Benchmark TensorFlow GitHub
A benchmarking suite comparing the performance of public convolutional neural network implementations across multiple deep learning frameworks.
What is Benchmark TensorFlow GitHub?
ConvNet Benchmarks is a benchmarking suite that compares the performance of various convolutional neural network implementations across different deep learning frameworks. It measures forward and backward pass times for popular CNN architectures like AlexNet, Overfeat, and GoogleNet, providing standardized performance data to help researchers and developers evaluate framework efficiency.
Deep learning researchers, computer vision engineers, and framework developers who need to compare the computational performance of different CNN implementations for model training and inference.
It provides transparent, hardware-standardized benchmarks that reveal real performance differences between frameworks—helping users avoid misleading conclusions about framework speed and enabling data-driven framework selection.
Overview
Easy benchmarking of all publicly accessible implementations of convnets
Use Cases
Best For
- Comparing CNN performance across TensorFlow, Caffe, Torch, and other frameworks
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
