priya-sundaram-dev
f0ab75d0d2
Per discussion in #15418, these four files are not algorithms (they are how-to-use scripts wrapping a deep-learning framework) and dragged in the heavy keras/tensorflow dependency stack: - computer_vision/cnn_classification.py - dynamic_programming/k_means_clustering_tensorflow.py - machine_learning/lstm/lstm_prediction.py - neural_network/input_data.py (TF MNIST data loader; nothing imports it) Also removes the now-orphaned machine_learning/lstm/ package (only __init__.py + sample_data.csv, which served lstm_prediction.py). Cleanups: - Drop keras from pyproject.toml dependencies; regenerate uv.lock (removes absl-py, h5py, keras, ml-dtypes, namex, optree). - Remove the pre-release libhdf5-dev install step from build.yml and sphinx.yml (it existed only because keras needs hdf5). - Drop the four stale pytest --ignore entries in build.yml. - Remove the four DIRECTORY.md entries and the empty Lstm heading.
Computer Vision
Computer vision is an interdisciplinary field focused on enabling computers to gain high-level understanding from images and video—automatically extracting, analyzing, and interpreting visual information to produce outputs such as labels, measurements, 3D structure, or decisions.
In practice, computer vision methods combine geometry, physics, statistics, and machine learning to connect pixel data to semantic concepts like objects, actions, and scenes.
Image processing vs. computer vision
Image processing primarily transforms images (e.g., denoising, contrast enhancement, geometric warping) where the output is another image.
Computer vision uses images/video as input but often outputs information about the scene (e.g., detections, segmentation masks, pose estimates, tracking results, or a decision), which may then drive downstream behavior in a larger system.