卷积神经网络可视化-权重或激活? [英] Convolutional Neural Network visualization - weights or activations?

问题描述

上面的可视化是第一卷积层的权重或第一卷积层上给定输入图像上的激活的呈现吗?

Is the above visualization a rendering of the weights of the first convolutional layer or the activations on a given input image on the first convolutional layer?

下面是我已经训练了48个小时的Inception v2模型的第一卷积层权重的可视化视图:

Below is a visualization of the weights of the first convolutional layer of the Inception v2 model that I've been training for 48 hours:

我确定仅在48小时后(在CPU上)我尚未收敛模型.训练精度超过90％的这些权重现在是否应该现在就可以消除?

I'm sure I have not converged my model after only 48 hours (on a CPU). Shouldn't those weights begin to smooth out by now, where training accuracy is over 90%?

推荐答案

根据

According to ImageNet Classification with Deep Convolutional Neural Networks, The first convolutional layer takes as input a 224x224x3 image (note: should be 227x227 instead of 224x224) and filters it with 96 kernels of size 11x11x3.

上图显示了第一卷积层学习的卷积内核.

The figure above shows the convolutional kernels learned by the first convolutional layer.

注意:实际上，图中可能有96个卷积核，其大小为11×11×3.

note: in fact in the figure is possible count 96 convolutional kernels that sould be of size 11×11×3.

这篇关于卷积神经网络可视化-权重或激活?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！