Lexic0n commited on
Commit
4097c98
1 Parent(s): ebe9c80

Upload 10 files

Browse files
.gitattributes CHANGED
@@ -25,7 +25,6 @@
25
  *.safetensors filter=lfs diff=lfs merge=lfs -text
26
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
  *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
  *.tflite filter=lfs diff=lfs merge=lfs -text
30
  *.tgz filter=lfs diff=lfs merge=lfs -text
31
  *.wasm filter=lfs diff=lfs merge=lfs -text
 
25
  *.safetensors filter=lfs diff=lfs merge=lfs -text
26
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
  *.tar.* filter=lfs diff=lfs merge=lfs -text
 
28
  *.tflite filter=lfs diff=lfs merge=lfs -text
29
  *.tgz filter=lfs diff=lfs merge=lfs -text
30
  *.wasm filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - vision
5
+ - image-segmentation
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: segformer-b0-finetuned-human-parsing
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # segformer-b0-finetuned-human-parsing
16
+
17
+ This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.9476
20
+ - Mean Iou: 0.0726
21
+ - Mean Accuracy: 0.1221
22
+ - Overall Accuracy: 0.3575
23
+ - Accuracy Background: nan
24
+ - Accuracy Hat: 0.0048
25
+ - Accuracy Hair: 0.4813
26
+ - Accuracy Sunglasses: 0.0
27
+ - Accuracy Upper-clothes: 0.9405
28
+ - Accuracy Skirt: 0.0000
29
+ - Accuracy Pants: 0.0631
30
+ - Accuracy Dress: 0.1031
31
+ - Accuracy Belt: 0.0
32
+ - Accuracy Left-shoe: 0.0011
33
+ - Accuracy Right-shoe: 0.0010
34
+ - Accuracy Face: 0.4406
35
+ - Accuracy Left-leg: 0.0291
36
+ - Accuracy Right-leg: 0.0
37
+ - Accuracy Left-arm: 0.0
38
+ - Accuracy Right-arm: 0.0001
39
+ - Accuracy Bag: 0.0114
40
+ - Accuracy Scarf: 0.0
41
+ - Iou Background: 0.0
42
+ - Iou Hat: 0.0043
43
+ - Iou Hair: 0.4221
44
+ - Iou Sunglasses: 0.0
45
+ - Iou Upper-clothes: 0.3239
46
+ - Iou Skirt: 0.0000
47
+ - Iou Pants: 0.0559
48
+ - Iou Dress: 0.0728
49
+ - Iou Belt: 0.0
50
+ - Iou Left-shoe: 0.0011
51
+ - Iou Right-shoe: 0.0009
52
+ - Iou Face: 0.3872
53
+ - Iou Left-leg: 0.0271
54
+ - Iou Right-leg: 0.0
55
+ - Iou Left-arm: 0.0
56
+ - Iou Right-arm: 0.0001
57
+ - Iou Bag: 0.0106
58
+ - Iou Scarf: 0.0
59
+
60
+ ## Model description
61
+
62
+ More information needed
63
+
64
+ ## Intended uses & limitations
65
+
66
+ More information needed
67
+
68
+ ## Training and evaluation data
69
+
70
+ More information needed
71
+
72
+ ## Training procedure
73
+
74
+ ### Training hyperparameters
75
+
76
+ The following hyperparameters were used during training:
77
+ - learning_rate: 6e-05
78
+ - train_batch_size: 2
79
+ - eval_batch_size: 2
80
+ - seed: 42
81
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
82
+ - lr_scheduler_type: linear
83
+ - num_epochs: 2
84
+
85
+ ### Training results
86
+
87
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Hat | Accuracy Hair | Accuracy Sunglasses | Accuracy Upper-clothes | Accuracy Skirt | Accuracy Pants | Accuracy Dress | Accuracy Belt | Accuracy Left-shoe | Accuracy Right-shoe | Accuracy Face | Accuracy Left-leg | Accuracy Right-leg | Accuracy Left-arm | Accuracy Right-arm | Accuracy Bag | Accuracy Scarf | Iou Background | Iou Hat | Iou Hair | Iou Sunglasses | Iou Upper-clothes | Iou Skirt | Iou Pants | Iou Dress | Iou Belt | Iou Left-shoe | Iou Right-shoe | Iou Face | Iou Left-leg | Iou Right-leg | Iou Left-arm | Iou Right-arm | Iou Bag | Iou Scarf |
88
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:------------:|:-------------:|:-------------------:|:----------------------:|:--------------:|:--------------:|:--------------:|:-------------:|:------------------:|:-------------------:|:-------------:|:-----------------:|:------------------:|:-----------------:|:------------------:|:------------:|:--------------:|:--------------:|:-------:|:--------:|:--------------:|:-----------------:|:---------:|:---------:|:---------:|:--------:|:-------------:|:--------------:|:--------:|:------------:|:-------------:|:------------:|:-------------:|:-------:|:---------:|
89
+ | 2.5768 | 0.4 | 20 | 2.7812 | 0.0726 | 0.1332 | 0.2876 | nan | 0.0178 | 0.3204 | 0.0004 | 0.5548 | 0.0004 | 0.2555 | 0.2373 | 0.0 | 0.0103 | 0.0003 | 0.5637 | 0.0287 | 0.0302 | 0.0001 | 0.0008 | 0.2435 | 0.0 | 0.0 | 0.0166 | 0.2759 | 0.0001 | 0.2781 | 0.0004 | 0.1710 | 0.1295 | 0.0 | 0.0098 | 0.0003 | 0.3251 | 0.0260 | 0.0248 | 0.0001 | 0.0007 | 0.0491 | 0.0 |
90
+ | 2.2093 | 0.8 | 40 | 2.5166 | 0.0563 | 0.1052 | 0.3288 | nan | 0.0 | 0.1994 | 0.0 | 0.9447 | 0.0015 | 0.0435 | 0.1164 | 0.0 | 0.0008 | 0.0000 | 0.4655 | 0.0007 | 0.0003 | 0.0 | 0.0 | 0.0153 | 0.0 | 0.0 | 0.0 | 0.1946 | 0.0 | 0.3037 | 0.0015 | 0.0417 | 0.0842 | 0.0 | 0.0008 | 0.0000 | 0.3726 | 0.0007 | 0.0003 | 0.0 | 0.0 | 0.0124 | 0.0 |
91
+ | 1.8804 | 1.2 | 60 | 2.0209 | 0.0632 | 0.1110 | 0.3374 | nan | 0.0087 | 0.3724 | 0.0 | 0.9475 | 0.0014 | 0.0162 | 0.0528 | 0.0 | 0.0001 | 0.0008 | 0.4257 | 0.0561 | 0.0001 | 0.0 | 0.0 | 0.0055 | 0.0 | 0.0 | 0.0077 | 0.3472 | 0.0 | 0.3086 | 0.0014 | 0.0156 | 0.0403 | 0.0 | 0.0001 | 0.0008 | 0.3597 | 0.0515 | 0.0001 | 0.0 | 0.0 | 0.0052 | 0.0 |
92
+ | 1.8776 | 1.6 | 80 | 2.0016 | 0.0665 | 0.1154 | 0.3454 | nan | 0.0056 | 0.4172 | 0.0 | 0.9412 | 0.0000 | 0.0490 | 0.0697 | 0.0 | 0.0002 | 0.0006 | 0.4349 | 0.0329 | 0.0000 | 0.0 | 0.0000 | 0.0100 | 0.0 | 0.0 | 0.0048 | 0.3791 | 0.0 | 0.3138 | 0.0000 | 0.0438 | 0.0542 | 0.0 | 0.0002 | 0.0006 | 0.3608 | 0.0304 | 0.0000 | 0.0 | 0.0000 | 0.0093 | 0.0 |
93
+ | 1.8471 | 2.0 | 100 | 1.9476 | 0.0726 | 0.1221 | 0.3575 | nan | 0.0048 | 0.4813 | 0.0 | 0.9405 | 0.0000 | 0.0631 | 0.1031 | 0.0 | 0.0011 | 0.0010 | 0.4406 | 0.0291 | 0.0 | 0.0 | 0.0001 | 0.0114 | 0.0 | 0.0 | 0.0043 | 0.4221 | 0.0 | 0.3239 | 0.0000 | 0.0559 | 0.0728 | 0.0 | 0.0011 | 0.0009 | 0.3872 | 0.0271 | 0.0 | 0.0 | 0.0001 | 0.0106 | 0.0 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.28.1
99
+ - Pytorch 2.0.0+cu118
100
+ - Datasets 2.12.0
101
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nvidia/mit-b0",
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,
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
+ 32,
26
+ 64,
27
+ 160,
28
+ 256
29
+ ],
30
+ "id2label": {
31
+ "0": "Background",
32
+ "1": "Hat",
33
+ "2": "Hair",
34
+ "3": "Sunglasses",
35
+ "4": "Upper-clothes",
36
+ "5": "Skirt",
37
+ "6": "Pants",
38
+ "7": "Dress",
39
+ "8": "Belt",
40
+ "9": "Left-shoe",
41
+ "10": "Right-shoe",
42
+ "11": "Face",
43
+ "12": "Left-leg",
44
+ "13": "Right-leg",
45
+ "14": "Left-arm",
46
+ "15": "Right-arm",
47
+ "16": "Bag",
48
+ "17": "Scarf"
49
+ },
50
+ "image_size": 224,
51
+ "initializer_range": 0.02,
52
+ "label2id": {
53
+ "Background": 0,
54
+ "Bag": 16,
55
+ "Belt": 8,
56
+ "Dress": 7,
57
+ "Face": 11,
58
+ "Hair": 2,
59
+ "Hat": 1,
60
+ "Left-arm": 14,
61
+ "Left-leg": 12,
62
+ "Left-shoe": 9,
63
+ "Pants": 6,
64
+ "Right-arm": 15,
65
+ "Right-leg": 13,
66
+ "Right-shoe": 10,
67
+ "Scarf": 17,
68
+ "Skirt": 5,
69
+ "Sunglasses": 3,
70
+ "Upper-clothes": 4
71
+ },
72
+ "layer_norm_eps": 1e-06,
73
+ "mlp_ratios": [
74
+ 4,
75
+ 4,
76
+ 4,
77
+ 4
78
+ ],
79
+ "model_type": "segformer",
80
+ "num_attention_heads": [
81
+ 1,
82
+ 2,
83
+ 5,
84
+ 8
85
+ ],
86
+ "num_channels": 3,
87
+ "num_encoder_blocks": 4,
88
+ "patch_sizes": [
89
+ 7,
90
+ 3,
91
+ 3,
92
+ 3
93
+ ],
94
+ "reshape_last_stage": true,
95
+ "semantic_loss_ignore_index": 255,
96
+ "sr_ratios": [
97
+ 8,
98
+ 4,
99
+ 2,
100
+ 1
101
+ ],
102
+ "strides": [
103
+ 4,
104
+ 2,
105
+ 2,
106
+ 2
107
+ ],
108
+ "torch_dtype": "float32",
109
+ "transformers_version": "4.28.1"
110
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0e1988d796792fb04fe61e4b834ed702a7d288517107bb4b83b7f432f331c9
3
+ size 14901232
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_reduce_labels": false,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "SegformerFeatureExtractor",
7
+ "image_mean": [
8
+ 0.485,
9
+ 0.456,
10
+ 0.406
11
+ ],
12
+ "image_processor_type": "SegformerImageProcessor",
13
+ "image_std": [
14
+ 0.229,
15
+ 0.224,
16
+ 0.225
17
+ ],
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9944fe18ba3f4304a155f46bc1270ebb9e97d4e747c7cb5a7a2cbd8fbf223ffe
3
+ size 14948237
runs/May02_17-23-28_abfa69157e8e/1683048260.7719638/events.out.tfevents.1683048260.abfa69157e8e.609.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c302d6aa2d2a3cf7f1028d0bafced59cb9560bd47f1b23c6853380645a397364
3
+ size 5988
runs/May02_17-23-28_abfa69157e8e/events.out.tfevents.1683048260.abfa69157e8e.609.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d77b2201147bec8415ae17eea919d71204adf06cb81700c702add9c7afdf21
3
+ size 33230
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb5f2102b672e1098e894108bf8ea111d779b135f056af3bdbb03483070eb769
3
+ size 3643