代码之家 › 专栏 › 技术社区 › grabbag

如何在keras模型中可视化所学的训练权重?

jupyter-notebook keras tensorflow python-3.x

0

grabbag · 技术社区 · 6 年前

我的keras正在使用tensorflow后端。这是在docker图像中运行的,是从jupyter笔记本上运行的。

print(model.summary())将生成所有可训练参数的列表。

_____________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, 512, 512, 3)       0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 512, 512, 16)      448       
_________________________________________________________________
activation_1 (Activation)    (None, 512, 512, 16)      0         
_________________________________________________________________
batch_normalization_1 (Batch (None, 512, 512, 16)      64        
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 256, 256, 16)      0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 256, 256, 32)      4640

[<tf.Variable 'conv2d_1/kernel:0' shape=(3, 3, 3, 16) dtype=float32_ref>,
 <tf.Variable 'conv2d_1/bias:0' shape=(16,) dtype=float32_ref>,
 <tf.Variable 'batch_normalization_1/gamma:0' shape=(16,) dtype=float32_ref>,
 <tf.Variable 'batch_normalization_1/beta:0' shape=(16,) dtype=float32_ref>,
 <tf.Variable 'conv2d_2/kernel:0' shape=(3, 3, 16, 32) dtype=float32_ref>,
 <tf.Variable 'conv2d_2/bias:0' shape=(32,) dtype=float32_ref>,

我如何打印这些变量的值,以查看有多少得到疯狂的值,如0、1或无穷大?

0 回复 | 直到 6 年前

1

Daniele Grattarola 6 年前

最简单的方法是计算重量张量:

from keras import backend as K

for w in model.trainable_weights:
    print(K.eval(w))

K.eval(w)

np.isnan(w)
np.isinf(w)
w == 0
w == 1

你可以使用 np.any 或 np.argwhere

干杯