frncscp commited on
Commit
d2cf2da
1 Parent(s): 593a4c9

End of training

Browse files
Files changed (4) hide show
  1. README.md +55 -0
  2. config.json +51 -0
  3. preprocessor_config.json +22 -0
  4. 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