TF2-MNIST

!pip install tensorflow

Collecting tensorflow
  Downloading tensorflow-2.3.1-cp37-cp37m-manylinux2010_x86_64.whl (320.4 MB)
     |████████████████████████████████| 320.4 MB 25 kB/s 
Collecting tensorboard<3,>=2.3.0
  Downloading tensorboard-2.3.0-py3-none-any.whl (6.8 MB)
     |████████████████████████████████| 6.8 MB 36.5 MB/s 
Collecting google-pasta>=0.1.8
  Downloading google_pasta-0.2.0-py3-none-any.whl (57 kB)
     |████████████████████████████████| 57 kB 14.6 MB/s 
Collecting wrapt>=1.11.1
  Downloading wrapt-1.12.1.tar.gz (27 kB)
Collecting astunparse==1.6.3
  Downloading astunparse-1.6.3-py2.py3-none-any.whl (12 kB)
Collecting gast==0.3.3
  Downloading gast-0.3.3-py2.py3-none-any.whl (9.7 kB)
Collecting termcolor>=1.1.0
  Downloading termcolor-1.1.0.tar.gz (3.9 kB)
Requirement already satisfied: wheel>=0.26 in /opt/venv/lib/python3.7/site-packages (from tensorflow) (0.35.1)
Requirement already satisfied: six>=1.12.0 in /opt/venv/lib/python3.7/site-packages (from tensorflow) (1.15.0)
Collecting numpy<1.19.0,>=1.16.0
  Downloading numpy-1.18.5-cp37-cp37m-manylinux1_x86_64.whl (20.1 MB)
     |████████████████████████████████| 20.1 MB 54.5 MB/s 
Collecting opt-einsum>=2.3.2
  Downloading opt_einsum-3.3.0-py3-none-any.whl (65 kB)
     |████████████████████████████████| 65 kB 8.0 MB/s 
Collecting tensorflow-estimator<2.4.0,>=2.3.0
  Downloading tensorflow_estimator-2.3.0-py2.py3-none-any.whl (459 kB)
     |████████████████████████████████| 459 kB 57.7 MB/s 
Collecting protobuf>=3.9.2
  Downloading protobuf-3.13.0-cp37-cp37m-manylinux1_x86_64.whl (1.3 MB)
     |████████████████████████████████| 1.3 MB 74.7 MB/s 
Collecting h5py<2.11.0,>=2.10.0
  Downloading h5py-2.10.0-cp37-cp37m-manylinux1_x86_64.whl (2.9 MB)
     |████████████████████████████████| 2.9 MB 55.4 MB/s 
Collecting grpcio>=1.8.6
  Downloading grpcio-1.33.2-cp37-cp37m-manylinux2014_x86_64.whl (3.8 MB)
     |████████████████████████████████| 3.8 MB 51.3 MB/s 
Collecting absl-py>=0.7.0
  Downloading absl_py-0.11.0-py3-none-any.whl (127 kB)
     |████████████████████████████████| 127 kB 58.4 MB/s 
Collecting keras-preprocessing<1.2,>=1.1.1
  Downloading Keras_Preprocessing-1.1.2-py2.py3-none-any.whl (42 kB)
     |████████████████████████████████| 42 kB 3.0 MB/s 
Collecting werkzeug>=0.11.15
  Downloading Werkzeug-1.0.1-py2.py3-none-any.whl (298 kB)
     |████████████████████████████████| 298 kB 56.9 MB/s 
Requirement already satisfied: requests<3,>=2.21.0 in /opt/venv/lib/python3.7/site-packages (from tensorboard<3,>=2.3.0->tensorflow) (2.24.0)
Collecting google-auth<2,>=1.6.3
  Downloading google_auth-1.23.0-py2.py3-none-any.whl (114 kB)
     |████████████████████████████████| 114 kB 62.2 MB/s 
Collecting tensorboard-plugin-wit>=1.6.0
  Downloading tensorboard_plugin_wit-1.7.0-py3-none-any.whl (779 kB)
     |████████████████████████████████| 779 kB 63.2 MB/s 
Collecting google-auth-oauthlib<0.5,>=0.4.1
  Downloading google_auth_oauthlib-0.4.2-py2.py3-none-any.whl (18 kB)
Collecting markdown>=2.6.8
  Downloading Markdown-3.3.3-py3-none-any.whl (96 kB)
     |████████████████████████████████| 96 kB 12.0 MB/s 
Requirement already satisfied: setuptools>=41.0.0 in /opt/venv/lib/python3.7/site-packages (from tensorboard<3,>=2.3.0->tensorflow) (50.3.0)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/venv/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard<3,>=2.3.0->tensorflow) (1.25.10)
Requirement already satisfied: certifi>=2017.4.17 in /opt/venv/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard<3,>=2.3.0->tensorflow) (2020.6.20)
Requirement already satisfied: chardet<4,>=3.0.2 in /opt/venv/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard<3,>=2.3.0->tensorflow) (3.0.4)
Requirement already satisfied: idna<3,>=2.5 in /opt/venv/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard<3,>=2.3.0->tensorflow) (2.10)
Collecting rsa<5,>=3.1.4; python_version >= "3.5"
  Downloading rsa-4.6-py3-none-any.whl (47 kB)
     |████████████████████████████████| 47 kB 14.3 MB/s 
Collecting pyasn1-modules>=0.2.1
  Downloading pyasn1_modules-0.2.8-py2.py3-none-any.whl (155 kB)
     |████████████████████████████████| 155 kB 61.3 MB/s 
Collecting cachetools<5.0,>=2.0.0
  Downloading cachetools-4.1.1-py3-none-any.whl (10 kB)
Collecting requests-oauthlib>=0.7.0
  Downloading requests_oauthlib-1.3.0-py2.py3-none-any.whl (23 kB)
Requirement already satisfied: importlib-metadata; python_version < "3.8" in /opt/venv/lib/python3.7/site-packages (from markdown>=2.6.8->tensorboard<3,>=2.3.0->tensorflow) (2.0.0)
Collecting pyasn1>=0.1.3
  Downloading pyasn1-0.4.8-py2.py3-none-any.whl (77 kB)
     |████████████████████████████████| 77 kB 14.0 MB/s 
Collecting oauthlib>=3.0.0
  Downloading oauthlib-3.1.0-py2.py3-none-any.whl (147 kB)
     |████████████████████████████████| 147 kB 91.7 MB/s 
Requirement already satisfied: zipp>=0.5 in /opt/venv/lib/python3.7/site-packages (from importlib-metadata; python_version < "3.8"->markdown>=2.6.8->tensorboard<3,>=2.3.0->tensorflow) (3.3.0)
Building wheels for collected packages: wrapt, termcolor
  Building wheel for wrapt (setup.py) ... done
  Created wheel for wrapt: filename=wrapt-1.12.1-cp37-cp37m-linux_x86_64.whl size=33281 sha256=e00eccdd0471f337c605466a6e3eaddefabcb2ace9e8e1ac44fbd1fa1eb749c4
  Stored in directory: /home/jovyan/.cache/pip/wheels/62/76/4c/aa25851149f3f6d9785f6c869387ad82b3fd37582fa8147ac6
  Building wheel for termcolor (setup.py) ... done
  Created wheel for termcolor: filename=termcolor-1.1.0-py3-none-any.whl size=4830 sha256=5b299331b9e18d8200b867f17502c2cb0cfebe5bb08acd1dc752984d38b72d88
  Stored in directory: /home/jovyan/.cache/pip/wheels/3f/e3/ec/8a8336ff196023622fbcb36de0c5a5c218cbb24111d1d4c7f2
Successfully built wrapt termcolor
Installing collected packages: werkzeug, protobuf, pyasn1, rsa, pyasn1-modules, cachetools, google-auth, grpcio, tensorboard-plugin-wit, oauthlib, requests-oauthlib, google-auth-oauthlib, numpy, markdown, absl-py, tensorboard, google-pasta, wrapt, astunparse, gast, termcolor, opt-einsum, tensorflow-estimator, h5py, keras-preprocessing, tensorflow
  Attempting uninstall: numpy
    Found existing installation: numpy 1.19.2
    Uninstalling numpy-1.19.2:
      Successfully uninstalled numpy-1.19.2
Successfully installed absl-py-0.11.0 astunparse-1.6.3 cachetools-4.1.1 gast-0.3.3 google-auth-1.23.0 google-auth-oauthlib-0.4.2 google-pasta-0.2.0 grpcio-1.33.2 h5py-2.10.0 keras-preprocessing-1.1.2 markdown-3.3.3 numpy-1.18.5 oauthlib-3.1.0 opt-einsum-3.3.0 protobuf-3.13.0 pyasn1-0.4.8 pyasn1-modules-0.2.8 requests-oauthlib-1.3.0 rsa-4.6 tensorboard-2.3.0 tensorboard-plugin-wit-1.7.0 tensorflow-2.3.1 tensorflow-estimator-2.3.0 termcolor-1.1.0 werkzeug-1.0.1 wrapt-1.12.1
WARNING: You are using pip version 20.2.3; however, version 20.2.4 is available.
You should consider upgrading via the '/opt/venv/bin/python -m pip install --upgrade pip' command.

import tensorflow as tf print(tf.__version__)

2.3.1

import tensorflow as tf mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data() x_train = tf.keras.utils.normalize(x_train, axis=1) x_test = tf.keras.utils.normalize(x_test, axis=1)

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz
11493376/11490434 [==============================] - 0s 0us/step

model = tf.keras.models.Sequential() model.add(tf.keras.layers.Flatten()) model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu)) #model.add(tf.keras.layers.Dropout(0.2)) model.add(tf.keras.layers.Dense(10, activation=tf.nn.softmax))

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(x_train, y_train, epochs=30) model.evaluate(x_test, y_test)

Epoch 1/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3124 - accuracy: 0.9137
Epoch 2/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.1463 - accuracy: 0.9569
Epoch 3/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.1007 - accuracy: 0.9701
Epoch 4/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0744 - accuracy: 0.9778
Epoch 5/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0574 - accuracy: 0.9830
Epoch 6/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0455 - accuracy: 0.9868
Epoch 7/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0366 - accuracy: 0.9894
Epoch 8/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0297 - accuracy: 0.9916
Epoch 9/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0230 - accuracy: 0.9939
Epoch 10/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0189 - accuracy: 0.9950
Epoch 11/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0157 - accuracy: 0.9956
Epoch 12/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0120 - accuracy: 0.9971
Epoch 13/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0109 - accuracy: 0.9974
Epoch 14/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0077 - accuracy: 0.9984
Epoch 15/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0071 - accuracy: 0.9982
Epoch 16/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0055 - accuracy: 0.9988
Epoch 17/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0052 - accuracy: 0.9988
Epoch 18/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0043 - accuracy: 0.9991
Epoch 19/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0041 - accuracy: 0.9989
Epoch 20/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0036 - accuracy: 0.9993
Epoch 21/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0030 - accuracy: 0.9992
Epoch 22/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0027 - accuracy: 0.9994
Epoch 23/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0021 - accuracy: 0.9995
Epoch 24/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0027 - accuracy: 0.9994
Epoch 25/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0018 - accuracy: 0.9997
Epoch 26/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0021 - accuracy: 0.9995
Epoch 27/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0024 - accuracy: 0.9992
Epoch 28/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0021 - accuracy: 0.9993
Epoch 29/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0016 - accuracy: 0.9996
Epoch 30/30
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0020 - accuracy: 0.9995
313/313 [==============================] - 0s 1ms/step - loss: 0.1437 - accuracy: 0.9742

import matplotlib.pyplot as plt

plt.figure(figsize=(30,18)) for i in range(20): plt.subplot(6,6,i+1) plt.imshow(x_train[i], cmap=plt.cm.binary) plt.xlabel(y_train[i])