Difference between YOLO,ALEXNET,VGG-16,VGG-19 and MOBILE NET in terms of CNN layer and working Criteria in each layer involved in given pre-trained model.

YOLO, ALEXNET, VGG-16, VGG-19, and MOBILE NET are all pre-trained models used in computer vision tasks, specifically in object detection and classification. Each of these models has different architectures and working criteria. Let's break down the differences in terms of CNN layers and the working criteria involved in each layer.

1. YOLO (You Only Look Once):

   • YOLO is a real-time object detection model.
   • It uses a single CNN architecture to simultaneously predict bounding boxes and class probabilities.
   • The CNN layers in YOLO are responsible for extracting features from the input image.
   • The final layer of YOLO performs object detection by dividing the image into a grid and predicting bounding boxes and class probabilities for each grid cell.

2. ALEXNET:

   • ALEXNET was one of the first deep CNN architectures to achieve high accuracy on the ImageNet dataset.
   • It consists of five convolutional layers and three fully connected layers.
   • The CNN layers in ALEXNET perform feature extraction by applying convolutional filters to the input image.
   • The fully connected layers are responsible for classification.

3. VGG-16 and VGG-19:

   • VGG-16 and VGG-19 are deep CNN architectures with 16 and 19 layers, respectively.
   • Both models have a similar structure, consisting of multiple convolutional layers followed by fully connected layers.
   • The CNN layers in VGG models perform feature extraction by applying convolutional filters of various sizes to the input image.
   • The fully connected layers are responsible for classification.

4. MOBILE NET:

   • MOBILE NET is a lightweight CNN architecture designed for mobile and embedded devices.
   • It uses depthwise separable convolutions to reduce the number of parameters and computational complexity.
   • The CNN layers in MOBILE NET perform feature extraction using depthwise separable convolutions.
   • The final layers of MOBILE NET are responsible for classification.

In summary, YOLO is a real-time object detection model, ALEXNET and VGG models are primarily used for image classification, and MOBILE NET is a lightweight model suitable for mobile and embedded devices. The CNN layers in each model have different architectures and perform feature extraction, while the final layers are responsible for classification or object detection.