DeepTracker swMATH ID: 25889 Software Authors: Dongyu Liu; Weiwei Cui; Kai Jin; Yuxiao Guo; Huamin Qu Description: DeepTracker: Visualizing the Training Process of Convolutional Neural Networks. Deep convolutional neural networks (CNNs) have achieved remarkable success in various fields. However, training an excellent CNN is practically a trial-and-error process that consumes a tremendous amount of time and computer resources. To accelerate the training process and reduce the number of trials, experts need to understand what has occurred in the training process and why the resulting CNN behaves as such. However, current popular training platforms, such as TensorFlow, only provide very little and general information, such as training/validation errors, which is far from enough to serve this purpose. To bridge this gap and help domain experts with their training tasks in a practical environment, we propose a visual analytics system, DeepTracker, to facilitate the exploration of the rich dynamics of CNN training processes and to identify the unusual patterns that are hidden behind the huge amount of training log. Specifically,we combine a hierarchical index mechanism and a set of hierarchical small multiples to help experts explore the entire training log from different levels of detail. We also introduce a novel cube-style visualization to reveal the complex correlations among multiple types of heterogeneous training data including neuron weights, validation images, and training iterations. Three case studies are conducted to demonstrate how DeepTracker provides its users with valuable knowledge in an industry-level CNN training process, namely in our case, training ResNet-50 on the ImageNet dataset. We show that our method can be easily applied to other state-of-the-art ”very deep” CNN models. Homepage: https://arxiv.org/abs/1808.08531 Keywords: arXiv_publication; deep learning; training process; multiple time series; visual analytics; correlation analysis Related Software: DeepTrack Cited in: 1 Document Standard Articles 1 Publication describing the Software Year DeepTracker: Visualizing the Training Process of Convolutional Neural Networks Dongyu Liu; Weiwei Cui; Kai Jin; Yuxiao Guo; Huamin Qu 2018 Cited by 1 Author 1 Kwon, Junseok Cited in 1 Serial 1 Journal of Mathematical Imaging and Vision Cited in 1 Field 1 Information and communication theory, circuits (94-XX) Citations by Year