Upload folder using huggingface_hub
Browse files- README.md +60 -0
- config.json +50 -0
- preprocessor_config.json +22 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: google/vit-base-patch16-224-in21k
|
5 |
+
tags:
|
6 |
+
- generated_from_keras_callback
|
7 |
+
model-index:
|
8 |
+
- name: CodeMania/Vehicle_classifier
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
13 |
+
probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# CodeMania/Vehicle_classifier
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Train Loss: 0.4395
|
20 |
+
- Validation Loss: 0.5309
|
21 |
+
- Train Accuracy: 0.8601
|
22 |
+
- Epoch: 4
|
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 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 13595, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
42 |
+
- training_precision: float32
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
47 |
+
|:----------:|:---------------:|:--------------:|:-----:|
|
48 |
+
| 1.8665 | 1.3278 | 0.6654 | 0 |
|
49 |
+
| 1.1317 | 0.9559 | 0.7569 | 1 |
|
50 |
+
| 0.7964 | 0.7558 | 0.7908 | 2 |
|
51 |
+
| 0.5967 | 0.6633 | 0.8183 | 3 |
|
52 |
+
| 0.4395 | 0.5309 | 0.8601 | 4 |
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.44.2
|
58 |
+
- TensorFlow 2.17.0
|
59 |
+
- Datasets 3.0.0
|
60 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
3 |
+
"architectures": [
|
4 |
+
"ViTForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"encoder_stride": 16,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "auto-rickshaw",
|
13 |
+
"1": "bicycle",
|
14 |
+
"10": "truck",
|
15 |
+
"11": "van",
|
16 |
+
"2": "bus",
|
17 |
+
"3": "car",
|
18 |
+
"4": "e-rickshaw",
|
19 |
+
"5": "mini-bus",
|
20 |
+
"6": "mini-truck",
|
21 |
+
"7": "motorcycle",
|
22 |
+
"8": "rickshaw",
|
23 |
+
"9": "tractor"
|
24 |
+
},
|
25 |
+
"image_size": 224,
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"auto-rickshaw": "0",
|
30 |
+
"bicycle": "1",
|
31 |
+
"bus": "2",
|
32 |
+
"car": "3",
|
33 |
+
"e-rickshaw": "4",
|
34 |
+
"mini-bus": "5",
|
35 |
+
"mini-truck": "6",
|
36 |
+
"motorcycle": "7",
|
37 |
+
"rickshaw": "8",
|
38 |
+
"tractor": "9",
|
39 |
+
"truck": "10",
|
40 |
+
"van": "11"
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-12,
|
43 |
+
"model_type": "vit",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_channels": 3,
|
46 |
+
"num_hidden_layers": 12,
|
47 |
+
"patch_size": 16,
|
48 |
+
"qkv_bias": true,
|
49 |
+
"transformers_version": "4.44.2"
|
50 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a16241bf062ccd69f343d3d2e0da2394cedd4b371e6235393435636081c28a77
|
3 |
+
size 343516856
|