he Moving MNIST dataset contains 10,000 video sequences, each consisting of 20 frames. In each video sequence, two digits move independently around the frame, which has a spatial resolution of 64×64 pixels. The digits frequently intersect with each other and bounce off the edges of the frame
(移动MNIST数据集包含10，000个视频序列，每个序列包含20帧。在每一个视频序列中，两个数字独立地在64×64像素的框架内移动。这些数字经常相互穿插，并在框架边缘弹跳。)
声明：本站所有文章，如无特殊说明或标注，本站所有资源来源于网络，版权均属于原作者所有。如若本站内容侵犯了原著者的合法权益，可联系我们进行处理。
算力导航