A Common CNN Architecture in Python
Convolutional Neural Networks are a powerful choice for problems and datsets involving images. However, they can grow to become so big, that training it on a normal system takes too long. So, the following template shows a particular network architecture that can be very effective for most problems, but is also small enough to be trained quickly. Some other related topics you might be interested in are Pooling Layers in Python, Tensorboard - Tracking Metrics in Python, Tensorboard - Confusion Metrics in Python, and Tensorboard - Tuning Hyperparameters in Python. The Common CNN Architecture in Python template is among the topics covered in detail in the 365 Program.
Who is it for
This free .ipynb template is designed for any data professional and deep learning enthusiast who want to learn how to use CNN for image analysis and recognition.
How it can help you
Convolutional Neural Network Architectures are a combination of pooling layers, convolutional layers and fully connected layers and is used for analyzing visual images.