Modify the code below for the baseline CNN (TODO: #1) We are going to first construct the CNN model by filling out the correct dimensions of the CNN layers. Please choose the appropriate stride and padding to get the image sizes at the respective layers correct. The baseline CNN (TODO: #1) will have the following layers: conv1: 3x3 convolution to obtain 16 features of size 32x32 RELU activation pool: MaxPool2d layer with a kernel size=2, stride=2 and padding=0 to obtain 16 features of size 16x16 conv2: 3x3 convolution to obtain 32 features of size 16x16 RELU activation pool: MaxPool2d to obtain 32 features of size 8x8 conv3: 3x3 convolution to obtain 32 features of size 6x6 RELU activation linear1: Linear layer with 512 features in the output. Choose the input feature size carefully. You should reshape the RELU activation linear2: Linear layer with 128 features in the output. RELU activation linear 3: Linear layer with appropriate # features in the output. Choose the input feature size carefully. Code below: import torch.nn as nn import torch.nn.functional as F # define your CNN here, e.g. activation function: F.sigmoid or F.relu class Net(nn.Module): def init(self): super(Net, self).init() # YOUR CODE HERE def forward(self, x): # YOUR CODE HERE return x

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Modify the code below for the baseline CNN (TODO: #1)

We are going to first construct the CNN model by filling out the correct dimensions of the CNN layers. Please choose the appropriate stride and padding to get the image sizes at the respective layers correct. The baseline CNN (TODO: #1) will have the following layers:

conv1: 3x3 convolution to obtain 16 features of size 32x32
RELU activation
pool: MaxPool2d layer with a kernel size=2, stride=2 and padding=0 to obtain 16 features of size 16x16
conv2: 3x3 convolution to obtain 32 features of size 16x16
RELU activation
pool: MaxPool2d to obtain 32 features of size 8x8
conv3: 3x3 convolution to obtain 32 features of size 6x6
RELU activation
linear1: Linear layer with 512 features in the output. Choose the input feature size carefully. You should reshape the
RELU activation
linear2: Linear layer with 128 features in the output.
RELU activation
linear 3: Linear layer with appropriate # features in the output. Choose the input feature size carefully.

Code below:

import torch.nn as nn
import torch.nn.functional as F

# define your CNN here, e.g. activation function: F.sigmoid or F.relu

class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# YOUR CODE HERE

def forward(self, x):
# YOUR CODE HERE
return x

Expert Solution

Trending now

This is a popular solution!

Step by step

Solved in 3 steps with 1 images

SEE SOLUTION Check out a sample Q&A here

Knowledge Booster

Learn more about

Need a deep-dive on the concept behind this application? Look no further. Learn more about this topic, computer-science and related others by exploring similar questions and additional content below.

Similar questions