2016-04-05 52 views
5

我想知道如何理解生成的張量流圖/直方圖。 這個代碼可以找到here. 這張圖很容易理解準確性和損失是直截了當的理解。如何理解張量流形張量板的直方圖?

Accuracy- Accuracy of current state of network for given train data. 
Higher is better 

Accuracy/Validation - Accuracy of current state of network for given Validation data which is 
not seen by network before. Higher is better 

Loss- Loss of network on train data. Lower is better. 
Loss/Valadation - Loss of network on test data. Lower is better. 
If loss increases it's a sign of over-fitting. 
Conv2d/L2-Loss - Loss of particular layer wrt train data. 

enter image description here

基本上什麼圖表示,如何我可以用它來了解我的網絡,如果可能,什麼樣的變化,我可以做,以改善它。

如何解釋直方圖?

enter image description here

回答

-1

tf.summary.histogram接受一個任意的尺寸和形狀張量,並將其壓縮成由與寬度和計數許多倉的直方圖數據結構。例如,假設我們希望將數字[0.5,1.1,1.3,2.2,2.9,2.99]組織到分箱中。我們可以創建三個bin:一個bin,包含0到1之間的所有元素(它將包含一個元素,0.5),一個包含1-2的所有元素的bin(它將包含兩個元素1.1和1.3),* 2-3(它將包含三個元素:2.2,2.9和2.99)。

請按照下面的鏈接瞭解詳情:

sunside answer

Tensorflow documentation