CNN ARCHITECTURES: DENSENET

This is part of the CNN Architectures series by Dimitris Katsios. Find all CNN Architectures online: Notebooks: MLT GitHubVideo tutorials: YouTubeSupport MLT on Patreon DenseNet We will use the tensorflow.keras Functional API to build DenseNet from the original paper: “Densely Connected Convolutional Networks” by Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger. In the paper we can read: [i] “Note that … Continue reading CNN ARCHITECTURES: DENSENET

CNN ARCHITECTURES: SQUEEZENET

This is part of the CNN Architectures series by Dimitris Katsios. Find all CNN Architectures online: Notebooks: MLT GitHubVideo tutorials: YouTubeSupport MLT on Patreon SqueezeNet We will use the tensorflow.keras Functional API to build SqueezeNet from the original paper: “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size” by Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, … Continue reading CNN ARCHITECTURES: SQUEEZENET

AI DIGEST #MARCH20

By Alisher Abdulkhaev and Suzana Ilić Issue #9: March 2020 Keras turned 5Facebook releases SynSinTuring Award 2019 winners: Patrick M. Hanrahan and Edwin E. CatmullNeRF: Representing Scenes as Neural Radiance Fields for View SynthesisStanford NLP Group releases StanzaGoogle announced TensorFlow Developer CertificateICLR 2020 as a fully virtual conference due to the coronavirus spreadingGoogle announced TensorFlow Quantum: … Continue reading AI DIGEST #MARCH20