Storage-tank: 0.0
|
34 |
+
- Accuracy Baseball-diamond: 0.0
|
35 |
+
- Accuracy Large-vehicle: 0.2588
|
36 |
+
- Accuracy Bridge: 0.0
|
37 |
+
- Accuracy Roundabout: 0.0
|
38 |
+
- Iou Background: 0.0
|
39 |
+
- Iou Ship: 0.0532
|
40 |
+
- Iou Small-vehicle: 0.0001
|
41 |
+
- Iou Tennis-court: 0.7062
|
42 |
+
- Iou Helicopter: nan
|
43 |
+
- Iou Basketball-court: 0.0
|
44 |
+
- Iou Ground-track-field: 0.0
|
45 |
+
- Iou Swimming-pool: 0.0
|
46 |
+
- Iou Harbor: 0.2868
|
47 |
+
- Iou Soccer-ball-field: 0.0
|
48 |
+
- Iou Plane: 0.0
|
49 |
+
- Iou Storage-tank: 0.0
|
50 |
+
- Iou Baseball-diamond: 0.0
|
51 |
+
- Iou Large-vehicle: 0.2563
|
52 |
+
- Iou Bridge: 0.0
|
53 |
+
- Iou Roundabout: 0.0
|
54 |
+
|
55 |
+
## Model description
|
56 |
+
|
57 |
+
More information needed
|
58 |
+
|
59 |
+
## Intended uses & limitations
|
60 |
+
|
61 |
+
More information needed
|
62 |
+
|
63 |
+
## Training and evaluation data
|
64 |
+
|
65 |
+
More information needed
|
66 |
+
|
67 |
+
## Training procedure
|
68 |
+
|
69 |
+
### Training hyperparameters
|
70 |
+
|
71 |
+
The following hyperparameters were used during training:
|
72 |
+
- learning_rate: 6e-05
|
73 |
+
- train_batch_size: 8
|
74 |
+
- eval_batch_size: 8
|
75 |
+
- seed: 1337
|
76 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
77 |
+
- lr_scheduler_type: polynomial
|
78 |
+
- training_steps: 200
|
79 |
+
|
80 |
+
### Training results
|
81 |
+
|
82 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Ship | Accuracy Small-vehicle | Accuracy Tennis-court | Accuracy Helicopter | Accuracy Basketball-court | Accuracy Ground-track-field | Accuracy Swimming-pool | Accuracy Harbor | Accuracy Soccer-ball-field | Accuracy Plane | Accuracy Storage-tank | Accuracy Baseball-diamond | Accuracy Large-vehicle | Accuracy Bridge | Accuracy Roundabout | Iou Background | Iou Ship | Iou Small-vehicle | Iou Tennis-court | Iou Helicopter | Iou Basketball-court | Iou Ground-track-field | Iou Swimming-pool | Iou Harbor | Iou Soccer-ball-field | Iou Plane | Iou Storage-tank | Iou Baseball-diamond | Iou Large-vehicle | Iou Bridge | Iou Roundabout |
|
83 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:-------------:|:----------------------:|:---------------------:|:-------------------:|:-------------------------:|:---------------------------:|:----------------------:|:---------------:|:--------------------------:|:--------------:|:---------------------:|:-------------------------:|:----------------------:|:---------------:|:-------------------:|:--------------:|:--------:|:-----------------:|:----------------:|:--------------:|:--------------------:|:----------------------:|:-----------------:|:----------:|:---------------------:|:---------:|:----------------:|:--------------------:|:-----------------:|:----------:|:--------------:|
|
84 |
+
| 2.069 | 1.0 | 105 | 1.4975 | 0.0942 | 0.1496 | 0.2837 | nan | 0.4327 | 0.0002 | 0.8374 | nan | 0.0 | 0.0 | 0.0 | 0.4733 | 0.0002 | 0.0 | 0.0 | 0.0 | 0.3506 | 0.0 | 0.0 | 0.0 | 0.0794 | 0.0002 | 0.7660 | nan | 0.0 | 0.0 | 0.0 | 0.2213 | 0.0002 | 0.0 | 0.0 | 0.0 | 0.3460 | 0.0 | 0.0 |
|
85 |
+
| 1.5141 | 1.9 | 200 | 1.3138 | 0.0868 | 0.1217 | 0.2285 | nan | 0.1353 | 0.0001 | 0.7306 | nan | 0.0 | 0.0 | 0.0 | 0.5786 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2588 | 0.0 | 0.0 | 0.0 | 0.0532 | 0.0001 | 0.7062 | nan | 0.0 | 0.0 | 0.0 | 0.2868 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2563 | 0.0 | 0.0 |
|
86 |
+
|
87 |
+
|
88 |
+
### Framework versions
|
89 |
+
|
90 |
+
- Transformers 4.35.0.dev0
|
91 |
+
- Pytorch 2.0.1+cu118
|
92 |
+
- Datasets 2.14.5
|
93 |
+
- Tokenizers 0.14.1
|