Use google colab ipnyb or jupyter notebook for each experiment on one model variant. Name the files as minivgg, var1, var2 and var3 and var4.Implement a mini-vgg network and several of its variants. Train and test the models on the cifar-10 dataset (https://www.cs.toronto.edu/~kriz/cifar.html ). Investigate and compare the performance of the variants to the original model. Write half to one page to 1) summarize your experiment results and discuss 2) the classification performance of the modelsas well as 3) their size (# of parameters) and 4) the computation time to train them.Mini-VGG network structure:Layer Type(window size) – n filters1 Conv3 – 642 Conv3 – 643 Maxpool – 2×24 Conv3 – 1285 Conv3 – 1286 Maxpool – 2×27 Conv3 – 2568 Conv3 – 2569 Maxpool – 2×210* fully Connected 51211** soft-max* Note your need a reshape layer before this layer to reshape the data** Use cross entropy loss (torch.nn.CrossEntropyLoss or tf.nn.softmax_cross_entropy_with_logits()) feedthe loss function with the logits before softmax activation but get the prediction for accuracy aftersoftmax activation)Report the performance of each network by doing the following:A) Plot training loss vs validation lossB) Plot training accuracy vs validation accuracyC) Calculate test accuracy1. Implement the mini-vgg model and report its performance. Use ReLU activation function for all the all conv/fc layers except the last one.2. Variant 1: Change the ReLU activation functions to SELU and Swish. Would the performance improve?3. Variant 2: Remove the maxpool layers. Using stride=2 in the conv layer before the maxpool to achieve similar size reduction. Would the performance improve?4. Variant 3: Add a few dropout layers in the model. Would the performance improve? Try 2 different ways to add the dropout layers. Describe the ones you tried and their performance.5. Variant 4: Remove layers 9 and 10. Add two layers of (1, 1) convolution: conv (1, 1) x 128; conv (1, 1) x10. Then add “GlobalAveragePooling2D” to merge feature maps before pass them to softmax. This is an all-convolutional structure (no fully connected layers).
MiniVGG network structure
User generated content is uploaded by users for the purposes of learning and should be used following Studypool’s honor code & terms of service.