Data Structure
Networking
RDBMS
Operating System
Java
MS Excel
iOS
HTML
CSS
Android
Python
C Programming
C++
C#
MongoDB
MySQL
Javascript
PHP
We apply the BCELoss() method to compute the binary cross entropy loss between the input and target (predicted and actual) probabilities. BCELoss() is accessed from the torch.nn module. It creates a criterion that measures the binary cross entropy loss. It is a type of loss function provided by the torch.nn module.The loss functions are used to optimize a deep neural network by minimizing the loss. Both the input and target should be torch tensors having the class probabilities. Make sure that the target is between 0 and 1. Both the input and target tensors may have any number of dimensions. ... Read More
Making some of the random elements of an input tensor zero has been proven to be an effective technique for regularization during the training of a neural network. To achieve this task, we can apply torch.nn.Dropout(). It zeroes some of the elements of the input tensor.An element will be zeroed with the given probability p. It uses a Bernoulli distribution to take samples of the element being zeroed. It does not support complex-valued inputs.Syntaxtorch.nn.Dropout(p=0.5)The default probability of an element to zeroed is set to 0.5StepsWe could use the following steps to randomly zero some of the elements of an input ... Read More
We can rescale an n-dimensional input Tensor such that the elements lie within the range [0, 1] and sum to 1. To do this, we can apply the Softmax() function. We can rescale the n-dimensional input tensor along a particular dimension. The size of the output tensor is the same as the input tensor.Syntaxtorch.nn.Softmax(dim)Parametersdim – The dimension along which the Softmax is computed.StepsWe could use the following steps to crop an image at random location with given size −Import the required library. In all the following examples, the required Python library is torch. Make sure you have already installed it.import ... Read More
To apply a rectified linear unit (ReLU) function element-wise on an input tensor, we use torch.nn.ReLU(). It replaces all the negative elements in the input tensor with 0 (zero), and all the non-negative elements are left unchanged. It supports only real-valued input tensors. ReLU is used as an activation function in neural networks.Syntaxrelu = torch.nn.ReLU() output = relu(input)StepsYou could use the following steps to apply rectified linear unit (ReLU) function element-wise −Import the required library. In all the following examples, the required Python library is torch. Make sure you have already installed it.import torch import torch.nn as nnDefine input tensor ... Read More
We can apply a 2D Average Pooling over an input image composed of several input planes using the torch.nn.AvgPool2d() module. The input to a 2D Average Pooling layer must be of size [N, C, H, W] where N is the batch size, C is the number of channels, H and W are the height and width of the input image.The main feature of an Average Pooling operation is the filter or kernel size and stride. This module supports TensorFloat32.Syntaxtorch.nn.AvgPool2d(kernel_size)Parameterskernel_size – The size of the window to take an average over.Along with this parameter, there are some optional parameters also such ... Read More
In this problem, we are given two values n and a prime number p. Our task is to find Square Root under Modulo p (When p is in form of 4*i + 3). Here, p is of the form (4*i + 3) i.e. p % 4 = 3 for i > 1 and p being a prime number.Here are some numbers, 7, 11, 19, 23, 31...Let's take an example to understand the problem, Input : n = 3, p = 7 Output :Solution ApproachA simple solution to the problem is using a loop. We will loop from 2 to (p ... Read More
The torch.nn.ConstantPad2D() pads the input tensor boundaries with constant value. The size of the input tensor must be in 3D or 4D in (C, H, W) or (N, C, H, W) format respectively. Where N, C, H, W represents the mini batch size, number of channels, height and width respectively. The padding is done along the height and width of the input tensor.It takes the size of padding (padding) and constant values (value) as the parameters. The size of padding may be an integer or a tuple. The padding may be the same for all boundaries or different for each ... Read More
The torch.nn.ZeroPad2D() pads the input tensor boundaries with zeros. It takes the size of padding (padding) as a parameter. The size of padding may be an integer or a tuple. The padding may be the same for all boundaries or different for each boundary.The padding may be an integer or a tuple in (left, right, top, bottom) format. If it is an integer, then the padding along all the boundaries are the same. The height of the padded tensor is increased by top+bottom, whereas the width of the padded tensor is increased by left+right. It does not change the channel ... Read More
We can apply a 2D Max Pooling over an input image composed of several input planes using the torch.nn.MaxPool2d() module. The input to a 2D Max Pool layer must be of size [N, C, H, W] where N is the batch size, C is the number of channels, H and W are the height and width of the input image, respectively.The main feature of a Max Pool operation is the filter or kernel size and stride. This module supports TensorFloat32.Syntaxtorch.nn.MaxPool2d(kernel_size)Parameterskernel_size – The size of the window to take a max over.Along with this parameter, there are some optional parameters also ... Read More
We can apply a 2D transposed convolution operation over an input image composed of several input planes using the torch.nn.ConvTranspose2d() module. This module can be seen as the gradient of Conv2d with respect to its input.The input to a 2D transpose convolution layer must be of size [N, C, H, W] where N is the batch size, C is the number of channels, H and W are the height and width of the input image, respectively.Generally a 2D transposed convolution operation is applied on the image tensors. For a RGB image, the number of channels is 3. The main feature ... Read More