Update README.md

README.md

@@ -4,7 +4,7 @@ base_model: google/vit-base-patch16-224-in21k
 tags:
 - generated_from_trainer
 datasets:
-- image_folder
+- FastJobs/Visual_Emotional_Analysis
 metrics:
 - accuracy
 - precision
@@ -16,8 +16,8 @@ model-index:
       name: Image Classification
       type: image-classification
     dataset:
-      name: image_folder
-      type: image_folder
+      name: FastJobs/Visual_Emotional_Analysis
+      type: FastJobs/Visual_Emotional_Analysis
       config: FastJobs--Visual_Emotional_Analysis
       split: train
       args: FastJobs--Visual_Emotional_Analysis
@@ -33,12 +33,13 @@ model-index:
       value: 0.6712765732314218
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Emotion Classification
 
-# emotion_classification
+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 [FastJobs/Visual_Emotional_Analysis](https://huggingface.co/datasets/FastJobs/Visual_Emotional_Analysis) dataset.
+
+In theory, the accuracy for a random guess on this dataset is 0.1429.
 
-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 image_folder dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0511
 - Accuracy: 0.6687
@@ -47,15 +48,26 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+The Vision Transformer base version trained on ImageNet-21K released by Google. 
+Further details can be found on their [repo](https://huggingface.co/google/vit-base-patch16-224-in21k).
 
-## Intended uses & limitations
+## Training and evaluation data
 
-More information needed
+### Data Split
 
-## Training and evaluation data
+Used a 4:1 ratio for training and development sets and a random seed of 42.
+Also used a seed of 42 for batching the data, completely unrelated lol.
+
+### Pre-processing Augmentation
+
+The main pre-processing phase for both training and evaluation includes:
+- Bilinear interpolation to resize the image to (224, 224, 3) because it uses ImageNet images to train the original model
+- Normalizing images using a mean and standard deviation of [0.5, 0.5, 0.5] just like the original model
 
-More information needed
+Other than the aforementioned pre-processing, the training set was augmented using:
+- Random horizontal & vertical flip
+- Color jitter
+- Random resized crop
 
 ## Training procedure