End of training

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_keras_callback
+model-index:
+- name: NabeelShar/emotions_classifier
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# NabeelShar/emotions_classifier
+
+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.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.8852
+- Validation Loss: 1.7692
+- Train Accuracy: 0.425
+- Epoch: 19
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 12800, '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}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Accuracy | Epoch |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 1.9557     | 1.7012          | 0.2687         | 0     |
+| 1.8429     | 1.7698          | 0.2125         | 1     |
+| 1.8175     | 1.6158          | 0.2875         | 2     |
+| 1.6821     | 1.5730          | 0.3312         | 3     |
+| 1.5837     | 1.4980          | 0.3125         | 4     |
+| 1.5647     | 1.4806          | 0.375          | 5     |
+| 1.4481     | 1.4933          | 0.3438         | 6     |
+| 1.4185     | 1.4641          | 0.3688         | 7     |
+| 1.3848     | 1.4206          | 0.4188         | 8     |
+| 1.3315     | 1.4745          | 0.3625         | 9     |
+| 1.3214     | 1.3629          | 0.3875         | 10    |
+| 1.2092     | 1.3953          | 0.4375         | 11    |
+| 1.2342     | 1.3674          | 0.4313         | 12    |
+| 1.1648     | 1.3140          | 0.4375         | 13    |
+| 1.1258     | 1.4024          | 0.3812         | 14    |
+| 1.0459     | 1.5097          | 0.45           | 15    |
+| 1.0098     | 1.4080          | 0.4188         | 16    |
+| 0.9245     | 1.4329          | 0.4313         | 17    |
+| 0.8194     | 1.3921          | 0.4625         | 18    |
+| 0.8852     | 1.7692          | 0.425          | 19    |
+
+
+### Framework versions
+
+- Transformers 4.33.1
+- TensorFlow 2.13.0
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "contempt",
+    "2": "disgust",
+    "3": "fear",
+    "4": "happy",
+    "5": "neutral",
+    "6": "sad",
+    "7": "surprise"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": "0",
+    "contempt": "1",
+    "disgust": "2",
+    "fear": "3",
+    "happy": "4",
+    "neutral": "5",
+    "sad": "6",
+    "surprise": "7"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "transformers_version": "4.33.1"
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205e1cbff44905e647339d389f4ff966c8c92b14e9de7f805e67177dec25e605
+size 343488184