Plese see this answer for a detailed example of how tf.nn.conv2d_backprop_input and tf.nn.conv2d_backprop_filter in an example. In tf.nn, there are 4 closely related 2d conv functions: tf.nn.conv2d tf.nn.conv2d_backprop_filter tf.nn.conv2d_backprop_i
<Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition>,这篇paper提出了空间金字塔池化. 之前学习的RCNN,虽然使用了建议候选区域使得速度大大降低,但是对于超大容量的数据,计算速度还有待提高.对RCNN来说,计算冗余很大一部分来自于:对每一个proposal region提取一次特征,而不同region之间有很多的交集,这就导致很大的计算冗余.因此fast-rcnn提出了,先对图片进行