agrpdrlm commited on
Commit
64a90a9
1 Parent(s): a3f677e

vit_emotion_fine_tuned

Browse files
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/vit-base-patch16-224-in21k
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ - precision
12
+ - recall
13
+ - f1
14
+ model-index:
15
+ - name: vit-facial-expression
16
+ results:
17
+ - task:
18
+ name: Image Classification
19
+ type: image-classification
20
+ dataset:
21
+ name: imagefolder
22
+ type: imagefolder
23
+ config: default
24
+ split: train
25
+ args: default
26
+ metrics:
27
+ - name: Accuracy
28
+ type: accuracy
29
+ value: 0.7378253732509966
30
+ - name: Precision
31
+ type: precision
32
+ value: 0.7302570858866146
33
+ - name: Recall
34
+ type: recall
35
+ value: 0.7378253732509966
36
+ - name: F1
37
+ type: f1
38
+ value: 0.7274264799279716
39
+ ---
40
+
41
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
42
+ should probably proofread and complete it, then remove this comment. -->
43
+
44
+ # vit-facial-expression
45
+
46
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
47
+ It achieves the following results on the evaluation set:
48
+ - Loss: 0.8099
49
+ - Accuracy: 0.7378
50
+ - Precision: 0.7303
51
+ - Recall: 0.7378
52
+ - F1: 0.7274
53
+
54
+ ## Model description
55
+
56
+ More information needed
57
+
58
+ ## Intended uses & limitations
59
+
60
+ More information needed
61
+
62
+ ## Training and evaluation data
63
+
64
+ More information needed
65
+
66
+ ## Training procedure
67
+
68
+ ### Training hyperparameters
69
+
70
+ The following hyperparameters were used during training:
71
+ - learning_rate: 3e-05
72
+ - train_batch_size: 128
73
+ - eval_batch_size: 128
74
+ - seed: 42
75
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
76
+ - lr_scheduler_type: cosine
77
+ - lr_scheduler_warmup_steps: 500
78
+ - num_epochs: 3
79
+ - mixed_precision_training: Native AMP
80
+
81
+ ### Training results
82
+
83
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
84
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
85
+ | 2.0154 | 0.4831 | 100 | 1.8473 | 0.3168 | 0.3005 | 0.3168 | 0.1961 |
86
+ | 1.569 | 0.9662 | 200 | 1.3372 | 0.5767 | 0.5110 | 0.5767 | 0.4926 |
87
+ | 1.185 | 1.4493 | 300 | 1.1047 | 0.6474 | 0.5805 | 0.6474 | 0.5937 |
88
+ | 1.044 | 1.9324 | 400 | 0.9638 | 0.6896 | 0.6787 | 0.6896 | 0.6611 |
89
+ | 0.8813 | 2.4155 | 500 | 0.8928 | 0.7005 | 0.6822 | 0.7005 | 0.6646 |
90
+ | 0.7925 | 2.8986 | 600 | 0.8209 | 0.7301 | 0.7183 | 0.7301 | 0.7186 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.46.3
96
+ - Pytorch 2.5.1+cu121
97
+ - Datasets 3.2.0
98
+ - Tokenizers 0.20.3
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7"
20
+ },
21
+ "image_size": 224,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6,
32
+ "LABEL_7": 7
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "model_type": "vit",
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_hidden_layers": 12,
39
+ "patch_size": 16,
40
+ "problem_type": "single_label_classification",
41
+ "qkv_bias": true,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.46.3"
44
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c0d8631852d2fab1eed378fa6b9fec9919c03e4d540fcbe14d738a115cdfff
3
+ size 343242432
runs/Dec16_12-33-50_cedccf96d47c/events.out.tfevents.1734352449.cedccf96d47c.1160.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e84d24dee48ab941163f5c9102a2c96f39ad0386c97a6bc00cf7f3f4d480ad
3
+ size 5303
runs/Dec16_13-16-07_cedccf96d47c/events.out.tfevents.1734355001.cedccf96d47c.1160.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b1a512af7d88ee68096435d88c9522512a972505d5392831f705d619d450703
3
+ size 5287
runs/Dec16_13-18-34_cedccf96d47c/events.out.tfevents.1734355126.cedccf96d47c.1160.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c8d9b890ccea871479f5fdfefd2fdd8328eca0a67f6f39fa8fe31cd1ee7e466
3
+ size 5289
runs/Dec16_13-22-42_cedccf96d47c/events.out.tfevents.1734355366.cedccf96d47c.1160.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e6fa0ca90b1a8f69bc6f28742c13632ecef2c553adbf2067382101ffef36ef
3
+ size 5289
runs/Dec16_13-36-30_cedccf96d47c/events.out.tfevents.1734356197.cedccf96d47c.26489.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe156000db76fd5fc0ed8025f10e85ba3ae14a698e60e42d2bfefd784cbfd89
3
+ size 5302
runs/Dec16_13-40-47_cedccf96d47c/events.out.tfevents.1734356451.cedccf96d47c.26489.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a45fc76b75c2d16b1141e8ccda6bcf1e43cd6f0bb0300618c87d3180397db6f
3
+ size 7387
runs/Dec16_13-40-47_cedccf96d47c/events.out.tfevents.1734358817.cedccf96d47c.26489.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8142b66648f656ece2932a0065ee934d19e9c3d25bda3bdb27cd8f12eb448263
3
+ size 359
runs/Dec16_13-40-47_cedccf96d47c/events.out.tfevents.1734359556.cedccf96d47c.26489.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589c73a4bc436107edd80c538dea015ebe09a1fdaff6f413765cc473f07715bb
3
+ size 5343
runs/Dec16_14-35-03_cedccf96d47c/events.out.tfevents.1734359720.cedccf96d47c.26489.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70efc97bb5aad5ce11c744c52fa1f6ff6fcdf0a777ac5108f5e89ddc92d05d64
3
+ size 9731
runs/Dec16_14-35-03_cedccf96d47c/events.out.tfevents.1734362194.cedccf96d47c.26489.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a296a073084abb847101b4e77e1a662da51a2322642fd550164d7f2a8f559ce7
3
+ size 560
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e025d3f2b289c236ee32cf52084d292170c1784154d8dd840a82b27312b566b0
3
+ size 5304