From 6cae2b8d934e5ff451a0c38d557e8e6073595c89 Mon Sep 17 00:00:00 2001 From: mhjensen Date: Fri, 9 Oct 2020 07:08:46 +0200 Subject: [PATCH] updating keras --- doc/pub/week41/html/._week41-bs058.html | 9 ++++---- doc/pub/week41/html/._week41-bs059.html | 14 +++++------ doc/pub/week41/html/week41-reveal.html | 23 ++++++++++--------- doc/pub/week41/html/week41-solarized.html | 23 ++++++++++--------- doc/pub/week41/html/week41.html | 23 ++++++++++--------- doc/pub/week41/ipynb/ipynb-week41-src.tar.gz | Bin 87344 -> 87344 bytes doc/pub/week41/ipynb/week41.ipynb | 23 +++++++++---------- doc/src/week41/week41.do.txt | 23 +++++++++---------- 8 files changed, 70 insertions(+), 68 deletions(-) diff --git a/doc/pub/week41/html/._week41-bs058.html b/doc/pub/week41/html/._week41-bs058.html index 95b9f43bf..01583abf7 100644 --- a/doc/pub/week41/html/._week41-bs058.html +++ b/doc/pub/week41/html/._week41-bs058.html @@ -259,15 +259,16 @@ MathJax.Hub.Config({

-

from tensorflow.keras.layers import Input
+
from tensorflow.keras import datasets, layers, models
+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 tensorflow.keras import Conv2D
+#from tensorflow.keras import MaxPooling2D
+#from tensorflow.keras import Flatten
 
 from sklearn.model_selection import train_test_split
 
diff --git a/doc/pub/week41/html/._week41-bs059.html b/doc/pub/week41/html/._week41-bs059.html
index 902beec2a..6e3e83f13 100644
--- a/doc/pub/week41/html/._week41-bs059.html
+++ b/doc/pub/week41/html/._week41-bs059.html
@@ -264,14 +264,14 @@ MathJax.Hub.Config({
                                               n_filters, n_neurons_connected, n_categories,
                                               eta, lmbd):
     model = Sequential()
-    model.add(Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
-              activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(MaxPooling2D(pool_size=(2, 2)))
-    model.add(Flatten())
-    model.add(Dense(n_neurons_connected, activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(Dense(n_categories, activation='softmax', kernel_regularizer=l2(lmbd)))
+    model.add(layers.Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
+              activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
+    model.add(layers.Flatten())
+    model.add(layers.Dense(n_neurons_connected, activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.Dense(n_categories, activation='softmax', kernel_regularizer=regularizers.l2(lmbd)))
     
-    sgd = SGD(lr=eta)
+    sgd = optimizers.SGD(lr=eta)
     model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
     
     return model
diff --git a/doc/pub/week41/html/week41-reveal.html b/doc/pub/week41/html/week41-reveal.html
index bf44b4652..9478fb341 100644
--- a/doc/pub/week41/html/week41-reveal.html
+++ b/doc/pub/week41/html/week41-reveal.html
@@ -2545,15 +2545,16 @@ plt.show()
 

 
 
-
from tensorflow.keras.layers import Input
+
from tensorflow.keras import datasets, layers, models
+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 tensorflow.keras import Conv2D
+#from tensorflow.keras import MaxPooling2D
+#from tensorflow.keras import Flatten
 
 from sklearn.model_selection import train_test_split
 
@@ -2580,14 +2581,14 @@ X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=t
                                               n_filters, n_neurons_connected, n_categories,
                                               eta, lmbd):
     model = Sequential()
-    model.add(Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
-              activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(MaxPooling2D(pool_size=(2, 2)))
-    model.add(Flatten())
-    model.add(Dense(n_neurons_connected, activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(Dense(n_categories, activation='softmax', kernel_regularizer=l2(lmbd)))
+    model.add(layers.Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
+              activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
+    model.add(layers.Flatten())
+    model.add(layers.Dense(n_neurons_connected, activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.Dense(n_categories, activation='softmax', kernel_regularizer=regularizers.l2(lmbd)))
     
-    sgd = SGD(lr=eta)
+    sgd = optimizers.SGD(lr=eta)
     model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
     
     return model
diff --git a/doc/pub/week41/html/week41-solarized.html b/doc/pub/week41/html/week41-solarized.html
index 0673a9412..f0f1314e6 100644
--- a/doc/pub/week41/html/week41-solarized.html
+++ b/doc/pub/week41/html/week41-solarized.html
@@ -2460,15 +2460,16 @@ plt.show()
 

 
 
-
from tensorflow.keras.layers import Input
+
from tensorflow.keras import datasets, layers, models
+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 tensorflow.keras import Conv2D
+#from tensorflow.keras import MaxPooling2D
+#from tensorflow.keras import Flatten
 
 from sklearn.model_selection import train_test_split
 
@@ -2494,14 +2495,14 @@ X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=t
                                               n_filters, n_neurons_connected, n_categories,
                                               eta, lmbd):
     model = Sequential()
-    model.add(Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
-              activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(MaxPooling2D(pool_size=(2, 2)))
-    model.add(Flatten())
-    model.add(Dense(n_neurons_connected, activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(Dense(n_categories, activation='softmax', kernel_regularizer=l2(lmbd)))
+    model.add(layers.Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
+              activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
+    model.add(layers.Flatten())
+    model.add(layers.Dense(n_neurons_connected, activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.Dense(n_categories, activation='softmax', kernel_regularizer=regularizers.l2(lmbd)))
     
-    sgd = SGD(lr=eta)
+    sgd = optimizers.SGD(lr=eta)
     model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
     
     return model
diff --git a/doc/pub/week41/html/week41.html b/doc/pub/week41/html/week41.html
index 6f9dc016d..1ae3109c6 100644
--- a/doc/pub/week41/html/week41.html
+++ b/doc/pub/week41/html/week41.html
@@ -2465,15 +2465,16 @@ plt.show()
 

 
 
-
from tensorflow.keras.layers import Input
+
from tensorflow.keras import datasets, layers, models
+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 tensorflow.keras import Conv2D
+#from tensorflow.keras import MaxPooling2D
+#from tensorflow.keras import Flatten
 
 from sklearn.model_selection import train_test_split
 
@@ -2499,14 +2500,14 @@ X_train, X_test, Y_train, Y_test = train_tes
                                               n_filters, n_neurons_connected, n_categories,
                                               eta, lmbd):
     model = Sequential()
-    model.add(Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
-              activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(MaxPooling2D(pool_size=(2, 2)))
-    model.add(Flatten())
-    model.add(Dense(n_neurons_connected, activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(Dense(n_categories, activation='softmax', kernel_regularizer=l2(lmbd)))
+    model.add(layers.Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
+              activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
+    model.add(layers.Flatten())
+    model.add(layers.Dense(n_neurons_connected, activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.Dense(n_categories, activation='softmax', kernel_regularizer=regularizers.l2(lmbd)))
     
-    sgd = SGD(lr=eta)
+    sgd = optimizers.SGD(lr=eta)
     model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
     
     return model
diff --git a/doc/pub/week41/ipynb/ipynb-week41-src.tar.gz b/doc/pub/week41/ipynb/ipynb-week41-src.tar.gz
index a6271cad596a885cf647ba71aae85467082416e4..897ca035886d41799bb6db2357e4668ccb6549f6 100644
GIT binary patch
delta 20
bcmdn6igm*(RyO%=4u-G~jci-l7_~wHOsEEb

delta 20
ccmdn6igm*(RyO%=4u;)t8rin8F=~YZ08kYM-~a#s

diff --git a/doc/pub/week41/ipynb/week41.ipynb b/doc/pub/week41/ipynb/week41.ipynb
index 446285be2..eda8793b1 100644
--- a/doc/pub/week41/ipynb/week41.ipynb
+++ b/doc/pub/week41/ipynb/week41.ipynb
@@ -2460,15 +2460,16 @@
    },
    "outputs": [],
    "source": [
+    "from tensorflow.keras import datasets, layers, models\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",
+    "#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",
@@ -2499,20 +2500,18 @@
    },
    "outputs": [],
    "source": [
-    "\n",
-    "\n",
     "def create_convolutional_neural_network_keras(input_shape, receptive_field,\n",
     "                                              n_filters, n_neurons_connected, n_categories,\n",
     "                                              eta, lmbd):\n",
     "    model = Sequential()\n",
-    "    model.add(Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',\n",
-    "              activation='relu', kernel_regularizer=l2(lmbd)))\n",
-    "    model.add(MaxPooling2D(pool_size=(2, 2)))\n",
-    "    model.add(Flatten())\n",
-    "    model.add(Dense(n_neurons_connected, activation='relu', kernel_regularizer=l2(lmbd)))\n",
-    "    model.add(Dense(n_categories, activation='softmax', kernel_regularizer=l2(lmbd)))\n",
+    "    model.add(layers.Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',\n",
+    "              activation='relu', kernel_regularizer=regularizers.l2(lmbd)))\n",
+    "    model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n",
+    "    model.add(layers.Flatten())\n",
+    "    model.add(layers.Dense(n_neurons_connected, activation='relu', kernel_regularizer=regularizers.l2(lmbd)))\n",
+    "    model.add(layers.Dense(n_categories, activation='softmax', kernel_regularizer=regularizers.l2(lmbd)))\n",
     "    \n",
-    "    sgd = SGD(lr=eta)\n",
+    "    sgd = optimizers.SGD(lr=eta)\n",
     "    model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])\n",
     "    \n",
     "    return model\n",
diff --git a/doc/src/week41/week41.do.txt b/doc/src/week41/week41.do.txt
index e055736d5..9eb94a41a 100644
--- a/doc/src/week41/week41.do.txt
+++ b/doc/src/week41/week41.do.txt
@@ -2018,15 +2018,16 @@ plt.show()
 !split
 ===== Importing Keras and Tensorflow =====
 !bc pycod
+from tensorflow.keras import datasets, layers, models
 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 tensorflow.keras import Conv2D
+#from tensorflow.keras import MaxPooling2D
+#from tensorflow.keras import Flatten
 
 from sklearn.model_selection import train_test_split
 
@@ -2045,20 +2046,18 @@ X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=t
 ===== Running with Keras =====
 
 !bc pycod
-
-
 def create_convolutional_neural_network_keras(input_shape, receptive_field,
                                               n_filters, n_neurons_connected, n_categories,
                                               eta, lmbd):
     model = Sequential()
-    model.add(Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
-              activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(MaxPooling2D(pool_size=(2, 2)))
-    model.add(Flatten())
-    model.add(Dense(n_neurons_connected, activation='relu', kernel_regularizer=l2(lmbd)))
-    model.add(Dense(n_categories, activation='softmax', kernel_regularizer=l2(lmbd)))
+    model.add(layers.Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
+              activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.MaxPooling2D(pool_size=(2, 2)))
+    model.add(layers.Flatten())
+    model.add(layers.Dense(n_neurons_connected, activation='relu', kernel_regularizer=regularizers.l2(lmbd)))
+    model.add(layers.Dense(n_categories, activation='softmax', kernel_regularizer=regularizers.l2(lmbd)))
     
-    sgd = SGD(lr=eta)
+    sgd = optimizers.SGD(lr=eta)
     model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
     
     return model