Carefully read the source code vgg16_modified_pytorch.py . Note that this is not the standardVGG16 network, so please carefully read the source code. Answer the followingquestions:Assuming the input image size is 448 by 448,a. What is the size of the feature map before the self.fc6 layer, and how many channels doesit have?b. A key parameter has been erased. What number should replace the question mark inthe following line? Note: Assuming the input image size is 448 X 448

Consider a convolutional neural network model that has three convolution layers. The first layer has 50 filters, the second layer has 100 filters, and the third layer has 200 filters. All convolution layers have stride=2, and the same padding. The input images are 300x400 pixels with RGB channels.What is the feature map size after the third convolution layer?4 points150x200x5075x100x10038x50x200

If a convolutional layer has an input size of 28x28 and applies a filter of size 3x3 with a stride of 1 and no padding, what is the size of the output feature map?

In YOLO grid size is 17x17, the number of anchor boxes are 5 and able to detect 80 classes .What will be the size of the output layer.*1 point2427632946476852250

Question 1How many colour channels does a Grayscale image have ?1 point1234

VGG-16’s feature extraction part