Keras Note

最新推荐文章于 2024-06-17 14:02:30 发布

MeJnCode

最新推荐文章于 2024-06-17 14:02:30 发布

阅读量1.1k

点赞数

CC 4.0 BY-SA版权

分类专栏： MachineLearning 文章标签：可视化 keras Theano

本文链接：https://blog.youkuaiyun.com/sinat_17496535/article/details/51933908

MachineLearning 专栏收录该内容

6 篇文章

订阅专栏

本文探讨了Keras中测试精度高于训练精度的原因，并提供了Keras模型及其特征层的可视化方法，包括卷积层和池化层。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Keras Note

Keras测试的精度比训练时返回的精度要高

Keras在测试时，一些规则化方法（如Drop out、L1/L2）被关闭了，且在训练时，权值始终在变化，而测试时keras的权值是训练时最后一次运算的结果，因此测试的精度通常都会比训练时返回的精度要高。

Keras可视化

可视化模型

from keras.utils.visualize_util import plot
plot(model, to_file='model.png')

可视化特征层

# -*- coding: utf-8 -*-
"""
visualizing model or feature maps in convolution layer and maxpooling layer
"""
from keras.models import model_from_json
from keras.utils.visualize_util import plot
import os
import theano
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm

MODEL_PATH = '/home/zhou/dl_data/chen-6-27/MachineLearning/cnn/Result/2016-07-12 04:09:21'
MODEL_NAME = 'model.json'


def visualize_model(to_file='model.png'):
    model = model_from_json(open(os.path.join(MODEL_PATH, MODEL_NAME)).read())
    plot(model, to_file=os.path.join(MODEL_PATH, to_file), show_shapes=True, show_layer_names=True)


def visualize_feature_map(data=None):
    """
    可视化特征层：卷积层、池化层
    """
    model = model_from_json(open(os.path.join(MODEL_PATH, MODEL_NAME)).read())
    input_shape = model.layers[0].input_shape
    assert input_shape[1:] == data.shape[1:], "data shape error, it should be {:}".format(input_shape)
    layers = model.layers
    pre = data.copy()
    for i in range(data.shape[0]):
        path = os.path.join(MODEL_PATH, "img{:}".format(i+1))
        if not os.path.exists(path):
            os.mkdir(path)
        path = os.path.join(path, 'original.png')
        img = np.squeeze(data[i])
        plt.imsave(path, img, cmap=cm.gray)
    for n, layer in enumerate(layers):
        prefix = layer.name.split('_')[0]
        if prefix == 'dropout':
            continue
        func = theano.function([layer.input], layer.output, allow_input_downcast=False)
        pre = func(pre)
        if prefix in ['convolution2d', 'maxpooling2d']:
            for i in range(pre.shape[0]):
                root = os.path.join(MODEL_PATH, 'img{:}'.format(i+1), 'layer{:}_'.format(n+1)+layer.name)
                if not os.path.exists(root):
                    os.mkdir(root)
                feature_maps = np.squeeze(pre[i])
                for j, m in enumerate(feature_maps):
                    path = os.path.join(root, '{:}.png'.format(j+1))
                    plt.imsave(path, m, cmap=cm.gray)


def require_data():
    # test
    from CNN import real_data
    data = real_data()[0][0:2]  # previous two images
    return data


def main():
    # visualize_model()
    data = require_data()
    visualize_feature_map(data)


if __name__ == '__main__':
    main()