Alexnet Implementation in TensorFlow
- 0 Collaborators
Implemented Alexnet Neural Network for Image Classification in TensorFlow. AlexNet contains eight layers in total.The first five are convolutional layers and the last three are fully connected layers. AlexNet network can classify among 1000 different classes. ...learn more
Project status: Published/In Market
Overview / Usage
Alexnet is a Convolutional Neural Network used for Object Detection. Alexnet network is trained on 1000 classes and consists of convolution, pooling and batch norm layers.It uses ReLu activation function instead of tanh or sigmoid to add non linearity and it also increases its speed.
Methodology / Approach
The weights of a pre-trained Alexnet CNN were used to initialise the weights the local model to avoid training time.
Implemented convolution, pooling ,fully connected and batch norm layers in TensorFlow.
Technologies Used
Python
TensorFlow
Ipython