$ show yanshengjia/ml-road
The repository 'ml-road' is primarily a collection of educational resources for machine learning, deep learning, and agentic AI, including curated links to courses, books, and recent topics. It also contains two small demo applications: one for Chinese character recognition using a convolutional neural network with batch normalization (TensorFlow 1.x) and another for MNIST handwritten digit recognition using a softmax regression (TensorFlow 1.x). The applications are runnable as command-line tools but require specific data directory structures and are tightly coupled to global flags, limiting their reusability. The codebase shows signs of technical drift due to reliance on deprecated TensorFlow 1.x APIs.
The LLM identified 1 files worth highlighting for reuse:
The `DataIterator` class provides a reusable pattern for loading image data from a directory structure (where each subdirectory represents a class) and creating a TensorFlow 1.x input pipeline with optional data augmentation (flipping, brightness, contrast). It encapsulates the logic for enumerating image files, assigning labels based on directory names, and setting up TensorFlow operations for reading, decoding, resizing, and batching images. This component can be extracted and used in other image classification projects with minimal modification (e.g., replacing flag references with parameters).