Deep Learning in Practice II: Transfer Learning Projects

Explore why transfer learning helps mitigate overfitting when training CNNs from scratch on a dataset of different vehicle types, by reusing well-designed networks from literature.

Apply transfer learning in practice using two ready-to-use notebooks for classification projects; adjust data paths and model, train in the first notebook, then automatically evaluate in the second.

Document experiment configurations in a training notebook, including dataset details (603 images, seven classes), batch size 64, learning rate, optimizer, categorical entropy, and transfer learning with Mobile Nedved V2.

Compare two transfer learning strategies by tuning all parameters versus freezing feature extraction layers, and analyze 2.4 million versus 173 thousand trainable parameters and their impact.

Evaluate the model using the validation dataset to obtain validation loss and accuracy, compare with training results, then test on the test dataset to assess generalization and potential overfitting.

Display the top five predictions and the classification report to measure per-class metrics such as precision, recall, and F1, identify sedan and SUV misclassifications, and guide data improvements.

Explain how convolutional networks handle large image inputs, reduce parameter count and memory usage, prevent overfitting, and enable effective feature extraction for classification.

Apply padding to convolution to preserve input size and enhance border contributions, using zero padding with pad=1 so a 6x6 input stays 6x6 in the feature map.

Explore strided convolutions and how increasing the stride reduces feature map size while focusing on different features, and learn the size formula (input + 2 - F)/S + 1, floor.

Learn how convolution uses filters, padding and stride to shape feature maps, extract hierarchical image features across layers, and feed them into a fully connected classifier in deep networks.

Illustrates a convolutional neural network on a 39x39x3 image using 3x3 filters, stride 1, producing 37x37x10 maps, a 5x5 stride-2 conv to 17x17x20, and a 7x7x40 output for classification.

Trace the evolution of computer vision classification models from traditional techniques to deep neural networks, highlighting key architectures from 2012 to recent breakthroughs and comparing state-of-the-art methods.

VGG-16 is a 16-layer convolutional network with a uniform conv-block architecture that grows filters from 64 to 512 while halving spatial dimensions and ending with three fully connected layers.

Explore how residual neural networks address vanishing and exploding gradients through identity shortcut connections, enabling deeper models like up to 152 layers while improving training and performance.