Hugging Face's logo

mouadenna
/
segformer-b1-finetuned-segments-pv_v1_normalized_t4_16batch

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mouadenna commited on
Commit
0817cee
·
verified ·
1 Parent(s): eda4507

End of training

Browse files
Files changed (5) hide show
  1. README.md +50 -59
  2. config.json +6 -6
  3. model.safetensors +2 -2
  4. runs/Jul26_10-45-38_4b7d3c846457/events.out.tfevents.1721990743.4b7d3c846457.24.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,12 +1,12 @@
1
  ---
2
- base_model: nvidia/segformer-b1-finetuned-ade-512-512
3
  license: other
4
- metrics:
5
- - precision
6
  tags:
7
  - vision
8
  - image-segmentation
9
  - generated_from_trainer
 
 
10
  model-index:
11
  - name: segformer-b1-finetuned-segments-pv_v1_normalized_t4_16batch
12
  results: []
@@ -15,10 +15,10 @@ model-index:
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mouadn773/huggingface/runs/thj03afd)
19
  # segformer-b1-finetuned-segments-pv_v1_normalized_t4_16batch
20
 
21
- This model is a fine-tuned version of [nvidia/segformer-b1-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b1-finetuned-ade-512-512) on the mouadenna/satellite_PV_dataset_train_test_v1 dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: nan
24
  - Mean Iou: 0.0
@@ -41,70 +41,61 @@ More information needed
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
- - learning_rate: 0.0032
45
- - train_batch_size: 32
46
- - eval_batch_size: 32
47
  - seed: 42
48
  - gradient_accumulation_steps: 4
49
- - total_train_batch_size: 128
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 50
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Precision |
58
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|
59
- | 0.024 | 0.9739 | 28 | 0.0208 | 0.0 | 1.0 |
60
- | 0.0156 | 1.9826 | 57 | 0.0145 | 0.6782 | 0.8283 |
61
- | 0.009 | 2.9913 | 86 | 0.0115 | 0.7282 | 0.9124 |
62
- | 0.0132 | 4.0 | 115 | 0.0098 | 0.7516 | 0.8954 |
63
- | 0.0069 | 4.9739 | 143 | 0.0082 | 0.7743 | 0.9003 |
64
- | 0.0058 | 5.9826 | 172 | 0.0092 | 0.7860 | 0.9163 |
65
- | 0.0064 | 6.9913 | 201 | 0.0115 | 0.7790 | 0.9320 |
66
- | 0.0049 | 8.0 | 230 | 0.0627 | 0.5688 | 0.9780 |
67
- | 0.0063 | 8.9739 | 258 | 0.1204 | 0.3259 | 0.9889 |
68
- | 0.0055 | 9.9826 | 287 | 0.2607 | 0.0005 | 1.0 |
69
- | 0.0065 | 10.9913 | 316 | 0.3377 | 0.0 | 1.0 |
70
- | 0.0079 | 12.0 | 345 | 0.6538 | 0.0 | 1.0 |
71
- | 0.0 | 12.9739 | 373 | nan | 0.0 | 1.0 |
72
- | 0.0 | 13.9826 | 402 | nan | 0.0 | 1.0 |
73
- | 0.0 | 14.9913 | 431 | nan | 0.0 | 1.0 |
74
- | 0.0 | 16.0 | 460 | nan | 0.0 | 1.0 |
75
- | 0.0 | 16.9739 | 488 | nan | 0.0 | 1.0 |
76
- | 0.0 | 17.9826 | 517 | nan | 0.0 | 1.0 |
77
- | 0.0 | 18.9913 | 546 | nan | 0.0 | 1.0 |
78
- | 0.0 | 20.0 | 575 | nan | 0.0 | 1.0 |
79
- | 0.0 | 20.9739 | 603 | nan | 0.0 | 1.0 |
80
- | 0.0 | 21.9826 | 632 | nan | 0.0 | 1.0 |
81
- | 0.0 | 22.9913 | 661 | nan | 0.0 | 1.0 |
82
- | 0.0 | 24.0 | 690 | nan | 0.0 | 1.0 |
83
- | 0.0 | 24.9739 | 718 | nan | 0.0 | 1.0 |
84
- | 0.0 | 25.9826 | 747 | nan | 0.0 | 1.0 |
85
- | 0.0 | 26.9913 | 776 | nan | 0.0 | 1.0 |
86
- | 0.0 | 28.0 | 805 | nan | 0.0 | 1.0 |
87
- | 0.0 | 28.9739 | 833 | nan | 0.0 | 1.0 |
88
- | 0.0 | 29.9826 | 862 | nan | 0.0 | 1.0 |
89
- | 0.0 | 30.9913 | 891 | nan | 0.0 | 1.0 |
90
- | 0.0 | 32.0 | 920 | nan | 0.0 | 1.0 |
91
- | 0.0 | 32.9739 | 948 | nan | 0.0 | 1.0 |
92
- | 0.0 | 33.9826 | 977 | nan | 0.0 | 1.0 |
93
- | 0.0 | 34.9913 | 1006 | nan | 0.0 | 1.0 |
94
- | 0.0 | 36.0 | 1035 | nan | 0.0 | 1.0 |
95
- | 0.0 | 36.9739 | 1063 | nan | 0.0 | 1.0 |
96
- | 0.0 | 37.9826 | 1092 | nan | 0.0 | 1.0 |
97
- | 0.0 | 38.9913 | 1121 | nan | 0.0 | 1.0 |
98
- | 0.0 | 40.0 | 1150 | nan | 0.0 | 1.0 |
99
- | 0.0 | 40.9739 | 1178 | nan | 0.0 | 1.0 |
100
- | 0.0 | 41.9826 | 1207 | nan | 0.0 | 1.0 |
101
- | 0.0 | 42.9913 | 1236 | nan | 0.0 | 1.0 |
102
- | 0.0 | 44.0 | 1265 | nan | 0.0 | 1.0 |
103
- | 0.0 | 44.9739 | 1293 | nan | 0.0 | 1.0 |
104
- | 0.0 | 45.9826 | 1322 | nan | 0.0 | 1.0 |
105
- | 0.0 | 46.9913 | 1351 | nan | 0.0 | 1.0 |
106
- | 0.0 | 48.0 | 1380 | nan | 0.0 | 1.0 |
107
- | 0.0 | 48.6957 | 1400 | nan | 0.0 | 1.0 |
108
 
109
 
110
  ### Framework versions
 
1
  ---
 
2
  license: other
3
+ base_model: nvidia/segformer-b2-finetuned-ade-512-512
 
4
  tags:
5
  - vision
6
  - image-segmentation
7
  - generated_from_trainer
8
+ metrics:
9
+ - precision
10
  model-index:
11
  - name: segformer-b1-finetuned-segments-pv_v1_normalized_t4_16batch
12
  results: []
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mouadn773/huggingface/runs/q060y659)
19
  # segformer-b1-finetuned-segments-pv_v1_normalized_t4_16batch
20
 
21
+ This model is a fine-tuned version of [nvidia/segformer-b2-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b2-finetuned-ade-512-512) on the mouadenna/satellite_PV_dataset_train_test_v1 dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: nan
24
  - Mean Iou: 0.0
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 0.0004
45
+ - train_batch_size: 4
46
+ - eval_batch_size: 4
47
  - seed: 42
48
  - gradient_accumulation_steps: 4
49
+ - total_train_batch_size: 16
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 40
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Precision |
58
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|
59
+ | 0.0042 | 0.9989 | 229 | 0.0076 | 0.8218 | 0.8749 |
60
+ | 0.0089 | 1.9978 | 458 | 0.0088 | 0.7565 | 0.7839 |
61
+ | 0.0076 | 2.9967 | 687 | 0.0054 | 0.8494 | 0.8956 |
62
+ | 0.0133 | 4.0 | 917 | 0.0068 | 0.8062 | 0.8367 |
63
+ | 0.008 | 4.9989 | 1146 | 0.0072 | 0.8127 | 0.8679 |
64
+ | 0.0036 | 5.9978 | 1375 | 0.0143 | 0.7063 | 0.9741 |
65
+ | 0.0031 | 6.9967 | 1604 | 0.6182 | 0.0 | 1.0 |
66
+ | 0.0 | 8.0 | 1834 | nan | 0.0 | 1.0 |
67
+ | 0.0 | 8.9989 | 2063 | nan | 0.0 | 1.0 |
68
+ | 0.0 | 9.9978 | 2292 | nan | 0.0 | 1.0 |
69
+ | 0.0 | 10.9967 | 2521 | nan | 0.0 | 1.0 |
70
+ | 0.0 | 12.0 | 2751 | nan | 0.0 | 1.0 |
71
+ | 0.0 | 12.9989 | 2980 | nan | 0.0 | 1.0 |
72
+ | 0.0 | 13.9978 | 3209 | nan | 0.0 | 1.0 |
73
+ | 0.0 | 14.9967 | 3438 | nan | 0.0 | 1.0 |
74
+ | 0.0 | 16.0 | 3668 | nan | 0.0 | 1.0 |
75
+ | 0.0 | 16.9989 | 3897 | nan | 0.0 | 1.0 |
76
+ | 0.0 | 17.9978 | 4126 | nan | 0.0 | 1.0 |
77
+ | 0.0 | 18.9967 | 4355 | nan | 0.0 | 1.0 |
78
+ | 0.0 | 20.0 | 4585 | nan | 0.0 | 1.0 |
79
+ | 0.0 | 20.9989 | 4814 | nan | 0.0 | 1.0 |
80
+ | 0.0 | 21.9978 | 5043 | nan | 0.0 | 1.0 |
81
+ | 0.0 | 22.9967 | 5272 | nan | 0.0 | 1.0 |
82
+ | 0.0 | 24.0 | 5502 | nan | 0.0 | 1.0 |
83
+ | 0.0 | 24.9989 | 5731 | nan | 0.0 | 1.0 |
84
+ | 0.0 | 25.9978 | 5960 | nan | 0.0 | 1.0 |
85
+ | 0.0 | 26.9967 | 6189 | nan | 0.0 | 1.0 |
86
+ | 0.0 | 28.0 | 6419 | nan | 0.0 | 1.0 |
87
+ | 0.0 | 28.9989 | 6648 | nan | 0.0 | 1.0 |
88
+ | 0.0 | 29.9978 | 6877 | nan | 0.0 | 1.0 |
89
+ | 0.0 | 30.9967 | 7106 | nan | 0.0 | 1.0 |
90
+ | 0.0 | 32.0 | 7336 | nan | 0.0 | 1.0 |
91
+ | 0.0 | 32.9989 | 7565 | nan | 0.0 | 1.0 |
92
+ | 0.0 | 33.9978 | 7794 | nan | 0.0 | 1.0 |
93
+ | 0.0 | 34.9967 | 8023 | nan | 0.0 | 1.0 |
94
+ | 0.0 | 36.0 | 8253 | nan | 0.0 | 1.0 |
95
+ | 0.0 | 36.9989 | 8482 | nan | 0.0 | 1.0 |
96
+ | 0.0 | 37.9978 | 8711 | nan | 0.0 | 1.0 |
97
+ | 0.0 | 38.9967 | 8940 | nan | 0.0 | 1.0 |
98
+ | 0.0 | 39.9564 | 9160 | nan | 0.0 | 1.0 |
 
 
 
 
 
 
 
 
 
99
 
100
 
101
  ### Framework versions
config.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "_name_or_path": "nvidia/segformer-b1-finetuned-ade-512-512",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
6
  "attention_probs_dropout_prob": 0.0,
7
  "classifier_dropout_prob": 0.1,
8
- "decoder_hidden_size": 256,
9
  "depths": [
10
- 2,
11
- 2,
12
- 2,
13
- 2
14
  ],
15
  "downsampling_rates": [
16
  1,
 
1
  {
2
+ "_name_or_path": "nvidia/segformer-b2-finetuned-ade-512-512",
3
  "architectures": [
4
  "SegformerForSemanticSegmentation"
5
  ],
6
  "attention_probs_dropout_prob": 0.0,
7
  "classifier_dropout_prob": 0.1,
8
+ "decoder_hidden_size": 768,
9
  "depths": [
10
+ 3,
11
+ 4,
12
+ 6,
13
+ 3
14
  ],
15
  "downsampling_rates": [
16
  1,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a00b1006ecd7aa0226dbbd0b6eb3006a298b330bff2973fd70dea9a50c76654a
3
- size 54737376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5994f1667a1ca9829b10f2ee9d3c5a3a3bde959452a860c864efef03f72bb42
3
+ size 109444016
runs/Jul26_10-45-38_4b7d3c846457/events.out.tfevents.1721990743.4b7d3c846457.24.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e1d1ab697570528ab900773150f85b0530e9b674763e2bce3dab6e477ebdc0
3
+ size 1953138
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:014ef312420b1169576ce79bbe89b1b146ec9733b31d366af30e809afd6b6c3e
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd1f817c4f44f774730bcfefda5b29f54e2022c0072a38f4b2953017f89c14f7
3
  size 5304