anaconda下keras&tensorflow @ubuntu18.04开发环境安装

最新推荐文章于 2022-10-04 14:15:32 发布
最新推荐文章于 2022-10-04 14:15:32 发布
阅读量527 收藏 1
点赞数 8
分类专栏： Linux 人工智能 嵌入式系统 文章标签： tensorflow keras linux
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/tugouxp/article/details/120464891
版权
嵌入式系统 同时被 3 个专栏收录
355 篇文章 54 订阅
订阅专栏
Linux
218 篇文章 29 订阅
订阅专栏
人工智能
156 篇文章 16 订阅
订阅专栏

前面尝试在windows10上安装keras&tensorflow开发环境，总体上感觉还是比较麻烦的，今天抽时间在ubuntu18.04上安装了一把，很快就搞定了回归训练的模型，发现anaconda对Linux环境是比较友好的，以后可以在Linux下干活了。现在简要介绍一下搭建环境并执行回归训练用例的过程

下载anaconda

我选择的版本是

https://repo.anaconda.com/archive/Anaconda3-2020.11-Linux-x86_64.shhttps://repo.anaconda.com/archive/Anaconda3-2020.11-Linux-x86_64.sh

按照常规套路安装即可,具体可看这篇博文ubuntu18.04上安装anaconda-python深度学习环境_tugouxp的专栏-CSDN博客_ubuntu安装anaconda

安装tensorflow&keras

新开一个控制台，执行

pip install tensorflow 
pip install keras
(base) caozilong@caozilong-Vostro-3268:~$ pip install tensorflow
Collecting tensorflow
  Using cached tensorflow-2.6.0-cp38-cp38-manylinux2010_x86_64.whl (458.4 MB)
Collecting flatbuffers~=1.12.0
  Using cached flatbuffers-1.12-py2.py3-none-any.whl (15 kB)
Processing ./.cache/pip/wheels/f1/60/77/22b9b5887bd47801796a856f47650d9789c74dc3161a26d608/clang-5.0-py3-none-any.whl
Processing ./.cache/pip/wheels/a0/16/9c/5473df82468f958445479c59e784896fa24f4a5fc024b0f501/termcolor-1.1.0-py3-none-any.whl
Collecting tensorboard~=2.6
  Using cached tensorboard-2.6.0-py3-none-any.whl (5.6 MB)
Requirement already satisfied: six~=1.15.0 in ./anaconda3/lib/python3.8/site-packages (from tensorflow) (1.15.0)
Requirement already satisfied: numpy~=1.19.2 in ./anaconda3/lib/python3.8/site-packages (from tensorflow) (1.19.2)
Collecting astunparse~=1.6.3
  Using cached astunparse-1.6.3-py2.py3-none-any.whl (12 kB)
Collecting keras~=2.6
  Using cached keras-2.6.0-py2.py3-none-any.whl (1.3 MB)
Collecting protobuf>=3.9.2
  Using cached protobuf-3.18.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.1 MB)
Collecting grpcio<2.0,>=1.37.0
  Using cached grpcio-1.40.0-cp38-cp38-manylinux2014_x86_64.whl (4.3 MB)
Collecting google-pasta~=0.2
  Using cached google_pasta-0.2.0-py3-none-any.whl (57 kB)
Collecting tensorflow-estimator~=2.6
  Using cached tensorflow_estimator-2.6.0-py2.py3-none-any.whl (462 kB)
Collecting gast==0.4.0
  Using cached gast-0.4.0-py3-none-any.whl (9.8 kB)
Collecting wrapt~=1.12.1
  Using cached wrapt-1.12.1.tar.gz (27 kB)
Collecting keras-preprocessing~=1.1.2
  Using cached Keras_Preprocessing-1.1.2-py2.py3-none-any.whl (42 kB)
Requirement already satisfied: typing-extensions~=3.7.4 in ./anaconda3/lib/python3.8/site-packages (from tensorflow) (3.7.4.3)
Collecting opt-einsum~=3.3.0
  Using cached opt_einsum-3.3.0-py3-none-any.whl (65 kB)
Collecting absl-py~=0.10
  Downloading absl_py-0.14.0-py3-none-any.whl (131 kB)
     |████████████████████████████████| 131 kB 14 kB/s 
Requirement already satisfied: wheel~=0.35 in ./anaconda3/lib/python3.8/site-packages (from tensorflow) (0.35.1)
Collecting h5py~=3.1.0
  Using cached h5py-3.1.0-cp38-cp38-manylinux1_x86_64.whl (4.4 MB)
Collecting tensorboard-plugin-wit>=1.6.0
  Using cached tensorboard_plugin_wit-1.8.0-py3-none-any.whl (781 kB)
Collecting markdown>=2.6.8
  Using cached Markdown-3.3.4-py3-none-any.whl (97 kB)
Requirement already satisfied: requests<3,>=2.21.0 in ./anaconda3/lib/python3.8/site-packages (from tensorboard~=2.6->tensorflow) (2.24.0)
Requirement already satisfied: setuptools>=41.0.0 in ./anaconda3/lib/python3.8/site-packages (from tensorboard~=2.6->tensorflow) (50.3.1.post20201107)
Collecting tensorboard-data-server<0.7.0,>=0.6.0
  Using cached tensorboard_data_server-0.6.1-py3-none-manylinux2010_x86_64.whl (4.9 MB)
Requirement already satisfied: werkzeug>=0.11.15 in ./anaconda3/lib/python3.8/site-packages (from tensorboard~=2.6->tensorflow) (1.0.1)
Collecting google-auth-oauthlib<0.5,>=0.4.1
  Using cached google_auth_oauthlib-0.4.6-py2.py3-none-any.whl (18 kB)
Collecting google-auth<2,>=1.6.3
  Using cached google_auth-1.35.0-py2.py3-none-any.whl (152 kB)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in ./anaconda3/lib/python3.8/site-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow) (1.25.11)
Requirement already satisfied: chardet<4,>=3.0.2 in ./anaconda3/lib/python3.8/site-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow) (3.0.4)
Requirement already satisfied: idna<3,>=2.5 in ./anaconda3/lib/python3.8/site-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow) (2.10)
Requirement already satisfied: certifi>=2017.4.17 in ./anaconda3/lib/python3.8/site-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow) (2020.6.20)
Collecting requests-oauthlib>=0.7.0
  Using cached requests_oauthlib-1.3.0-py2.py3-none-any.whl (23 kB)
Collecting cachetools<5.0,>=2.0.0
  Using cached cachetools-4.2.2-py3-none-any.whl (11 kB)
Collecting pyasn1-modules>=0.2.1
  Using cached pyasn1_modules-0.2.8-py2.py3-none-any.whl (155 kB)
Collecting rsa<5,>=3.1.4; python_version >= "3.6"
  Using cached rsa-4.7.2-py3-none-any.whl (34 kB)
Collecting oauthlib>=3.0.0
  Using cached oauthlib-3.1.1-py2.py3-none-any.whl (146 kB)
Collecting pyasn1<0.5.0,>=0.4.6
  Using cached pyasn1-0.4.8-py2.py3-none-any.whl (77 kB)
Building wheels for collected packages: wrapt
  Building wheel for wrapt (setup.py) ... done
  Created wheel for wrapt: filename=wrapt-1.12.1-cp38-cp38-linux_x86_64.whl size=78040 sha256=097f5121388a4d88c78120d94fd98a14adee8e5e3c3a9a4daca757fb04307a5d
  Stored in directory: /home/caozilong/.cache/pip/wheels/5f/fd/9e/b6cf5890494cb8ef0b5eaff72e5d55a70fb56316007d6dfe73
Successfully built wrapt
Installing collected packages: flatbuffers, clang, termcolor, tensorboard-plugin-wit, markdown, absl-py, grpcio, tensorboard-data-server, protobuf, oauthlib, requests-oauthlib, cachetools, pyasn1, pyasn1-modules, rsa, google-auth, google-auth-oauthlib, tensorboard, astunparse, keras, google-pasta, tensorflow-estimator, gast, wrapt, keras-preprocessing, opt-einsum, h5py, tensorflow
  Attempting uninstall: wrapt
    Found existing installation: wrapt 1.11.2
    Uninstalling wrapt-1.11.2:
      Successfully uninstalled wrapt-1.11.2
  Attempting uninstall: h5py
    Found existing installation: h5py 2.10.0
    Uninstalling h5py-2.10.0:
      Successfully uninstalled h5py-2.10.0
Successfully installed absl-py-0.14.0 astunparse-1.6.3 cachetools-4.2.2 clang-5.0 flatbuffers-1.12 gast-0.4.0 google-auth-1.35.0 google-auth-oauthlib-0.4.6 google-pasta-0.2.0 grpcio-1.40.0 h5py-3.1.0 keras-2.6.0 keras-preprocessing-1.1.2 markdown-3.3.4 oauthlib-3.1.1 opt-einsum-3.3.0 protobuf-3.18.0 pyasn1-0.4.8 pyasn1-modules-0.2.8 requests-oauthlib-1.3.0 rsa-4.7.2 tensorboard-2.6.0 tensorboard-data-server-0.6.1 tensorboard-plugin-wit-1.8.0 tensorflow-2.6.0 tensorflow-estimator-2.6.0 termcolor-1.1.0 wrapt-1.12.1
(base) caozilong@caozilong-Vostro-3268:~$ pip install keras
Requirement already satisfied: keras in ./anaconda3/lib/python3.8/site-packages (2.6.0)
(base) caozilong@caozilong-Vostro-3268:~$

打开jupter notebook,确认版本

确认安装结果：

使用conda list 和 pip list确认包是否成功安装。

或者在navagitor中查看

随着时间推移，pip install安装的tensorflow和keras版本可能变化，由于tensorflow扯淡的各种版本不兼容，版本变高后不到一定能跑之前写的代码，所以还是建议安装2.6.0版的keras和tensorflow.

方法是：pip install xxxxpackage==版本号，就是在安装命令后加上"==版本号",比如：

还有一个需要注意的问题，就是安装工具pip必须用 anaconda自带的，如果用系统的，可能会导致安装的包无法被anaconda环境识别，导致不能使用，确认的方法很简单：

确认能不能用也很简单

以下是在虚拟机中二次安装的结果：

回归训练

from tensorflow import keras
import numpy as np
model=keras.Sequential([keras.layers.Dense(units=1, input_shape=[1])])
model.compile(optimizer="sgd",loss="mean_squared_error")
xs=np.array([-1.0,0.0,1.0,2.0,3.0,4.0],dtype=float)
ys=np.array([-3.0,-1.0,1.0,3.0,5.0,7.0],dtype=float)

model.fit(xs,ys, epochs=500)
model.summary()
model.predict([10.0])

Epoch 1/500
1/1 [==============================] - 0s 141ms/step - loss: 6.6106
Epoch 2/500
1/1 [==============================] - 0s 2ms/step - loss: 5.3884
Epoch 3/500
1/1 [==============================] - 0s 2ms/step - loss: 4.4230
Epoch 4/500
1/1 [==============================] - 0s 2ms/step - loss: 3.6596
Epoch 5/500
1/1 [==============================] - 0s 2ms/step - loss: 3.0554
Epoch 6/500
1/1 [==============================] - 0s 2ms/step - loss: 2.5764
Epoch 7/500
1/1 [==============================] - 0s 2ms/step - loss: 2.1960
Epoch 8/500
1/1 [==============================] - 0s 3ms/step - loss: 1.8932
Epoch 9/500
1/1 [==============================] - 0s 3ms/step - loss: 1.6517
Epoch 10/500
1/1 [==============================] - 0s 2ms/step - loss: 1.4583
Epoch 11/500
1/1 [==============================] - 0s 4ms/step - loss: 1.3028
Epoch 12/500
1/1 [==============================] - 0s 2ms/step - loss: 1.1774
Epoch 13/500
1/1 [==============================] - 0s 2ms/step - loss: 1.0755
Epoch 14/500
1/1 [==============================] - 0s 4ms/step - loss: 0.9923
Epoch 15/500
1/1 [==============================] - 0s 3ms/step - loss: 0.9239
Epoch 16/500
1/1 [==============================] - 0s 2ms/step - loss: 0.8671
Epoch 17/500
1/1 [==============================] - 0s 2ms/step - loss: 0.8195
Epoch 18/500
1/1 [==============================] - 0s 3ms/step - loss: 0.7793
Epoch 19/500
1/1 [==============================] - 0s 3ms/step - loss: 0.7448
Epoch 20/500
1/1 [==============================] - 0s 4ms/step - loss: 0.7150
Epoch 21/500
1/1 [==============================] - 0s 3ms/step - loss: 0.6890
Epoch 22/500
1/1 [==============================] - 0s 2ms/step - loss: 0.6658
Epoch 23/500
1/1 [==============================] - 0s 2ms/step - loss: 0.6451
Epoch 24/500
1/1 [==============================] - 0s 2ms/step - loss: 0.6263
Epoch 25/500
1/1 [==============================] - 0s 3ms/step - loss: 0.6091
Epoch 26/500
1/1 [==============================] - 0s 3ms/step - loss: 0.5931
Epoch 27/500
1/1 [==============================] - 0s 2ms/step - loss: 0.5782
Epoch 28/500
1/1 [==============================] - 0s 2ms/step - loss: 0.5642
Epoch 29/500
1/1 [==============================] - 0s 3ms/step - loss: 0.5510
Epoch 30/500
1/1 [==============================] - 0s 2ms/step - loss: 0.5383
Epoch 31/500
1/1 [==============================] - 0s 2ms/step - loss: 0.5262
Epoch 32/500
1/1 [==============================] - 0s 4ms/step - loss: 0.5146
Epoch 33/500
1/1 [==============================] - 0s 2ms/step - loss: 0.5034
Epoch 34/500
1/1 [==============================] - 0s 2ms/step - loss: 0.4926
Epoch 35/500
1/1 [==============================] - 0s 3ms/step - loss: 0.4820
Epoch 36/500
1/1 [==============================] - 0s 2ms/step - loss: 0.4718
Epoch 37/500
1/1 [==============================] - 0s 2ms/step - loss: 0.4619
Epoch 38/500
1/1 [==============================] - 0s 2ms/step - loss: 0.4522
Epoch 39/500
1/1 [==============================] - 0s 3ms/step - loss: 0.4428
Epoch 40/500
1/1 [==============================] - 0s 3ms/step - loss: 0.4336
Epoch 41/500
1/1 [==============================] - 0s 2ms/step - loss: 0.4246
Epoch 42/500
1/1 [==============================] - 0s 3ms/step - loss: 0.4158
Epoch 43/500
1/1 [==============================] - 0s 3ms/step - loss: 0.4072
Epoch 44/500
1/1 [==============================] - 0s 2ms/step - loss: 0.3988
Epoch 45/500
1/1 [==============================] - 0s 3ms/step - loss: 0.3905
Epoch 46/500
1/1 [==============================] - 0s 3ms/step - loss: 0.3825
Epoch 47/500
1/1 [==============================] - 0s 2ms/step - loss: 0.3746
Epoch 48/500
1/1 [==============================] - 0s 2ms/step - loss: 0.3669
Epoch 49/500
1/1 [==============================] - 0s 4ms/step - loss: 0.3593
Epoch 50/500
1/1 [==============================] - 0s 3ms/step - loss: 0.3519
Epoch 51/500
1/1 [==============================] - 0s 6ms/step - loss: 0.3447
Epoch 52/500
1/1 [==============================] - 0s 3ms/step - loss: 0.3376
Epoch 53/500
1/1 [==============================] - 0s 3ms/step - loss: 0.3307
Epoch 54/500
1/1 [==============================] - 0s 3ms/step - loss: 0.3239
Epoch 55/500
1/1 [==============================] - 0s 3ms/step - loss: 0.3172
Epoch 56/500
1/1 [==============================] - 0s 2ms/step - loss: 0.3107
Epoch 57/500
1/1 [==============================] - 0s 6ms/step - loss: 0.3043
Epoch 58/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2981
Epoch 59/500
1/1 [==============================] - 0s 4ms/step - loss: 0.2919
Epoch 60/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2860
Epoch 61/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2801
Epoch 62/500
1/1 [==============================] - 0s 4ms/step - loss: 0.2743
Epoch 63/500
1/1 [==============================] - 0s 3ms/step - loss: 0.2687
Epoch 64/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2632
Epoch 65/500
1/1 [==============================] - 0s 3ms/step - loss: 0.2578
Epoch 66/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2525
Epoch 67/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2473
Epoch 68/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2422
Epoch 69/500
1/1 [==============================] - 0s 4ms/step - loss: 0.2372
Epoch 70/500
1/1 [==============================] - 0s 3ms/step - loss: 0.2324
Epoch 71/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2276
Epoch 72/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2229
Epoch 73/500
1/1 [==============================] - 0s 5ms/step - loss: 0.2183
Epoch 74/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2138
Epoch 75/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2095
Epoch 76/500
1/1 [==============================] - 0s 2ms/step - loss: 0.2051
Epoch 77/500
1/1 [==============================] - 0s 3ms/step - loss: 0.2009
Epoch 78/500
1/1 [==============================] - 0s 4ms/step - loss: 0.1968
Epoch 79/500
1/1 [==============================] - 0s 3ms/step - loss: 0.1928
Epoch 80/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1888
Epoch 81/500
1/1 [==============================] - 0s 6ms/step - loss: 0.1849
Epoch 82/500
1/1 [==============================] - 0s 3ms/step - loss: 0.1811
Epoch 83/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1774
Epoch 84/500
1/1 [==============================] - 0s 4ms/step - loss: 0.1738
Epoch 85/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1702
Epoch 86/500
1/1 [==============================] - 0s 3ms/step - loss: 0.1667
Epoch 87/500
1/1 [==============================] - 0s 4ms/step - loss: 0.1633
Epoch 88/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1599
Epoch 89/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1566
Epoch 90/500
1/1 [==============================] - 0s 5ms/step - loss: 0.1534
Epoch 91/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1503
Epoch 92/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1472
Epoch 93/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1442
Epoch 94/500
1/1 [==============================] - 0s 4ms/step - loss: 0.1412
Epoch 95/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1383
Epoch 96/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1355
Epoch 97/500
1/1 [==============================] - 0s 4ms/step - loss: 0.1327
Epoch 98/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1299
Epoch 99/500
1/1 [==============================] - 0s 3ms/step - loss: 0.1273
Epoch 100/500
1/1 [==============================] - 0s 3ms/step - loss: 0.1247
Epoch 101/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1221
Epoch 102/500
1/1 [==============================] - 0s 3ms/step - loss: 0.1196
Epoch 103/500
1/1 [==============================] - 0s 4ms/step - loss: 0.1171
Epoch 104/500
1/1 [==============================] - 0s 3ms/step - loss: 0.1147
Epoch 105/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1124
Epoch 106/500
1/1 [==============================] - 0s 4ms/step - loss: 0.1101
Epoch 107/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1078
Epoch 108/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1056
Epoch 109/500
1/1 [==============================] - 0s 2ms/step - loss: 0.1034
Epoch 110/500
1/1 [==============================] - 0s 3ms/step - loss: 0.1013
Epoch 111/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0992
Epoch 112/500
1/1 [==============================] - ETA: 0s - loss: 0.097 - 0s 3ms/step - loss: 0.0972
Epoch 113/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0952
Epoch 114/500
1/1 [==============================] - 0s 1ms/step - loss: 0.0932
Epoch 115/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0913
Epoch 116/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0894
Epoch 117/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0876
Epoch 118/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0858
Epoch 119/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0840
Epoch 120/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0823
Epoch 121/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0806
Epoch 122/500
1/1 [==============================] - 0s 4ms/step - loss: 0.0790
Epoch 123/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0773
Epoch 124/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0758
Epoch 125/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0742
Epoch 126/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0727
Epoch 127/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0712
Epoch 128/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0697
Epoch 129/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0683
Epoch 130/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0669
Epoch 131/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0655
Epoch 132/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0642
Epoch 133/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0628
Epoch 134/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0616
Epoch 135/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0603
Epoch 136/500
1/1 [==============================] - 0s 4ms/step - loss: 0.0591
Epoch 137/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0578
Epoch 138/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0567
Epoch 139/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0555
Epoch 140/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0544
Epoch 141/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0532
Epoch 142/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0521
Epoch 143/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0511
Epoch 144/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0500
Epoch 145/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0490
Epoch 146/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0480
Epoch 147/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0470
Epoch 148/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0460
Epoch 149/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0451
Epoch 150/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0442
Epoch 151/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0433
Epoch 152/500
1/1 [==============================] - 0s 4ms/step - loss: 0.0424
Epoch 153/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0415
Epoch 154/500
1/1 [==============================] - 0s 6ms/step - loss: 0.0406
Epoch 155/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0398
Epoch 156/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0390
Epoch 157/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0382
Epoch 158/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0374
Epoch 159/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0366
Epoch 160/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0359
Epoch 161/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0351
Epoch 162/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0344
Epoch 163/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0337
Epoch 164/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0330
Epoch 165/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0323
Epoch 166/500
1/1 [==============================] - ETA: 0s - loss: 0.031 - 0s 2ms/step - loss: 0.0317
Epoch 167/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0310
Epoch 168/500
1/1 [==============================] - 0s 4ms/step - loss: 0.0304
Epoch 169/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0298
Epoch 170/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0292
Epoch 171/500
1/1 [==============================] - 0s 4ms/step - loss: 0.0286
Epoch 172/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0280
Epoch 173/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0274
Epoch 174/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0268
Epoch 175/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0263
Epoch 176/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0257
Epoch 177/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0252
Epoch 178/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0247
Epoch 179/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0242
Epoch 180/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0237
Epoch 181/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0232
Epoch 182/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0227
Epoch 183/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0223
Epoch 184/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0218
Epoch 185/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0214
Epoch 186/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0209
Epoch 187/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0205
Epoch 188/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0201
Epoch 189/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0197
Epoch 190/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0193
Epoch 191/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0189
Epoch 192/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0185
Epoch 193/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0181
Epoch 194/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0177
Epoch 195/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0174
Epoch 196/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0170
Epoch 197/500
1/1 [==============================] - 0s 4ms/step - loss: 0.0167
Epoch 198/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0163
Epoch 199/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0160
Epoch 200/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0156
Epoch 201/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0153
Epoch 202/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0150
Epoch 203/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0147
Epoch 204/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0144
Epoch 205/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0141
Epoch 206/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0138
Epoch 207/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0135
Epoch 208/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0133
Epoch 209/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0130
Epoch 210/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0127
Epoch 211/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0125
Epoch 212/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0122
Epoch 213/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0119
Epoch 214/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0117
Epoch 215/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0115
Epoch 216/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0112
Epoch 217/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0110
Epoch 218/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0108
Epoch 219/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0105
Epoch 220/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0103
Epoch 221/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0101
Epoch 222/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0099
Epoch 223/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0097
Epoch 224/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0095
Epoch 225/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0093
Epoch 226/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0091
Epoch 227/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0089
Epoch 228/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0087
Epoch 229/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0086
Epoch 230/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0084
Epoch 231/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0082
Epoch 232/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0081
Epoch 233/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0079
Epoch 234/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0077
Epoch 235/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0076
Epoch 236/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0074
Epoch 237/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0073
Epoch 238/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0071
Epoch 239/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0070
Epoch 240/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0068
Epoch 241/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0067
Epoch 242/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0065
Epoch 243/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0064
Epoch 244/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0063
Epoch 245/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0061
Epoch 246/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0060
Epoch 247/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0059
Epoch 248/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0058
Epoch 249/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0057
Epoch 250/500
1/1 [==============================] - 0s 4ms/step - loss: 0.0055
Epoch 251/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0054
Epoch 252/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0053
Epoch 253/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0052
Epoch 254/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0051
Epoch 255/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0050
Epoch 256/500
1/1 [==============================] - 0s 4ms/step - loss: 0.0049
Epoch 257/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0048
Epoch 258/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0047
Epoch 259/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0046
Epoch 260/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0045
Epoch 261/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0044
Epoch 262/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0043
Epoch 263/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0042
Epoch 264/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0041
Epoch 265/500
1/1 [==============================] - 0s 1ms/step - loss: 0.0041
Epoch 266/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0040
Epoch 267/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0039
Epoch 268/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0038
Epoch 269/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0037
Epoch 270/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0037
Epoch 271/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0036
Epoch 272/500
1/1 [==============================] - ETA: 0s - loss: 0.003 - 0s 3ms/step - loss: 0.0035
Epoch 273/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0034
Epoch 274/500
1/1 [==============================] - 0s 1ms/step - loss: 0.0034
Epoch 275/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0033
Epoch 276/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0032
Epoch 277/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0032
Epoch 278/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0031
Epoch 279/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0030
Epoch 280/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0030
Epoch 281/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0029
Epoch 282/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0029
Epoch 283/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0028
Epoch 284/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0027
Epoch 285/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0027
Epoch 286/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0026
Epoch 287/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0026
Epoch 288/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0025
Epoch 289/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0025
Epoch 290/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0024
Epoch 291/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0024
Epoch 292/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0023
Epoch 293/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0023
Epoch 294/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0022
Epoch 295/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0022
Epoch 296/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0021
Epoch 297/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0021
Epoch 298/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0020
Epoch 299/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0020
Epoch 300/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0020
Epoch 301/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0019
Epoch 302/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0019
Epoch 303/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0018
Epoch 304/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0018
Epoch 305/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0018
Epoch 306/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0017
Epoch 307/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0017
Epoch 308/500
1/1 [==============================] - 0s 4ms/step - loss: 0.0017
Epoch 309/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0016
Epoch 310/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0016
Epoch 311/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0016
Epoch 312/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0015
Epoch 313/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0015
Epoch 314/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0015
Epoch 315/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0014
Epoch 316/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0014
Epoch 317/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0014
Epoch 318/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0014
Epoch 319/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0013
Epoch 320/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0013
Epoch 321/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0013
Epoch 322/500
1/1 [==============================] - 0s 3ms/step - loss: 0.0012
Epoch 323/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0012
Epoch 324/500
1/1 [==============================] - 0s 1ms/step - loss: 0.0012
Epoch 325/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0012
Epoch 326/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0011
Epoch 327/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0011
Epoch 328/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0011
Epoch 329/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0011
Epoch 330/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0011
Epoch 331/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0010
Epoch 332/500
1/1 [==============================] - 0s 2ms/step - loss: 0.0010
Epoch 333/500
1/1 [==============================] - 0s 4ms/step - loss: 9.8988e-04
Epoch 334/500
1/1 [==============================] - 0s 2ms/step - loss: 9.6955e-04
Epoch 335/500
1/1 [==============================] - 0s 2ms/step - loss: 9.4963e-04
Epoch 336/500
1/1 [==============================] - 0s 2ms/step - loss: 9.3013e-04
Epoch 337/500
1/1 [==============================] - 0s 2ms/step - loss: 9.1102e-04
Epoch 338/500
1/1 [==============================] - 0s 3ms/step - loss: 8.9231e-04
Epoch 339/500
1/1 [==============================] - 0s 2ms/step - loss: 8.7398e-04
Epoch 340/500
1/1 [==============================] - 0s 2ms/step - loss: 8.5602e-04
Epoch 341/500
1/1 [==============================] - 0s 3ms/step - loss: 8.3844e-04
Epoch 342/500
1/1 [==============================] - 0s 2ms/step - loss: 8.2122e-04
Epoch 343/500
1/1 [==============================] - 0s 2ms/step - loss: 8.0435e-04
Epoch 344/500
1/1 [==============================] - 0s 2ms/step - loss: 7.8783e-04
Epoch 345/500
1/1 [==============================] - 0s 2ms/step - loss: 7.7165e-04
Epoch 346/500
1/1 [==============================] - 0s 3ms/step - loss: 7.5580e-04
Epoch 347/500
1/1 [==============================] - 0s 2ms/step - loss: 7.4027e-04
Epoch 348/500
1/1 [==============================] - 0s 2ms/step - loss: 7.2507e-04
Epoch 349/500
1/1 [==============================] - 0s 3ms/step - loss: 7.1017e-04
Epoch 350/500
1/1 [==============================] - 0s 3ms/step - loss: 6.9559e-04
Epoch 351/500
1/1 [==============================] - 0s 2ms/step - loss: 6.8130e-04
Epoch 352/500
1/1 [==============================] - 0s 2ms/step - loss: 6.6731e-04
Epoch 353/500
1/1 [==============================] - 0s 2ms/step - loss: 6.5360e-04
Epoch 354/500
1/1 [==============================] - 0s 3ms/step - loss: 6.4017e-04
Epoch 355/500
1/1 [==============================] - 0s 2ms/step - loss: 6.2702e-04
Epoch 356/500
1/1 [==============================] - 0s 3ms/step - loss: 6.1414e-04
Epoch 357/500
1/1 [==============================] - 0s 2ms/step - loss: 6.0153e-04
Epoch 358/500
1/1 [==============================] - 0s 2ms/step - loss: 5.8917e-04
Epoch 359/500
1/1 [==============================] - 0s 3ms/step - loss: 5.7707e-04
Epoch 360/500
1/1 [==============================] - 0s 2ms/step - loss: 5.6521e-04
Epoch 361/500
1/1 [==============================] - 0s 2ms/step - loss: 5.5360e-04
Epoch 362/500
1/1 [==============================] - 0s 2ms/step - loss: 5.4223e-04
Epoch 363/500
1/1 [==============================] - 0s 4ms/step - loss: 5.3110e-04
Epoch 364/500
1/1 [==============================] - 0s 2ms/step - loss: 5.2018e-04
Epoch 365/500
1/1 [==============================] - 0s 2ms/step - loss: 5.0950e-04
Epoch 366/500
1/1 [==============================] - 0s 2ms/step - loss: 4.9903e-04
Epoch 367/500
1/1 [==============================] - 0s 3ms/step - loss: 4.8878e-04
Epoch 368/500
1/1 [==============================] - ETA: 0s - loss: 4.7874e-0 - 0s 3ms/step - loss: 4.7874e-04
Epoch 369/500
1/1 [==============================] - 0s 2ms/step - loss: 4.6891e-04
Epoch 370/500
1/1 [==============================] - 0s 2ms/step - loss: 4.5928e-04
Epoch 371/500
1/1 [==============================] - 0s 2ms/step - loss: 4.4985e-04
Epoch 372/500
1/1 [==============================] - 0s 3ms/step - loss: 4.4060e-04
Epoch 373/500
1/1 [==============================] - 0s 2ms/step - loss: 4.3156e-04
Epoch 374/500
1/1 [==============================] - 0s 3ms/step - loss: 4.2269e-04
Epoch 375/500
1/1 [==============================] - 0s 3ms/step - loss: 4.1401e-04
Epoch 376/500
1/1 [==============================] - 0s 2ms/step - loss: 4.0551e-04
Epoch 377/500
1/1 [==============================] - 0s 2ms/step - loss: 3.9718e-04
Epoch 378/500
1/1 [==============================] - 0s 4ms/step - loss: 3.8902e-04
Epoch 379/500
1/1 [==============================] - 0s 2ms/step - loss: 3.8103e-04
Epoch 380/500
1/1 [==============================] - 0s 2ms/step - loss: 3.7320e-04
Epoch 381/500
1/1 [==============================] - 0s 2ms/step - loss: 3.6554e-04
Epoch 382/500
1/1 [==============================] - 0s 2ms/step - loss: 3.5803e-04
Epoch 383/500
1/1 [==============================] - 0s 3ms/step - loss: 3.5067e-04
Epoch 384/500
1/1 [==============================] - 0s 2ms/step - loss: 3.4347e-04
Epoch 385/500
1/1 [==============================] - 0s 2ms/step - loss: 3.3641e-04
Epoch 386/500
1/1 [==============================] - 0s 2ms/step - loss: 3.2951e-04
Epoch 387/500
1/1 [==============================] - 0s 2ms/step - loss: 3.2274e-04
Epoch 388/500
1/1 [==============================] - 0s 2ms/step - loss: 3.1611e-04
Epoch 389/500
1/1 [==============================] - 0s 2ms/step - loss: 3.0961e-04
Epoch 390/500
1/1 [==============================] - 0s 3ms/step - loss: 3.0326e-04
Epoch 391/500
1/1 [==============================] - 0s 2ms/step - loss: 2.9703e-04
Epoch 392/500
1/1 [==============================] - 0s 3ms/step - loss: 2.9092e-04
Epoch 393/500
1/1 [==============================] - 0s 3ms/step - loss: 2.8495e-04
Epoch 394/500
1/1 [==============================] - 0s 3ms/step - loss: 2.7910e-04
Epoch 395/500
1/1 [==============================] - 0s 2ms/step - loss: 2.7336e-04
Epoch 396/500
1/1 [==============================] - 0s 2ms/step - loss: 2.6775e-04
Epoch 397/500
1/1 [==============================] - 0s 4ms/step - loss: 2.6225e-04
Epoch 398/500
1/1 [==============================] - 0s 3ms/step - loss: 2.5686e-04
Epoch 399/500
1/1 [==============================] - 0s 2ms/step - loss: 2.5159e-04
Epoch 400/500
1/1 [==============================] - 0s 3ms/step - loss: 2.4642e-04
Epoch 401/500
1/1 [==============================] - 0s 2ms/step - loss: 2.4135e-04
Epoch 402/500
1/1 [==============================] - 0s 3ms/step - loss: 2.3640e-04
Epoch 403/500
1/1 [==============================] - 0s 2ms/step - loss: 2.3154e-04
Epoch 404/500
1/1 [==============================] - 0s 2ms/step - loss: 2.2679e-04
Epoch 405/500
1/1 [==============================] - 0s 2ms/step - loss: 2.2213e-04
Epoch 406/500
1/1 [==============================] - 0s 2ms/step - loss: 2.1757e-04
Epoch 407/500
1/1 [==============================] - 0s 2ms/step - loss: 2.1310e-04
Epoch 408/500
1/1 [==============================] - 0s 2ms/step - loss: 2.0872e-04
Epoch 409/500
1/1 [==============================] - 0s 2ms/step - loss: 2.0443e-04
Epoch 410/500
1/1 [==============================] - 0s 2ms/step - loss: 2.0023e-04
Epoch 411/500
1/1 [==============================] - 0s 2ms/step - loss: 1.9612e-04
Epoch 412/500
1/1 [==============================] - 0s 3ms/step - loss: 1.9209e-04
Epoch 413/500
1/1 [==============================] - 0s 2ms/step - loss: 1.8815e-04
Epoch 414/500
1/1 [==============================] - 0s 2ms/step - loss: 1.8428e-04
Epoch 415/500
1/1 [==============================] - 0s 3ms/step - loss: 1.8050e-04
Epoch 416/500
1/1 [==============================] - 0s 2ms/step - loss: 1.7679e-04
Epoch 417/500
1/1 [==============================] - 0s 2ms/step - loss: 1.7316e-04
Epoch 418/500
1/1 [==============================] - 0s 2ms/step - loss: 1.6960e-04
Epoch 419/500
1/1 [==============================] - 0s 3ms/step - loss: 1.6612e-04
Epoch 420/500
1/1 [==============================] - 0s 2ms/step - loss: 1.6271e-04
Epoch 421/500
1/1 [==============================] - 0s 2ms/step - loss: 1.5936e-04
Epoch 422/500
1/1 [==============================] - 0s 2ms/step - loss: 1.5609e-04
Epoch 423/500
1/1 [==============================] - 0s 3ms/step - loss: 1.5288e-04
Epoch 424/500
1/1 [==============================] - 0s 2ms/step - loss: 1.4974e-04
Epoch 425/500
1/1 [==============================] - 0s 1ms/step - loss: 1.4666e-04
Epoch 426/500
1/1 [==============================] - 0s 2ms/step - loss: 1.4365e-04
Epoch 427/500
1/1 [==============================] - 0s 3ms/step - loss: 1.4070e-04
Epoch 428/500
1/1 [==============================] - 0s 3ms/step - loss: 1.3781e-04
Epoch 429/500
1/1 [==============================] - 0s 2ms/step - loss: 1.3498e-04
Epoch 430/500
1/1 [==============================] - 0s 2ms/step - loss: 1.3221e-04
Epoch 431/500
1/1 [==============================] - 0s 3ms/step - loss: 1.2949e-04
Epoch 432/500
1/1 [==============================] - 0s 2ms/step - loss: 1.2683e-04
Epoch 433/500
1/1 [==============================] - 0s 2ms/step - loss: 1.2423e-04
Epoch 434/500
1/1 [==============================] - 0s 3ms/step - loss: 1.2168e-04
Epoch 435/500
1/1 [==============================] - 0s 2ms/step - loss: 1.1918e-04
Epoch 436/500
1/1 [==============================] - 0s 2ms/step - loss: 1.1673e-04
Epoch 437/500
1/1 [==============================] - 0s 2ms/step - loss: 1.1433e-04
Epoch 438/500
1/1 [==============================] - 0s 3ms/step - loss: 1.1198e-04
Epoch 439/500
1/1 [==============================] - 0s 2ms/step - loss: 1.0968e-04
Epoch 440/500
1/1 [==============================] - ETA: 0s - loss: 1.0743e-0 - 0s 2ms/step - loss: 1.0743e-04
Epoch 441/500
1/1 [==============================] - 0s 3ms/step - loss: 1.0522e-04
Epoch 442/500
1/1 [==============================] - 0s 3ms/step - loss: 1.0306e-04
Epoch 443/500
1/1 [==============================] - 0s 2ms/step - loss: 1.0094e-04
Epoch 444/500
1/1 [==============================] - 0s 3ms/step - loss: 9.8870e-05
Epoch 445/500
1/1 [==============================] - 0s 2ms/step - loss: 9.6840e-05
Epoch 446/500
1/1 [==============================] - 0s 2ms/step - loss: 9.4850e-05
Epoch 447/500
1/1 [==============================] - 0s 2ms/step - loss: 9.2903e-05
Epoch 448/500
1/1 [==============================] - 0s 4ms/step - loss: 9.0994e-05
Epoch 449/500
1/1 [==============================] - 0s 2ms/step - loss: 8.9126e-05
Epoch 450/500
1/1 [==============================] - 0s 2ms/step - loss: 8.7295e-05
Epoch 451/500
1/1 [==============================] - 0s 2ms/step - loss: 8.5501e-05
Epoch 452/500
1/1 [==============================] - 0s 3ms/step - loss: 8.3744e-05
Epoch 453/500
1/1 [==============================] - 0s 3ms/step - loss: 8.2024e-05
Epoch 454/500
1/1 [==============================] - 0s 5ms/step - loss: 8.0339e-05
Epoch 455/500
1/1 [==============================] - 0s 2ms/step - loss: 7.8687e-05
Epoch 456/500
1/1 [==============================] - 0s 2ms/step - loss: 7.7072e-05
Epoch 457/500
1/1 [==============================] - 0s 2ms/step - loss: 7.5489e-05
Epoch 458/500
1/1 [==============================] - 0s 3ms/step - loss: 7.3938e-05
Epoch 459/500
1/1 [==============================] - 0s 2ms/step - loss: 7.2419e-05
Epoch 460/500
1/1 [==============================] - 0s 4ms/step - loss: 7.0932e-05
Epoch 461/500
1/1 [==============================] - 0s 2ms/step - loss: 6.9475e-05
Epoch 462/500
1/1 [==============================] - 0s 2ms/step - loss: 6.8049e-05
Epoch 463/500
1/1 [==============================] - 0s 2ms/step - loss: 6.6650e-05
Epoch 464/500
1/1 [==============================] - 0s 4ms/step - loss: 6.5282e-05
Epoch 465/500
1/1 [==============================] - 0s 2ms/step - loss: 6.3941e-05
Epoch 466/500
1/1 [==============================] - 0s 3ms/step - loss: 6.2626e-05
Epoch 467/500
1/1 [==============================] - 0s 2ms/step - loss: 6.1341e-05
Epoch 468/500
1/1 [==============================] - 0s 2ms/step - loss: 6.0080e-05
Epoch 469/500
1/1 [==============================] - 0s 2ms/step - loss: 5.8846e-05
Epoch 470/500
1/1 [==============================] - 0s 2ms/step - loss: 5.7637e-05
Epoch 471/500
1/1 [==============================] - 0s 2ms/step - loss: 5.6453e-05
Epoch 472/500
1/1 [==============================] - 0s 2ms/step - loss: 5.5294e-05
Epoch 473/500
1/1 [==============================] - 0s 2ms/step - loss: 5.4158e-05
Epoch 474/500
1/1 [==============================] - 0s 3ms/step - loss: 5.3046e-05
Epoch 475/500
1/1 [==============================] - 0s 3ms/step - loss: 5.1957e-05
Epoch 476/500
1/1 [==============================] - 0s 3ms/step - loss: 5.0889e-05
Epoch 477/500
1/1 [==============================] - 0s 4ms/step - loss: 4.9844e-05
Epoch 478/500
1/1 [==============================] - 0s 3ms/step - loss: 4.8819e-05
Epoch 479/500
1/1 [==============================] - 0s 2ms/step - loss: 4.7818e-05
Epoch 480/500
1/1 [==============================] - 0s 2ms/step - loss: 4.6835e-05
Epoch 481/500
1/1 [==============================] - 0s 2ms/step - loss: 4.5873e-05
Epoch 482/500
1/1 [==============================] - 0s 3ms/step - loss: 4.4931e-05
Epoch 483/500
1/1 [==============================] - 0s 2ms/step - loss: 4.4007e-05
Epoch 484/500
1/1 [==============================] - 0s 2ms/step - loss: 4.3104e-05
Epoch 485/500
1/1 [==============================] - 0s 5ms/step - loss: 4.2219e-05
Epoch 486/500
1/1 [==============================] - 0s 2ms/step - loss: 4.1352e-05
Epoch 487/500
1/1 [==============================] - 0s 2ms/step - loss: 4.0502e-05
Epoch 488/500
1/1 [==============================] - 0s 6ms/step - loss: 3.9670e-05
Epoch 489/500
1/1 [==============================] - 0s 2ms/step - loss: 3.8855e-05
Epoch 490/500
1/1 [==============================] - 0s 2ms/step - loss: 3.8057e-05
Epoch 491/500
1/1 [==============================] - 0s 3ms/step - loss: 3.7276e-05
Epoch 492/500
1/1 [==============================] - 0s 2ms/step - loss: 3.6510e-05
Epoch 493/500
1/1 [==============================] - 0s 2ms/step - loss: 3.5760e-05
Epoch 494/500
1/1 [==============================] - 0s 2ms/step - loss: 3.5025e-05
Epoch 495/500
1/1 [==============================] - 0s 2ms/step - loss: 3.4306e-05
Epoch 496/500
1/1 [==============================] - 0s 2ms/step - loss: 3.3602e-05
Epoch 497/500
1/1 [==============================] - 0s 2ms/step - loss: 3.2911e-05
Epoch 498/500
1/1 [==============================] - 0s 2ms/step - loss: 3.2235e-05
Epoch 499/500
1/1 [==============================] - 0s 2ms/step - loss: 3.1574e-05
Epoch 500/500
1/1 [==============================] - 0s 2ms/step - loss: 3.0924e-05
Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_1 (Dense)              (None, 1)                 2         
=================================================================
Total params: 2
Trainable params: 2
Non-trainable params: 0
_________________________________________________________________
array([[18.983774]], dtype=float32)
​

运行CNN模型：

from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv2D, MaxPool2D

# 下面代码在判断有没 mnist.npz, 如果没有, 在网上下载
# (train_data, train_labels), (test_data, test_labels) = keras.datasets.mnist.load_data()

# 
(train_data, train_labels), (test_data, test_labels) = keras.datasets.mnist.load_data(path='mnist.npz')
train_data = train_data.reshape(-1, 28, 28, 1)
print("train data type:{}, shape:{}, dim:{}".format(type(train_data), train_data.shape, train_data.ndim))

# 第一组
model = Sequential()
model.add(Conv2D(filters=32, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation='relu', input_shape=(28, 28, 1)))
model.add(Conv2D(filters=32, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation='relu'))
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

# 第二组
model.add(Conv2D(filters=64, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation='relu'))
model.add(Conv2D(filters=64, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation='relu'))
model.add(MaxPool2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

# 第三组
model.add(Flatten())
model.add(Dense(units=256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(units=10, activation='softmax'))

# 查看模型
model.summary()

如何切换下载源：

由于万里长城的原因，不同的下载源，下载速度差异非常大，幸运的是无论conda还是pip都可以切换下载源来提高包的下载速度。

conda的切换方式：

  1. conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/
  2. conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
  3. conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
  4. conda config --append channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/fastai/
  5. conda config --append channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/
  6. conda config --append channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/bioconda/
  7. conda config --set show_channel_urls yes

这样，在执行conda install后会有一个阶段显示每个包的下载源：

pip/pip2/pip3方式：

PIP就比较简单，直接加上 -i  https://pypi.tuna.tsinghua.edu.cn/simple 使用清华下载源即可。

结束！

papaofdoudou
关注
  • 8
    点赞
  • 踩
  • 1
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论
专栏目录
在ubuntu中的anaconda安装keras
嘿西西
01-06 366
安装过程 1、首先激活子环境 （在安装tensorflow的文章里面已经写过如何创建子环境）链接 source activate tf 2、安装keras pip install keras 3、测试keras python import keras 不报错则安装成功 4、关闭子环境 source deactivate 遇到的问题： ImportError: Keras requires TensorFlow 2.2 or higher. Install TensorFlow via `pip
Ubuntu18.04基于anaconda安装tensorflow
圣雅丹青
05-06 1万+
Ubuntu18.04下安装tensorflow需要安装的东西很多，包括 虚拟机——ubuntu18.04——Python3.6.5——setuptools——python-pip——Anaconda ——tensorflow 请跟随我一步一步走，不要着急，慢慢来~ 1.安装虚拟机 第一步我就遇到了问题，以前装好的虚拟机，更新后，却出现了问题，没有找到很好的解决办法，那就重装。 我选择的...
【在Ubuntu上安装Keras及其依赖】
weixin_42165744的博客
10-04 1862
Ubuntu系统更换驱动、安装CUDA、Tensorflow、Keras、Jupyter。
ubuntu 下安装 tensorflow 和 keras
程序猿视角
04-21 1556
申请了一台超算服务器，里面的系统很旧，试着安装了一下 tensorflow 和 keras，折腾了一天也无法在 python 中运行。今天耐下心来研究了一下安装程序，轻松解决这个问题。 了解 conda 在 ubuntu 系统中，有两个安装工具需要了解，一个是 conda，另一个是 pip。 这两个工具主要区别是，conda 不仅能为 python 安装软件包，而且也能为其它语言安装。pip 只能安装 python 的软件包。 conda 可以创建自己的运行环境。最初我反复折腾，没有效果，主要原因是我是在
新手傻瓜式推荐教程：anaconda+Tensorflow+keras的安装详细教程
Hdhdi的博客
06-22 7497
一、Anaconda的安装 可以在官网直接下载https://www.anaconda.com/products/individual 也可以在清华镜像上，博主是直接在清华镜像去下载的快一些，这里附上链接：https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive/ 下载好安装包后，双击安装包点Next按照以下图片所指进行 接下来选择路径，不建议安装在C盘，可以在其他盘创建一个文件夹，安装在其他盘 选好后点next 添加环境变量把两个选
tensorflow安装教程
pypyquixue的博客
05-04 2167
今天打算要安装tensorflow，结果就遇到事情了。。。。 pip安装tensorflow pip install tensorflow 结果翻车了 ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
Ubuntu18.04下Anaconda虚拟环境创建和tensorflow_gpu安装
weixin_43064339的博客
01-09 9630
这里写自定义目录标题1 虚拟环境创建2 激活环境3 TensorFlow安装 1 虚拟环境创建 conda create -n tensorflow python=3.6 如下图 2 激活环境 source activate tensorflow 如下图 3 TensorFlow安装 conda install -n tensorflow -c https://conda.anaco...
在 Ubuntu 18.04 上安装 Anaconda 的教程
最新发布
11-18
安装 Anaconda 在 Ubuntu 18.04 上的步骤 安装 Anaconda 在 Ubuntu 18.04 上需要遵循特定的步骤，以确保成功安装 Anaconda。以下是安装 Anaconda 在 Ubuntu 18.04 上的步骤： Step 1: 下载 Anaconda 安装包 首先...
Ubuntu18.04安装 PyCharm并使用 Anaconda 管理的Python环境
09-17
在Ubuntu 18.04操作系统中安装PyCharm并结合Anaconda来管理Python环境是一项重要的任务，这对于数据科学和机器学习项目的开发尤其关键。PyCharm是一款强大的集成开发环境（IDE），支持多种编程语言，尤其是Python。...
Ubuntu18.04下安装MySQL(图文教程)
09-09
在Ubuntu 18.04操作系统中安装MySQL是一项基础且重要的任务，尤其对于开发者和系统管理员来说。MySQL是一种流行的开源关系型数据库管理系统，广泛应用于Web应用、数据分析和其他需要高效数据存储和检索的场景。在这...
Anaconda+VSCode配置tensorflow开发环境的教程详解
09-17
Anaconda是一个开源的python发行版本，是现在比较流行的python数据科学平台，可以对python的科学包做到有效管理。这篇文章主要介绍了Anaconda+VSCode配置tensorflow开发环境,需要的朋友可以参考下
ubuntu 18.04搭建python环境（pycharm+anaconda）
09-19
在Ubuntu 18.04上搭建Python开发环境是一个重要的步骤，尤其是对于那些正在学习或从事数据分析、机器学习以及Web开发的用户。本教程将详细讲解如何安装和配置Python环境，包括Anaconda和PyCharm。 **Anaconda的安装...
Linux+Ubuntu； Keras安装步骤
sunny
09-06 9060
Keras的安装 一、Anaconda的安装： 1、 下载anaconda，官网地址：http://continuum.io/downloads。 选择linux64-bit-python2.7 2、 安装anaconda，在终端输入:cd ~/Downloads;（切换目录） bash Anaconda-2.2.0-Linux-x86_64.sh（安装）(现在版本已更新，按下载的版本名...
ubuntu安装keras
weixin_30869099的博客
03-13 70
参考此链接 http://blog.csdn.net/a1311543690/article/details/48878843 http://blog.csdn.net/u011037837/article/details/51580142 转载于:https://www.cnblogs.com/edhg/p/6540476.html
Ubuntu深度学习环境配置（3）：Ubuntu18.04基于anaconda安装tensorflow+keras+pytorch
Hankerchen的博客
05-16 1822
TensorFlow安装及报错 1 遇到的问题2 继续安装tensorflow-gpu3.安装kreas-gpu3.安装pytorch ) 根据史上最详细的UEFI+GTP安装ubuntu18.04LTS全记录，涵盖安装过程中的各种问题，所有的问题都将在这里终结博文，安装了Anaconda，本文继续安装TensorFlow。 conda create --name tensorflow_env python=3.7 1 遇到的问题 准备创建TensorFlow环境，出现如下问题。 NotWritable
建立深度学习工作站：在Ubuntu上安装Keras及其依赖
南七行者的博客
07-21 1529
一、建立深度学习工作站的步骤 （1）安装Python科学套件( Numpy 和 Scipy) + 基础线性代数子程序库( BLAS ) （2）安装HDF5 + Graphviz （3）安装CUDA驱动程序和cuDNN （4）安装一个Keras后端：TensorFlow （5）安装Keras 参考书目：《Python深度学习（Keras）》附录 pip3 install tensorflow-gpu==1.15.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
Anaconda安装tensorflow和keras包
qq_48078689的博客
04-19 9352
1.背景 在Anaconda中无法直接安装这两个包，安装过程异常漫长。 2.准备工作 //建议安装最新版本的Anaconda，可直接在Anaconda prompt(用电脑全局搜索直接打开)中通过输入命令行安装更新，我是卸载了旧版本然后在官网安装了最新版本 添加清华源 1.首先寻找到用户目录下的.condarc文件，如果没找到的话可能是隐藏了，可右键设置显示隐藏文件 2.将该文件内容更改为 channels: defaults show_channel_urls: true default_channel
ubuntu 18.04安装tensorflow环境
奔跑的蜗牛蒋
10-14 856
参考：https://blog.csdn.net/tjuyanming/article/details/80862290 https://blog.csdn.net/u010801439/article/details/80483036 https://blog.csdn.net/JackSparrow_sjl/article/details/81878270 安装显卡驱动 1、禁nouv...
使用OpenCV识别二维码
热门推荐
tugouxp的专栏
09-12 1万+
程序： # -*-coding:utf-8 -*- import cv2 as cv import numpy as np # 加载图片 src_image = cv.imread("./webwxgetmsgimg.jpeg") # 实例化 qrcoder = cv.QRCodeDetector() # qr检测并解码 codeinfo, points, straight_qrcode = qrcoder.detectAndDecode(src_image) # 绘制qr的检测结果 cv.dr

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

papaofdoudou

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付：¥1
获取中
扫码支付

您的余额不足，请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值