Convolutional Neural Networks (CNN) are widely used in different artificial intelligence (AI) applications. Major part of the computation of a CNN involves 2D convolution. In this paper, we propose ...

Article citations More>> Huang, H., Huang, W., Zhang, X. and Zhang, Y. (2020) Image Forgery Detection Using Integrated Convolution-LSTM (2D) and Convolution (2D). IEEE Signal Processing Letters, 27, ...

DLB (Deep Learning Blocks) as a part of DPU (Deep Learning Processing Unit) is a collection of synthesizable Verilog modules for deep learning inference network. - adki/Deep_Learning_Blocks ...

Thus, if my X has shape (batch_size, dimA, dimB) I can easily reshape it into a 2D input of shape (batch_size, (dimA * dimB)), with sequence_length= (dimA * dimB), but reshaping it back to get an X ...