update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: segformer-b0-finetuned-pokemon
|
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-pokemon
|
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: 0.0298
|
18 |
+
- Mean Iou: 0.4971
|
19 |
+
- Mean Accuracy: 0.9941
|
20 |
+
- Overall Accuracy: 0.9941
|
21 |
+
- Per Category Iou: [0.0, 0.99410193702663]
|
22 |
+
- Per Category Accuracy: [nan, 0.99410193702663]
|
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: 24
|
43 |
+
- eval_batch_size: 24
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 50
|
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 |
+
| 0.0286 | 40.0 | 1160 | 0.0304 | 0.4965 | 0.9929 | 0.9929 | [0.0, 0.9929262067682688] | [nan, 0.9929262067682688] |
|
54 |
+
| 0.0272 | 41.0 | 1189 | 0.0301 | 0.4966 | 0.9933 | 0.9933 | [0.0, 0.9932505252321254] | [nan, 0.9932505252321254] |
|
55 |
+
| 0.0279 | 42.0 | 1218 | 0.0305 | 0.4973 | 0.9947 | 0.9947 | [0.0, 0.994698129326027] | [nan, 0.994698129326027] |
|
56 |
+
| 0.0309 | 43.0 | 1247 | 0.0295 | 0.4966 | 0.9931 | 0.9931 | [0.0, 0.9931164081595019] | [nan, 0.9931164081595019] |
|
57 |
+
| 0.028 | 44.0 | 1276 | 0.0294 | 0.4967 | 0.9934 | 0.9934 | [0.0, 0.9933975466612431] | [nan, 0.9933975466612431] |
|
58 |
+
| 0.0276 | 45.0 | 1305 | 0.0298 | 0.4970 | 0.9941 | 0.9941 | [0.0, 0.994062837929389] | [nan, 0.994062837929389] |
|
59 |
+
| 0.0281 | 46.0 | 1334 | 0.0300 | 0.4969 | 0.9939 | 0.9939 | [0.0, 0.9938931511561724] | [nan, 0.9938931511561724] |
|
60 |
+
| 0.0273 | 47.0 | 1363 | 0.0297 | 0.4968 | 0.9936 | 0.9936 | [0.0, 0.993593207587916] | [nan, 0.993593207587916] |
|
61 |
+
| 0.0291 | 48.0 | 1392 | 0.0297 | 0.4970 | 0.9941 | 0.9941 | [0.0, 0.9940591430922732] | [nan, 0.9940591430922732] |
|
62 |
+
| 0.0269 | 49.0 | 1421 | 0.0294 | 0.4968 | 0.9936 | 0.9936 | [0.0, 0.9936409647363091] | [nan, 0.9936409647363091] |
|
63 |
+
| 0.0279 | 50.0 | 1450 | 0.0298 | 0.4971 | 0.9941 | 0.9941 | [0.0, 0.99410193702663] | [nan, 0.99410193702663] |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.20.1
|
69 |
+
- Pytorch 1.12.0+cu113
|
70 |
+
- Datasets 2.3.2
|
71 |
+
- Tokenizers 0.12.1
|