You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This Problem is based on a Image Data set consisting of different types of weeds, to detect them in crops and fields. I have used Deep Learning Model called CNN(Convolutional Neural Networks) with Dropout, Batch Normalization, ReduceLearning rate on plateau, Early stoppig rounds, and Transposd Convolutional Neural Networks.
Demonstrate how to do backpropagation using an example of BatchNorm-Sigmoid-MSELoss network with a detailed derivation of gradients and custom implementations.
Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning. TL;DR: Fine-tuning only the batch norm affine parameters leads to similar performance as to fine-tuning all of the model parameters
Demo on performing multiclass image classification using Convolutional Neural Network (CNN) in Tensorflow 2. Techniques such as earlystopping, batchnormalizing and dropout are explored to prevent overfitting
Batch normalization from scratch on LeNet using tensorflow.keras on mnist dataset. The goal is to learn and characterize batch normalization's impact on the NN performance.
Developed CNN model with 93% validation accuracy using techniques like Dropouts & Batch Normalization. Using haar cascade of Computer Vision It is then used to detect sunglasses on real time basis