NOTE: Each image in the dataset has size 28x28, so the data has size 28x28x32 (since batch_size is 32); kernelsize = 3 in the convolutional layer, and default stride = 1. To calculate output size of the convolution layer we use this formula: convolutionOutputSize = 1+ (inputSize - kernelSize)/stride = 1+ (28 - kernelSize)/stride The final output of the convolution layer, and therefore the input to the 1st linear layer will then have the following size: convolutionOutputSize x convolutionOutputSize x 32 2 Linear layers. The last linear layer is already defined. For the forward propogation function use F.relu as the activation function for the convolution layer and the first linear layer. The last linear layer and the activation function for it (softmax) are already written. CODE: class MyModel(nn.Module): definit(self): super(MyModel, self).init() # DEFINE CONVOLUTION LAYER HERE, CALL IT self.conv1 * #self.conv1 = complete this line # DEFINE LINEAR LAYER 1 HERE, CALL IT self.d1 * #self.d1 = complete this line self.d2 = nn.Linear(128,10) defforward(self, x): ## * WRITE CONVOLUTION LAYER HERE * x = x.flatten(start_dim = 1) # we use a flatten between the convolution and linear layers ## * WRITE FIRST LINEAR LAYER HERE * logits = self.d2(x) #10 class score out = F.softmax(logits, dim=1) return out

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

Related questions

Question

100%

NOTE: Each image in the dataset has size 28x28, so the data has size 28x28x32 (since batch_size is 32); kernelsize = 3 in the convolutional layer, and default stride = 1. To calculate output size of the convolution layer we use this formula:

convolutionOutputSize = 1+ (inputSize - kernelSize)/stride = 1+ (28 - kernelSize)/stride

The final output of the convolution layer, and therefore the input to the 1st linear layer will then have the following size: convolutionOutputSize x convolutionOutputSize x 32

2 Linear layers. The last linear layer is already defined.
For the forward propogation function use F.relu as the activation function for the convolution layer and the first linear layer. The last linear layer and the activation function for it (softmax) are already written.

CODE:

class MyModel(nn.Module):

def__init__(self):

super(MyModel, self).__init__()

# DEFINE CONVOLUTION LAYER HERE, CALL IT self.conv1 ***

#self.conv1 = **complete this line**

# DEFINE LINEAR LAYER 1 HERE, CALL IT self.d1 ***

#self.d1 = **complete this line**

self.d2 = nn.Linear(128,10)

defforward(self, x):

## *** WRITE CONVOLUTION LAYER HERE ***

x = x.flatten(start_dim = 1) # we use a flatten between the convolution and linear layers

## *** WRITE FIRST LINEAR LAYER HERE ***

logits = self.d2(x) #10 class score

out = F.softmax(logits, dim=1)

return out

Expert Solution

Step by step

Solved in 4 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