We present the Deep-learning Transient Astronomical Object (Deep-TAO), a dataset of 1,249,079 annotated images from the Catalina Real-time Transient Survey, including 3,807 transient and 12,500 non-transient sequences. Deep-TAO has been curated to provide a clean, open-access, and user-friendly resource for benchmarking deep learning models. Deep-TAO covers transient classes such as blazars, active galactic nuclei, cataclysmic variables, supernovae, and events of indeterminate nature. The dataset is publicly available in FITS format, with Python routines and Jupyter notebooks for easy data manipulation. Using Deep-TAO, a baseline Convolutional Neural Network outperformed traditional random forest classifiers trained on light curves, demonstrating its potential for advancing transient classification.