diff --git a/doc/pub/week41/html/._week41-bs028.html b/doc/pub/week41/html/._week41-bs028.html index c333dd65e..f40af878d 100644 --- a/doc/pub/week41/html/._week41-bs028.html +++ b/doc/pub/week41/html/._week41-bs028.html @@ -258,7 +258,6 @@ MathJax.Hub.Config({

Keras is a high level neural network that supports Tensorflow, CTNK and Theano as backends. -If you have Tensorflow installed Keras is available through the tf.keras module. If you have Anaconda installed you may run the following command

@@ -266,15 +265,10 @@ If you have Anaconda installed you may run the following command 

conda install keras

-Alternatively, if you have Tensorflow or one of the other supported backends install you may use the pip package manager: +You can look up the instructions here for more information.

- - -

pip install keras
-
-

-or look up the instructions here. +We will to a large extent use keras in this course.

diff --git a/doc/pub/week41/html/._week41-bs029.html b/doc/pub/week41/html/._week41-bs029.html index f9bfbf306..b3d7c3e88 100644 --- a/doc/pub/week41/html/._week41-bs029.html +++ b/doc/pub/week41/html/._week41-bs029.html @@ -255,6 +255,9 @@ MathJax.Hub.Config({

Collect and pre-process data

+

+Let us look again at the MINST data set. +

@@ -326,7 +329,14 @@ X_train, X_test, Y_train, Y_test = train_tes

-

def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
+
epochs = 100
+batch_size = 100
+n_neurons_layer1 = 100
+n_neurons_layer2 = 50
+n_categories = 10
+eta_vals = np.logspace(-5, 1, 7)
+lmbd_vals = np.logspace(-5, 1, 7)
+def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
     model = Sequential()
     model.add(Dense(n_neurons_layer1, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))
     model.add(Dense(n_neurons_layer2, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))
diff --git a/doc/pub/week41/html/._week41-bs057.html b/doc/pub/week41/html/._week41-bs057.html
index 842615fcd..330870843 100644
--- a/doc/pub/week41/html/._week41-bs057.html
+++ b/doc/pub/week41/html/._week41-bs057.html
@@ -257,7 +257,16 @@ MathJax.Hub.Config({
 

 
 
-
from keras.utils import to_categorical
+
from tensorflow.keras.layers import Input
+from tensorflow.keras.models import Sequential      #This allows appending layers to existing models
+from tensorflow.keras.layers import Dense           #This allows defining the characteristics of a particular layer
+from tensorflow.keras import optimizers             #This allows using whichever optimiser we want (sgd,adam,RMSprop)
+from tensorflow.keras import regularizers           #This allows using whichever regularizer we want (l1,l2,l1_l2)
+from tensorflow.keras.utils import to_categorical   #This allows using categorical cross entropy as the cost function
+from tensorflow.keras import Conv2D
+from tensorflow.keras import MaxPooling2D
+from tensorflow.keras import Flatten
+
 from sklearn.model_selection import train_test_split
 
 # representation of labels
diff --git a/doc/pub/week41/html/._week41-bs058.html b/doc/pub/week41/html/._week41-bs058.html
index bed3fbe8d..b639fd7ad 100644
--- a/doc/pub/week41/html/._week41-bs058.html
+++ b/doc/pub/week41/html/._week41-bs058.html
@@ -258,15 +258,7 @@ MathJax.Hub.Config({
 

 
 
-
from keras.models import Sequential
-from keras.layers.convolutional import Conv2D
-from keras.layers.convolutional import MaxPooling2D
-from keras.layers import Flatten
-from keras.layers import Dense
-from keras.regularizers import l2
-from keras.optimizers import SGD
-
-def create_convolutional_neural_network_keras(input_shape, receptive_field,
+
def create_convolutional_neural_network_keras(input_shape, receptive_field,
                                               n_filters, n_neurons_connected, n_categories,
                                               eta, lmbd):
     model = Sequential()
diff --git a/doc/pub/week41/html/week41-reveal.html b/doc/pub/week41/html/week41-reveal.html
index 7bb99a7c6..0d5daa439 100644
--- a/doc/pub/week41/html/week41-reveal.html
+++ b/doc/pub/week41/html/week41-reveal.html
@@ -1534,7 +1534,6 @@ conda activate tf-gpu
 

 Keras is a high level neural network
 that supports Tensorflow, CTNK and Theano as backends.  
-If you have Tensorflow installed Keras is available through the tf.keras module.  
 If you have Anaconda installed you may run the following command
 

 
@@ -1542,21 +1541,19 @@ If you have Anaconda installed you may run the following command
 
conda install keras
 

 

-Alternatively, if you have Tensorflow or one of the other supported backends install you may use the pip package manager:
+You can look up the instructions here for more information.
 
 

-
-
-
pip install keras
-

-

-or look up the instructions here.
+We will to a large extent use keras in this course.
 
 
 
 

 
Collect and pre-process data 

 
+

+Let us look again at the MINST data set.
+
 

 
 
@@ -1628,7 +1625,14 @@ X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=t
 

 
 
-
def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
+
epochs = 100
+batch_size = 100
+n_neurons_layer1 = 100
+n_neurons_layer2 = 50
+n_categories = 10
+eta_vals = np.logspace(-5, 1, 7)
+lmbd_vals = np.logspace(-5, 1, 7)
+def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
     model = Sequential()
     model.add(Dense(n_neurons_layer1, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))
     model.add(Dense(n_neurons_layer2, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))
@@ -2533,7 +2537,16 @@ plt.show()
 

 
 
-
from keras.utils import to_categorical
+
from tensorflow.keras.layers import Input
+from tensorflow.keras.models import Sequential      #This allows appending layers to existing models
+from tensorflow.keras.layers import Dense           #This allows defining the characteristics of a particular layer
+from tensorflow.keras import optimizers             #This allows using whichever optimiser we want (sgd,adam,RMSprop)
+from tensorflow.keras import regularizers           #This allows using whichever regularizer we want (l1,l2,l1_l2)
+from tensorflow.keras.utils import to_categorical   #This allows using categorical cross entropy as the cost function
+from tensorflow.keras import Conv2D
+from tensorflow.keras import MaxPooling2D
+from tensorflow.keras import Flatten
+
 from sklearn.model_selection import train_test_split
 
 # representation of labels
@@ -2555,15 +2568,7 @@ X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=t
 

 
 
-
from keras.models import Sequential
-from keras.layers.convolutional import Conv2D
-from keras.layers.convolutional import MaxPooling2D
-from keras.layers import Flatten
-from keras.layers import Dense
-from keras.regularizers import l2
-from keras.optimizers import SGD
-
-def create_convolutional_neural_network_keras(input_shape, receptive_field,
+
def create_convolutional_neural_network_keras(input_shape, receptive_field,
                                               n_filters, n_neurons_connected, n_categories,
                                               eta, lmbd):
     model = Sequential()
diff --git a/doc/pub/week41/html/week41-solarized.html b/doc/pub/week41/html/week41-solarized.html
index b0f026995..7e0d7b463 100644
--- a/doc/pub/week41/html/week41-solarized.html
+++ b/doc/pub/week41/html/week41-solarized.html
@@ -1463,7 +1463,6 @@ conda activate tf-gpu
 

 Keras is a high level neural network
 that supports Tensorflow, CTNK and Theano as backends.  
-If you have Tensorflow installed Keras is available through the tf.keras module.  
 If you have Anaconda installed you may run the following command
 

 
@@ -1471,21 +1470,19 @@ If you have Anaconda installed you may run the following command
 
conda install keras
 

 

-Alternatively, if you have Tensorflow or one of the other supported backends install you may use the pip package manager:
+You can look up the instructions here for more information.
 
 

-
-
-
pip install keras
-

-

-or look up the instructions here.
+We will to a large extent use keras in this course.
 
 

 










 
 
Collect and pre-process data 

 
+

+Let us look again at the MINST data set.
+
 

 
 
@@ -1557,7 +1554,14 @@ X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=t
 

 
 
-
def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
+
epochs = 100
+batch_size = 100
+n_neurons_layer1 = 100
+n_neurons_layer2 = 50
+n_categories = 10
+eta_vals = np.logspace(-5, 1, 7)
+lmbd_vals = np.logspace(-5, 1, 7)
+def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
     model = Sequential()
     model.add(Dense(n_neurons_layer1, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))
     model.add(Dense(n_neurons_layer2, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))
@@ -2447,7 +2451,16 @@ plt.show()
 

 
 
-
from keras.utils import to_categorical
+
from tensorflow.keras.layers import Input
+from tensorflow.keras.models import Sequential      #This allows appending layers to existing models
+from tensorflow.keras.layers import Dense           #This allows defining the characteristics of a particular layer
+from tensorflow.keras import optimizers             #This allows using whichever optimiser we want (sgd,adam,RMSprop)
+from tensorflow.keras import regularizers           #This allows using whichever regularizer we want (l1,l2,l1_l2)
+from tensorflow.keras.utils import to_categorical   #This allows using categorical cross entropy as the cost function
+from tensorflow.keras import Conv2D
+from tensorflow.keras import MaxPooling2D
+from tensorflow.keras import Flatten
+
 from sklearn.model_selection import train_test_split
 
 # representation of labels
@@ -2468,15 +2481,7 @@ X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=t
 

 
 
-
from keras.models import Sequential
-from keras.layers.convolutional import Conv2D
-from keras.layers.convolutional import MaxPooling2D
-from keras.layers import Flatten
-from keras.layers import Dense
-from keras.regularizers import l2
-from keras.optimizers import SGD
-
-def create_convolutional_neural_network_keras(input_shape, receptive_field,
+
def create_convolutional_neural_network_keras(input_shape, receptive_field,
                                               n_filters, n_neurons_connected, n_categories,
                                               eta, lmbd):
     model = Sequential()
diff --git a/doc/pub/week41/html/week41.html b/doc/pub/week41/html/week41.html
index 5345112de..bf88efb09 100644
--- a/doc/pub/week41/html/week41.html
+++ b/doc/pub/week41/html/week41.html
@@ -1468,7 +1468,6 @@ conda activate tf-gpu
 

 Keras is a high level neural network
 that supports Tensorflow, CTNK and Theano as backends.  
-If you have Tensorflow installed Keras is available through the tf.keras module.  
 If you have Anaconda installed you may run the following command
 

 
@@ -1476,21 +1475,19 @@ If you have Anaconda installed you may run the following command
 
conda install keras
 

 

-Alternatively, if you have Tensorflow or one of the other supported backends install you may use the pip package manager:
+You can look up the instructions here for more information.
 
 

-
-
-
pip install keras
-

-

-or look up the instructions here.
+We will to a large extent use keras in this course.
 
 

 










 
 
Collect and pre-process data 

 
+

+Let us look again at the MINST data set.
+
 

 
 
@@ -1562,7 +1559,14 @@ X_train, X_test, Y_train, Y_test = train_tes
 

 
 
-
def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
+
epochs = 100
+batch_size = 100
+n_neurons_layer1 = 100
+n_neurons_layer2 = 50
+n_categories = 10
+eta_vals = np.logspace(-5, 1, 7)
+lmbd_vals = np.logspace(-5, 1, 7)
+def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
     model = Sequential()
     model.add(Dense(n_neurons_layer1, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))
     model.add(Dense(n_neurons_layer2, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))
@@ -2452,7 +2456,16 @@ plt.show()
 

 
 
-
from keras.utils import to_categorical
+
from tensorflow.keras.layers import Input
+from tensorflow.keras.models import Sequential      #This allows appending layers to existing models
+from tensorflow.keras.layers import Dense           #This allows defining the characteristics of a particular layer
+from tensorflow.keras import optimizers             #This allows using whichever optimiser we want (sgd,adam,RMSprop)
+from tensorflow.keras import regularizers           #This allows using whichever regularizer we want (l1,l2,l1_l2)
+from tensorflow.keras.utils import to_categorical   #This allows using categorical cross entropy as the cost function
+from tensorflow.keras import Conv2D
+from tensorflow.keras import MaxPooling2D
+from tensorflow.keras import Flatten
+
 from sklearn.model_selection import train_test_split
 
 # representation of labels
@@ -2473,15 +2486,7 @@ X_train, X_test, Y_train, Y_test = train_tes
 

 
 
-
from keras.models import Sequential
-from keras.layers.convolutional import Conv2D
-from keras.layers.convolutional import MaxPooling2D
-from keras.layers import Flatten
-from keras.layers import Dense
-from keras.regularizers import l2
-from keras.optimizers import SGD
-
-def create_convolutional_neural_network_keras(input_shape, receptive_field,
+
def create_convolutional_neural_network_keras(input_shape, receptive_field,
                                               n_filters, n_neurons_connected, n_categories,
                                               eta, lmbd):
     model = Sequential()
diff --git a/doc/pub/week41/ipynb/ipynb-week41-src.tar.gz b/doc/pub/week41/ipynb/ipynb-week41-src.tar.gz
index b7f9e9bde..1fae036bf 100644
Binary files a/doc/pub/week41/ipynb/ipynb-week41-src.tar.gz and b/doc/pub/week41/ipynb/ipynb-week41-src.tar.gz differ
diff --git a/doc/pub/week41/ipynb/week41.ipynb b/doc/pub/week41/ipynb/week41.ipynb
index 1e0483f08..43b741032 100644
--- a/doc/pub/week41/ipynb/week41.ipynb
+++ b/doc/pub/week41/ipynb/week41.ipynb
@@ -1465,7 +1465,6 @@
     "\n",
     "Keras is a high level [neural network](https://en.wikipedia.org/wiki/Application_programming_interface)\n",
     "that supports Tensorflow, CTNK and Theano as backends.  \n",
-    "If you have Tensorflow installed Keras is available through the *tf.keras* module.  \n",
     "If you have Anaconda installed you may run the following command"
    ]
   },
@@ -1484,7 +1483,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Alternatively, if you have Tensorflow or one of the other supported backends install you may use the pip package manager:"
+    "You can look up the [instructions here](https://keras.io/) for more information.\n",
+    "\n",
+    "We will to a large extent use **keras** in this course. \n",
+    "\n",
+    "## Collect and pre-process data\n",
+    "\n",
+    "Let us look again at the MINST data set."
    ]
   },
   {
@@ -1494,27 +1499,6 @@
     "collapsed": false
    },
    "outputs": [],
-   "source": [
-    "pip install keras"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "or look up the [instructions here](https://keras.io/).\n",
-    "\n",
-    "\n",
-    "## Collect and pre-process data"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [],
    "source": [
     "# import necessary packages\n",
     "import numpy as np\n",
@@ -1563,7 +1547,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 17,
    "metadata": {
     "collapsed": false
    },
@@ -1590,13 +1574,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 18,
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
     "\n",
+    "epochs = 100\n",
+    "batch_size = 100\n",
+    "n_neurons_layer1 = 100\n",
+    "n_neurons_layer2 = 50\n",
+    "n_categories = 10\n",
+    "eta_vals = np.logspace(-5, 1, 7)\n",
+    "lmbd_vals = np.logspace(-5, 1, 7)\n",
     "def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):\n",
     "    model = Sequential()\n",
     "    model.add(Dense(n_neurons_layer1, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))\n",
@@ -1611,7 +1602,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 19,
    "metadata": {
     "collapsed": false
    },
@@ -1636,7 +1627,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 20,
    "metadata": {
     "collapsed": false
    },
@@ -1684,7 +1675,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 21,
    "metadata": {
     "collapsed": false
    },
@@ -2400,7 +2391,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 22,
    "metadata": {
     "collapsed": false
    },
@@ -2457,13 +2448,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 23,
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
-    "from keras.utils import to_categorical\n",
+    "from tensorflow.keras.layers import Input\n",
+    "from tensorflow.keras.models import Sequential      #This allows appending layers to existing models\n",
+    "from tensorflow.keras.layers import Dense           #This allows defining the characteristics of a particular layer\n",
+    "from tensorflow.keras import optimizers             #This allows using whichever optimiser we want (sgd,adam,RMSprop)\n",
+    "from tensorflow.keras import regularizers           #This allows using whichever regularizer we want (l1,l2,l1_l2)\n",
+    "from tensorflow.keras.utils import to_categorical   #This allows using categorical cross entropy as the cost function\n",
+    "from tensorflow.keras import Conv2D\n",
+    "from tensorflow.keras import MaxPooling2D\n",
+    "from tensorflow.keras import Flatten\n",
+    "\n",
     "from sklearn.model_selection import train_test_split\n",
     "\n",
     "# representation of labels\n",
@@ -2487,19 +2487,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 24,
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
-    "from keras.models import Sequential\n",
-    "from keras.layers.convolutional import Conv2D\n",
-    "from keras.layers.convolutional import MaxPooling2D\n",
-    "from keras.layers import Flatten\n",
-    "from keras.layers import Dense\n",
-    "from keras.regularizers import l2\n",
-    "from keras.optimizers import SGD\n",
+    "\n",
     "\n",
     "def create_convolutional_neural_network_keras(input_shape, receptive_field,\n",
     "                                              n_filters, n_neurons_connected, n_categories,\n",
@@ -2538,7 +2532,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 25,
    "metadata": {
     "collapsed": false
    },
diff --git a/doc/src/week41/week41.do.txt b/doc/src/week41/week41.do.txt
index 026c7ba06..7cb4a956c 100644
--- a/doc/src/week41/week41.do.txt
+++ b/doc/src/week41/week41.do.txt
@@ -1116,23 +1116,19 @@ conda activate tf-gpu
   
 Keras is a high level "neural network":"https://en.wikipedia.org/wiki/Application_programming_interface"
 that supports Tensorflow, CTNK and Theano as backends.  
-If you have Tensorflow installed Keras is available through the *tf.keras* module.  
 If you have Anaconda installed you may run the following command
 !bc pycod
 conda install keras
 !ec
-  
-Alternatively, if you have Tensorflow or one of the other supported backends install you may use the pip package manager: 
-
-!bc pycod
-pip install keras
-!ec
-or look up the "instructions here":"https://keras.io/".
+You can look up the "instructions here":"https://keras.io/" for more information.
 
+We will to a large extent use _keras_ in this course. 
 
 !split
 ===== Collect and pre-process data =====
 
+Let us look again at the MINST data set.
+
 !bc pycod
 # import necessary packages
 import numpy as np
@@ -1203,6 +1199,13 @@ X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=t
 
 !bc pycod
 
+epochs = 100
+batch_size = 100
+n_neurons_layer1 = 100
+n_neurons_layer2 = 50
+n_categories = 10
+eta_vals = np.logspace(-5, 1, 7)
+lmbd_vals = np.logspace(-5, 1, 7)
 def create_neural_network_keras(n_neurons_layer1, n_neurons_layer2, n_categories, eta, lmbd):
     model = Sequential()
     model.add(Dense(n_neurons_layer1, activation='sigmoid', kernel_regularizer=regularizers.l2(lmbd)))
@@ -2005,7 +2008,16 @@ plt.show()
 !split
 ===== Importing Keras and Tensorflow =====
 !bc pycod
-from keras.utils import to_categorical
+from tensorflow.keras.layers import Input
+from tensorflow.keras.models import Sequential      #This allows appending layers to existing models
+from tensorflow.keras.layers import Dense           #This allows defining the characteristics of a particular layer
+from tensorflow.keras import optimizers             #This allows using whichever optimiser we want (sgd,adam,RMSprop)
+from tensorflow.keras import regularizers           #This allows using whichever regularizer we want (l1,l2,l1_l2)
+from tensorflow.keras.utils import to_categorical   #This allows using categorical cross entropy as the cost function
+from tensorflow.keras import Conv2D
+from tensorflow.keras import MaxPooling2D
+from tensorflow.keras import Flatten
+
 from sklearn.model_selection import train_test_split
 
 # representation of labels
@@ -2023,13 +2035,7 @@ X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=t
 ===== Running with Keras =====
 
 !bc pycod
-from keras.models import Sequential
-from keras.layers.convolutional import Conv2D
-from keras.layers.convolutional import MaxPooling2D
-from keras.layers import Flatten
-from keras.layers import Dense
-from keras.regularizers import l2
-from keras.optimizers import SGD
+
 
 def create_convolutional_neural_network_keras(input_shape, receptive_field,
                                               n_filters, n_neurons_connected, n_categories,