End of training
Browse files- README.md +55 -0
- config.json +51 -0
- preprocessor_config.json +22 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: frncscp/pataconxt
|
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 |
+
# frncscp/pataconxt
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [facebook/convnext-large-224](https://huggingface.co/facebook/convnext-large-224) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.0423
|
18 |
+
- Validation Loss: 0.0341
|
19 |
+
- Train Accuracy: 0.9910
|
20 |
+
- Epoch: 1
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1748, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
40 |
+
- training_precision: float32
|
41 |
+
|
42 |
+
### Training results
|
43 |
+
|
44 |
+
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|
45 |
+
|:----------:|:---------------:|:--------------:|:-----:|
|
46 |
+
| 0.2163 | 0.0820 | 0.9887 | 0 |
|
47 |
+
| 0.0423 | 0.0341 | 0.9910 | 1 |
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.28.1
|
53 |
+
- TensorFlow 2.12.0
|
54 |
+
- Datasets 2.12.0
|
55 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/convnext-large-224",
|
3 |
+
"architectures": [
|
4 |
+
"ConvNextForImageClassification"
|
5 |
+
],
|
6 |
+
"depths": [
|
7 |
+
3,
|
8 |
+
3,
|
9 |
+
27,
|
10 |
+
3
|
11 |
+
],
|
12 |
+
"drop_path_rate": 0.0,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_sizes": [
|
15 |
+
192,
|
16 |
+
384,
|
17 |
+
768,
|
18 |
+
1536
|
19 |
+
],
|
20 |
+
"id2label": {
|
21 |
+
"0": "Patacon-False",
|
22 |
+
"1": "Patacon-True"
|
23 |
+
},
|
24 |
+
"image_size": 224,
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"label2id": {
|
27 |
+
"Patacon-False": "0",
|
28 |
+
"Patacon-True": "1"
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
+
"layer_scale_init_value": 1e-06,
|
32 |
+
"model_type": "convnext",
|
33 |
+
"num_channels": 3,
|
34 |
+
"num_stages": 4,
|
35 |
+
"out_features": [
|
36 |
+
"stage4"
|
37 |
+
],
|
38 |
+
"out_indices": [
|
39 |
+
4
|
40 |
+
],
|
41 |
+
"patch_size": 4,
|
42 |
+
"stage_names": [
|
43 |
+
"stem",
|
44 |
+
"stage1",
|
45 |
+
"stage2",
|
46 |
+
"stage3",
|
47 |
+
"stage4"
|
48 |
+
],
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.28.1"
|
51 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_pct": 0.875,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.485,
|
8 |
+
0.456,
|
9 |
+
0.406
|
10 |
+
],
|
11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.229,
|
14 |
+
0.224,
|
15 |
+
0.225
|
16 |
+
],
|
17 |
+
"resample": 3,
|
18 |
+
"rescale_factor": 0.00392156862745098,
|
19 |
+
"size": {
|
20 |
+
"shortest_edge": 224
|
21 |
+
}
|
22 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f049aa86067ebb544c9222ec6b2dfe74d1a7011370988554cee1b94a166e5fa3
|
3 |
+
size 785325136
|