autoKeras
autoKeras GitHub:https://github.com/jhfjhfj1/autokeras
百度网盘下载地址:http://pandownload.com/
autoKeras官方文档:https://autokeras.com/
开始进入主题:Windows安装autoKeras
第一步:安装autoKeras:https://github.com/jhfjhfj1/autokeras 这里是压缩包,使用 python setup.py install
第二步:依赖于pytorch 所以需要安装 torch
版本对比:torch0.4-cuda9.0-python3.6
torch 见博客。此处需要翻墙https://pytorch.org/,
cuda9 博客
第三步:pip3 install torchvision
过程中遇到的错误或许能帮助你,更新numpy到新 numpy+mke 保存可视化图片需安装:https://www.cnblogs.com/shuodehaoa/p/8667045.html
测试结果如下:
说明成功安装能使用GPU加速。
from keras.datasets import mnist from autokeras.image_supervised import ImageClassifier if __name__ == '__main__': (x_train, y_train), (x_test, y_test) = mnist.load_data(r'E:xxxxpython_basics自动深度学习datamnist.npz') x_train = x_train.reshape(x_train.shape + (1,)) x_test = x_test.reshape(x_test.shape + (1,)) clf = ImageClassifier(verbose=True) clf.fit(x_train, y_train, time_limit=1*60) clf.final_fit(x_train, y_train, x_test, y_test, retrain=True) y = clf.evaluate(x_test, y_test) print(y)