Training in progress, epoch 1
Browse files- README.md +71 -71
- config.json +80 -80
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,71 +1,71 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: other
|
| 3 |
-
base_model: nvidia/mit-b3
|
| 4 |
-
tags:
|
| 5 |
-
- generated_from_trainer
|
| 6 |
-
model-index:
|
| 7 |
-
- name: segformer-roof
|
| 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 |
-
# segformer-roof
|
| 15 |
-
|
| 16 |
-
This model is a fine-tuned version of [nvidia/mit-b3](https://huggingface.co/nvidia/mit-b3) on the None dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.1331
|
| 19 |
-
- Mean Iou: 0.6705
|
| 20 |
-
- Mean Accuracy: 0.7459
|
| 21 |
-
- Overall Accuracy: 0.9509
|
| 22 |
-
- Per Category Iou: [0.9501174871140823, 0.44914356298751956, 0.612314004780354]
|
| 23 |
-
- Per Category Accuracy: [0.9835400780911927, 0.5547023488814158, 0.6996065789512536]
|
| 24 |
-
|
| 25 |
-
## Model description
|
| 26 |
-
|
| 27 |
-
More information needed
|
| 28 |
-
|
| 29 |
-
## Intended uses & limitations
|
| 30 |
-
|
| 31 |
-
More information needed
|
| 32 |
-
|
| 33 |
-
## Training and evaluation data
|
| 34 |
-
|
| 35 |
-
More information needed
|
| 36 |
-
|
| 37 |
-
## Training procedure
|
| 38 |
-
|
| 39 |
-
### Training hyperparameters
|
| 40 |
-
|
| 41 |
-
The following hyperparameters were used during training:
|
| 42 |
-
- learning_rate: 6e-05
|
| 43 |
-
- train_batch_size: 8
|
| 44 |
-
- eval_batch_size: 8
|
| 45 |
-
- seed: 42
|
| 46 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
-
- lr_scheduler_type: linear
|
| 48 |
-
- num_epochs: 10
|
| 49 |
-
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
|
| 53 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------------------------------------------------:|:-------------------------------------------------------------:|
|
| 54 |
-
| 0.2357 | 1.0 | 930 | 0.1790 | 0.5725 | 0.6427 | 0.9370 | [0.9372296551214157, 0.265369517396097, 0.5150004888948623] | [0.9831748407739025, 0.30066901406516805, 0.6442311056295564] |
|
| 55 |
-
| 0.1732 | 2.0 | 1860 | 0.1700 | 0.5944 | 0.6623 | 0.9398 | [0.9401268036898566, 0.32807672100401025, 0.5150202791005837] | [0.9839554901228429, 0.3979733503813561, 0.6048359409441622] |
|
| 56 |
-
| 0.1559 | 3.0 | 2790 | 0.1600 | 0.6127 | 0.6753 | 0.9429 | [0.9427325757540327, 0.35965960312996503, 0.5357965624353673] | [0.9857619070576414, 0.448355090982288, 0.5917792010373596] |
|
| 57 |
-
| 0.1482 | 4.0 | 3720 | 0.1550 | 0.6070 | 0.6703 | 0.9437 | [0.944172393520638, 0.32282759103373876, 0.553957021364391] | [0.9867471837507854, 0.3693595842127839, 0.6546589242888398] |
|
| 58 |
-
| 0.1388 | 5.0 | 4650 | 0.1459 | 0.6224 | 0.6804 | 0.9463 | [0.9459092954263936, 0.3388316205746287, 0.582315028654454] | [0.9880828845164424, 0.3845685735297591, 0.6686608983285444] |
|
| 59 |
-
| 0.1311 | 6.0 | 5580 | 0.1462 | 0.6577 | 0.7466 | 0.9468 | [0.9461722360255241, 0.43412167635821636, 0.5928671376046599] | [0.9789455448939886, 0.5812880374397429, 0.679673538106026] |
|
| 60 |
-
| 0.1279 | 7.0 | 6510 | 0.1423 | 0.6611 | 0.7569 | 0.9469 | [0.9465891089044499, 0.4381184809600582, 0.5986930952368954] | [0.9773687408863051, 0.6022321705637107, 0.6909579192751797] |
|
| 61 |
-
| 0.1232 | 8.0 | 7440 | 0.1388 | 0.6682 | 0.7548 | 0.9491 | [0.9484426711464405, 0.44975791193706466, 0.6064948465370358] | [0.9802070573066378, 0.5898759789294347, 0.6944388397098907] |
|
| 62 |
-
| 0.1175 | 9.0 | 8370 | 0.1353 | 0.6665 | 0.7392 | 0.9505 | [0.9497153698000098, 0.44248964964215, 0.6074386624389524] | [0.9841990715683068, 0.5444332218950657, 0.6888275633995394] |
|
| 63 |
-
| 0.1174 | 10.0 | 9300 | 0.1331 | 0.6705 | 0.7459 | 0.9509 | [0.9501174871140823, 0.44914356298751956, 0.612314004780354] | [0.9835400780911927, 0.5547023488814158, 0.6996065789512536] |
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
### Framework versions
|
| 67 |
-
|
| 68 |
-
- Transformers 4.33.1
|
| 69 |
-
- Pytorch 2.0.1
|
| 70 |
-
- Datasets 2.14.5
|
| 71 |
-
- Tokenizers 0.13.3
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: nvidia/mit-b3
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: segformer-roof
|
| 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 |
+
# segformer-roof
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [nvidia/mit-b3](https://huggingface.co/nvidia/mit-b3) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1331
|
| 19 |
+
- Mean Iou: 0.6705
|
| 20 |
+
- Mean Accuracy: 0.7459
|
| 21 |
+
- Overall Accuracy: 0.9509
|
| 22 |
+
- Per Category Iou: [0.9501174871140823, 0.44914356298751956, 0.612314004780354]
|
| 23 |
+
- Per Category Accuracy: [0.9835400780911927, 0.5547023488814158, 0.6996065789512536]
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 6e-05
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 10
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------------------------------------------------:|:-------------------------------------------------------------:|
|
| 54 |
+
| 0.2357 | 1.0 | 930 | 0.1790 | 0.5725 | 0.6427 | 0.9370 | [0.9372296551214157, 0.265369517396097, 0.5150004888948623] | [0.9831748407739025, 0.30066901406516805, 0.6442311056295564] |
|
| 55 |
+
| 0.1732 | 2.0 | 1860 | 0.1700 | 0.5944 | 0.6623 | 0.9398 | [0.9401268036898566, 0.32807672100401025, 0.5150202791005837] | [0.9839554901228429, 0.3979733503813561, 0.6048359409441622] |
|
| 56 |
+
| 0.1559 | 3.0 | 2790 | 0.1600 | 0.6127 | 0.6753 | 0.9429 | [0.9427325757540327, 0.35965960312996503, 0.5357965624353673] | [0.9857619070576414, 0.448355090982288, 0.5917792010373596] |
|
| 57 |
+
| 0.1482 | 4.0 | 3720 | 0.1550 | 0.6070 | 0.6703 | 0.9437 | [0.944172393520638, 0.32282759103373876, 0.553957021364391] | [0.9867471837507854, 0.3693595842127839, 0.6546589242888398] |
|
| 58 |
+
| 0.1388 | 5.0 | 4650 | 0.1459 | 0.6224 | 0.6804 | 0.9463 | [0.9459092954263936, 0.3388316205746287, 0.582315028654454] | [0.9880828845164424, 0.3845685735297591, 0.6686608983285444] |
|
| 59 |
+
| 0.1311 | 6.0 | 5580 | 0.1462 | 0.6577 | 0.7466 | 0.9468 | [0.9461722360255241, 0.43412167635821636, 0.5928671376046599] | [0.9789455448939886, 0.5812880374397429, 0.679673538106026] |
|
| 60 |
+
| 0.1279 | 7.0 | 6510 | 0.1423 | 0.6611 | 0.7569 | 0.9469 | [0.9465891089044499, 0.4381184809600582, 0.5986930952368954] | [0.9773687408863051, 0.6022321705637107, 0.6909579192751797] |
|
| 61 |
+
| 0.1232 | 8.0 | 7440 | 0.1388 | 0.6682 | 0.7548 | 0.9491 | [0.9484426711464405, 0.44975791193706466, 0.6064948465370358] | [0.9802070573066378, 0.5898759789294347, 0.6944388397098907] |
|
| 62 |
+
| 0.1175 | 9.0 | 8370 | 0.1353 | 0.6665 | 0.7392 | 0.9505 | [0.9497153698000098, 0.44248964964215, 0.6074386624389524] | [0.9841990715683068, 0.5444332218950657, 0.6888275633995394] |
|
| 63 |
+
| 0.1174 | 10.0 | 9300 | 0.1331 | 0.6705 | 0.7459 | 0.9509 | [0.9501174871140823, 0.44914356298751956, 0.612314004780354] | [0.9835400780911927, 0.5547023488814158, 0.6996065789512536] |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.33.1
|
| 69 |
+
- Pytorch 2.0.1
|
| 70 |
+
- Datasets 2.14.5
|
| 71 |
+
- Tokenizers 0.13.3
|
config.json
CHANGED
|
@@ -1,80 +1,80 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "nvidia/mit-b3",
|
| 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 |
-
18,
|
| 13 |
-
3
|
| 14 |
-
],
|
| 15 |
-
"downsampling_rates": [
|
| 16 |
-
1,
|
| 17 |
-
4,
|
| 18 |
-
8,
|
| 19 |
-
16
|
| 20 |
-
],
|
| 21 |
-
"drop_path_rate": 0.1,
|
| 22 |
-
"hidden_act": "gelu",
|
| 23 |
-
"hidden_dropout_prob": 0.0,
|
| 24 |
-
"hidden_sizes": [
|
| 25 |
-
64,
|
| 26 |
-
128,
|
| 27 |
-
320,
|
| 28 |
-
512
|
| 29 |
-
],
|
| 30 |
-
"id2label": {
|
| 31 |
-
"0": "\u0424\u043e\u043d",
|
| 32 |
-
"1": "\u0412\u0437\u0434\u0443\u0442\u0438\u0435",
|
| 33 |
-
"2": "\u0412\u043f\u0430\u0434\u0438\u043d\u0430"
|
| 34 |
-
},
|
| 35 |
-
"image_size": 224,
|
| 36 |
-
"initializer_range": 0.02,
|
| 37 |
-
"label2id": {
|
| 38 |
-
"\u0412\u0437\u0434\u0443\u0442\u0438\u0435": 1,
|
| 39 |
-
"\u0412\u043f\u0430\u0434\u0438\u043d\u0430": 2,
|
| 40 |
-
"\u0424\u043e\u043d": 0
|
| 41 |
-
},
|
| 42 |
-
"layer_norm_eps": 1e-06,
|
| 43 |
-
"mlp_ratios": [
|
| 44 |
-
4,
|
| 45 |
-
4,
|
| 46 |
-
4,
|
| 47 |
-
4
|
| 48 |
-
],
|
| 49 |
-
"model_type": "segformer",
|
| 50 |
-
"num_attention_heads": [
|
| 51 |
-
1,
|
| 52 |
-
2,
|
| 53 |
-
5,
|
| 54 |
-
8
|
| 55 |
-
],
|
| 56 |
-
"num_channels": 3,
|
| 57 |
-
"num_encoder_blocks": 4,
|
| 58 |
-
"patch_sizes": [
|
| 59 |
-
7,
|
| 60 |
-
3,
|
| 61 |
-
3,
|
| 62 |
-
3
|
| 63 |
-
],
|
| 64 |
-
"reshape_last_stage": true,
|
| 65 |
-
"semantic_loss_ignore_index": 255,
|
| 66 |
-
"sr_ratios": [
|
| 67 |
-
8,
|
| 68 |
-
4,
|
| 69 |
-
2,
|
| 70 |
-
1
|
| 71 |
-
],
|
| 72 |
-
"strides": [
|
| 73 |
-
4,
|
| 74 |
-
2,
|
| 75 |
-
2,
|
| 76 |
-
2
|
| 77 |
-
],
|
| 78 |
-
"torch_dtype": "float32",
|
| 79 |
-
"transformers_version": "4.33.1"
|
| 80 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b3",
|
| 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 |
+
18,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
"downsampling_rates": [
|
| 16 |
+
1,
|
| 17 |
+
4,
|
| 18 |
+
8,
|
| 19 |
+
16
|
| 20 |
+
],
|
| 21 |
+
"drop_path_rate": 0.1,
|
| 22 |
+
"hidden_act": "gelu",
|
| 23 |
+
"hidden_dropout_prob": 0.0,
|
| 24 |
+
"hidden_sizes": [
|
| 25 |
+
64,
|
| 26 |
+
128,
|
| 27 |
+
320,
|
| 28 |
+
512
|
| 29 |
+
],
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "\u0424\u043e\u043d",
|
| 32 |
+
"1": "\u0412\u0437\u0434\u0443\u0442\u0438\u0435",
|
| 33 |
+
"2": "\u0412\u043f\u0430\u0434\u0438\u043d\u0430"
|
| 34 |
+
},
|
| 35 |
+
"image_size": 224,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"\u0412\u0437\u0434\u0443\u0442\u0438\u0435": 1,
|
| 39 |
+
"\u0412\u043f\u0430\u0434\u0438\u043d\u0430": 2,
|
| 40 |
+
"\u0424\u043e\u043d": 0
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-06,
|
| 43 |
+
"mlp_ratios": [
|
| 44 |
+
4,
|
| 45 |
+
4,
|
| 46 |
+
4,
|
| 47 |
+
4
|
| 48 |
+
],
|
| 49 |
+
"model_type": "segformer",
|
| 50 |
+
"num_attention_heads": [
|
| 51 |
+
1,
|
| 52 |
+
2,
|
| 53 |
+
5,
|
| 54 |
+
8
|
| 55 |
+
],
|
| 56 |
+
"num_channels": 3,
|
| 57 |
+
"num_encoder_blocks": 4,
|
| 58 |
+
"patch_sizes": [
|
| 59 |
+
7,
|
| 60 |
+
3,
|
| 61 |
+
3,
|
| 62 |
+
3
|
| 63 |
+
],
|
| 64 |
+
"reshape_last_stage": true,
|
| 65 |
+
"semantic_loss_ignore_index": 255,
|
| 66 |
+
"sr_ratios": [
|
| 67 |
+
8,
|
| 68 |
+
4,
|
| 69 |
+
2,
|
| 70 |
+
1
|
| 71 |
+
],
|
| 72 |
+
"strides": [
|
| 73 |
+
4,
|
| 74 |
+
2,
|
| 75 |
+
2,
|
| 76 |
+
2
|
| 77 |
+
],
|
| 78 |
+
"torch_dtype": "float32",
|
| 79 |
+
"transformers_version": "4.33.1"
|
| 80 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 189128349
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ee1dd3761971f29f1979225d069ecb03578e88305f90a9badbbce8755db4522
|
| 3 |
size 189128349
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3963
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe746e79814b9e4085e1dedadf74f6a977385b495ed803e33fd9fe586614c064
|
| 3 |
size 3963
|