Training in progress epoch 0
Browse files- README.md +78 -0
- config.json +144 -0
- preprocessor_config.json +18 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: nateraw/mit-b0-finetuned-sidewalks-v2
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# nateraw/mit-b0-finetuned-sidewalks-v2
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 1.4089
|
18 |
+
- Validation Loss: 0.8220
|
19 |
+
- Validation Mean Iou: 0.1975
|
20 |
+
- Validation Mean Accuracy: 0.2427
|
21 |
+
- Validation Overall Accuracy: 0.7701
|
22 |
+
- Validation Per Category Iou: [0. 0.58353931 0.7655921 0.04209491 0.53135026 0.11779776
|
23 |
+
nan 0.07709853 0.15950712 0. 0.69634813 0.
|
24 |
+
0. 0. 0. 0. 0. 0.
|
25 |
+
0.61456822 0. 0.24971248 0.27129675 0. nan
|
26 |
+
0. 0.07697324 0. 0. 0.78576516 0.61267064
|
27 |
+
0.84564576 0. 0. 0.08904216 0. ]
|
28 |
+
- Validation Per Category Accuracy: [0. 0.88026971 0.93475302 0.04216372 0.5484085 0.13285614
|
29 |
+
nan 0.08669707 0.19044773 0. 0.90089024 0.
|
30 |
+
0. 0. 0. 0. 0. 0.
|
31 |
+
0.76783975 0. 0.42102101 0.28659817 0. nan
|
32 |
+
0. 0.08671771 0. 0. 0.89590301 0.74932576
|
33 |
+
0.9434814 0. 0. 0.14245566 0. ]
|
34 |
+
- Epoch: 0
|
35 |
+
|
36 |
+
## Model description
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Intended uses & limitations
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training and evaluation data
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training procedure
|
49 |
+
|
50 |
+
### Training hyperparameters
|
51 |
+
|
52 |
+
The following hyperparameters were used during training:
|
53 |
+
- optimizer: {'name': 'Adam', 'learning_rate': 6e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
54 |
+
- training_precision: float32
|
55 |
+
|
56 |
+
### Training results
|
57 |
+
|
58 |
+
| Train Loss | Validation Loss | Validation Mean Iou | Validation Mean Accuracy | Validation Overall Accuracy | Validation Per Category Iou | Validation Per Category Accuracy | Epoch |
|
59 |
+
|:----------:|:---------------:|:-------------------:|:------------------------:|:---------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-----:|
|
60 |
+
| 1.4089 | 0.8220 | 0.1975 | 0.2427 | 0.7701 | [0. 0.58353931 0.7655921 0.04209491 0.53135026 0.11779776
|
61 |
+
nan 0.07709853 0.15950712 0. 0.69634813 0.
|
62 |
+
0. 0. 0. 0. 0. 0.
|
63 |
+
0.61456822 0. 0.24971248 0.27129675 0. nan
|
64 |
+
0. 0.07697324 0. 0. 0.78576516 0.61267064
|
65 |
+
0.84564576 0. 0. 0.08904216 0. ] | [0. 0.88026971 0.93475302 0.04216372 0.5484085 0.13285614
|
66 |
+
nan 0.08669707 0.19044773 0. 0.90089024 0.
|
67 |
+
0. 0. 0. 0. 0. 0.
|
68 |
+
0.76783975 0. 0.42102101 0.28659817 0. nan
|
69 |
+
0. 0.08671771 0. 0. 0.89590301 0.74932576
|
70 |
+
0.9434814 0. 0. 0.14245566 0. ] | 0 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- Transformers 4.24.0
|
76 |
+
- TensorFlow 2.9.2
|
77 |
+
- Datasets 2.7.0
|
78 |
+
- Tokenizers 0.13.2
|
config.json
ADDED
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "unlabeled",
|
32 |
+
"1": "flat-road",
|
33 |
+
"2": "flat-sidewalk",
|
34 |
+
"3": "flat-crosswalk",
|
35 |
+
"4": "flat-cyclinglane",
|
36 |
+
"5": "flat-parkingdriveway",
|
37 |
+
"6": "flat-railtrack",
|
38 |
+
"7": "flat-curb",
|
39 |
+
"8": "human-person",
|
40 |
+
"9": "human-rider",
|
41 |
+
"10": "vehicle-car",
|
42 |
+
"11": "vehicle-truck",
|
43 |
+
"12": "vehicle-bus",
|
44 |
+
"13": "vehicle-tramtrain",
|
45 |
+
"14": "vehicle-motorcycle",
|
46 |
+
"15": "vehicle-bicycle",
|
47 |
+
"16": "vehicle-caravan",
|
48 |
+
"17": "vehicle-cartrailer",
|
49 |
+
"18": "construction-building",
|
50 |
+
"19": "construction-door",
|
51 |
+
"20": "construction-wall",
|
52 |
+
"21": "construction-fenceguardrail",
|
53 |
+
"22": "construction-bridge",
|
54 |
+
"23": "construction-tunnel",
|
55 |
+
"24": "construction-stairs",
|
56 |
+
"25": "object-pole",
|
57 |
+
"26": "object-trafficsign",
|
58 |
+
"27": "object-trafficlight",
|
59 |
+
"28": "nature-vegetation",
|
60 |
+
"29": "nature-terrain",
|
61 |
+
"30": "sky",
|
62 |
+
"31": "void-ground",
|
63 |
+
"32": "void-dynamic",
|
64 |
+
"33": "void-static",
|
65 |
+
"34": "void-unclear"
|
66 |
+
},
|
67 |
+
"image_size": 224,
|
68 |
+
"initializer_range": 0.02,
|
69 |
+
"label2id": {
|
70 |
+
"construction-bridge": 22,
|
71 |
+
"construction-building": 18,
|
72 |
+
"construction-door": 19,
|
73 |
+
"construction-fenceguardrail": 21,
|
74 |
+
"construction-stairs": 24,
|
75 |
+
"construction-tunnel": 23,
|
76 |
+
"construction-wall": 20,
|
77 |
+
"flat-crosswalk": 3,
|
78 |
+
"flat-curb": 7,
|
79 |
+
"flat-cyclinglane": 4,
|
80 |
+
"flat-parkingdriveway": 5,
|
81 |
+
"flat-railtrack": 6,
|
82 |
+
"flat-road": 1,
|
83 |
+
"flat-sidewalk": 2,
|
84 |
+
"human-person": 8,
|
85 |
+
"human-rider": 9,
|
86 |
+
"nature-terrain": 29,
|
87 |
+
"nature-vegetation": 28,
|
88 |
+
"object-pole": 25,
|
89 |
+
"object-trafficlight": 27,
|
90 |
+
"object-trafficsign": 26,
|
91 |
+
"sky": 30,
|
92 |
+
"unlabeled": 0,
|
93 |
+
"vehicle-bicycle": 15,
|
94 |
+
"vehicle-bus": 12,
|
95 |
+
"vehicle-car": 10,
|
96 |
+
"vehicle-caravan": 16,
|
97 |
+
"vehicle-cartrailer": 17,
|
98 |
+
"vehicle-motorcycle": 14,
|
99 |
+
"vehicle-tramtrain": 13,
|
100 |
+
"vehicle-truck": 11,
|
101 |
+
"void-dynamic": 32,
|
102 |
+
"void-ground": 31,
|
103 |
+
"void-static": 33,
|
104 |
+
"void-unclear": 34
|
105 |
+
},
|
106 |
+
"layer_norm_eps": 1e-06,
|
107 |
+
"mlp_ratios": [
|
108 |
+
4,
|
109 |
+
4,
|
110 |
+
4,
|
111 |
+
4
|
112 |
+
],
|
113 |
+
"model_type": "segformer",
|
114 |
+
"num_attention_heads": [
|
115 |
+
1,
|
116 |
+
2,
|
117 |
+
5,
|
118 |
+
8
|
119 |
+
],
|
120 |
+
"num_channels": 3,
|
121 |
+
"num_encoder_blocks": 4,
|
122 |
+
"patch_sizes": [
|
123 |
+
7,
|
124 |
+
3,
|
125 |
+
3,
|
126 |
+
3
|
127 |
+
],
|
128 |
+
"reshape_last_stage": true,
|
129 |
+
"semantic_loss_ignore_index": 255,
|
130 |
+
"sr_ratios": [
|
131 |
+
8,
|
132 |
+
4,
|
133 |
+
2,
|
134 |
+
1
|
135 |
+
],
|
136 |
+
"strides": [
|
137 |
+
4,
|
138 |
+
2,
|
139 |
+
2,
|
140 |
+
2
|
141 |
+
],
|
142 |
+
"torch_dtype": "float32",
|
143 |
+
"transformers_version": "4.24.0"
|
144 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_resize": true,
|
4 |
+
"feature_extractor_type": "SegformerFeatureExtractor",
|
5 |
+
"image_mean": [
|
6 |
+
0.485,
|
7 |
+
0.456,
|
8 |
+
0.406
|
9 |
+
],
|
10 |
+
"image_std": [
|
11 |
+
0.229,
|
12 |
+
0.224,
|
13 |
+
0.225
|
14 |
+
],
|
15 |
+
"reduce_labels": false,
|
16 |
+
"resample": 2,
|
17 |
+
"size": 512
|
18 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b9a22e666e272a5bbacc00e76192c77981d2cd2331ed7c78c9ff5784be56b5a
|
3 |
+
size 15167588
|