commit files to HF hub

README.md

@@ -0,0 +1,33 @@
+
+---
+language: en
+license: mit
+tags:
+- VIT
+- image-classification
+- drowsiness-detection
+---
+
+# VIT_Drowsiness_2
+
+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 +1,55 @@
+{
+  "_name_or_path": "apple/mobilevit-small",
+  "architectures": [
+    "MobileViTForImageClassification"
+  ],
+  "aspp_dropout_prob": 0.1,
+  "aspp_out_channels": 256,
+  "atrous_rates": [
+    6,
+    12,
+    18
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "conv_kernel_size": 3,
+  "expand_ratio": 4.0,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_sizes": [
+    144,
+    192,
+    240
+  ],
+  "id2label": {
+    "0": "Drowsy",
+    "1": "Awake"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Awake": 1,
+    "Drowsy": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 2.0,
+  "model_type": "mobilevit",
+  "neck_hidden_sizes": [
+    16,
+    32,
+    64,
+    96,
+    128,
+    160,
+    640
+  ],
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "output_stride": 32,
+  "patch_size": 2,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c78572ec96fb6739be5233fefa6985a365e94e8e7c639c53eed4c45bba0541
+size 19851560

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "crop_size": {
+    "height": 256,
+    "width": 256
+  },
+  "do_center_crop": true,
+  "do_flip_channel_order": true,
+  "do_flip_channels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_processor_type": "MobileViTImageProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 288
+  }
+}