commit files to HF hub

README.md

@@ -0,0 +1,33 @@
+
+---
+language: en
+license: mit
+tags:
+- VIT
+- image-classification
+- drowsiness-detection
+---
+
+# VIT_Drowsiness
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) for drowsiness detection.
+
+## Model description
+
+This model is a Vision Transformer (ViT) fine-tuned for drowsiness detection. It classifies images into two categories: drowsy and not drowsy.
+
+## Intended uses & limitations
+
+This model is intended for drowsiness detection in images. It should be used on facial images similar to those in the training dataset.
+
+## Training data
+
+The model was trained on a custom dataset located at /kaggle/input/nthuddd2/train_data. The dataset was split into 70% training, 15% validation, and 15% test sets.
+
+## Training procedure
+
+The model was trained for 10 epochs using the Lion optimizer with a learning rate of 0.0001 and weight decay of 0.01. A cosine learning rate scheduler with 0.1 warmup ratio was used.
+
+## Evaluation results
+
+[Add your evaluation results here after training]

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Drowsy",
+    "1": "Awake"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Awake": 1,
+    "Drowsy": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b5110ce4073645d4612e43efd3f1a758998e1f3a278e1356e1f25d70df5292a
+size 343223968

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
+  }
+}