Refactored the code for recommenders and nlp_class2

ann_class2/batch_norm_tf.py

@@ -4,13 +4,15 @@
 # sudo pip install -U future
 
 import numpy as np
-import pandas as pd
+#import pandas as pd
 import matplotlib.pyplot as plt
 import tensorflow as tf
 from sklearn.utils import shuffle
-from sklearn.model_selection import train_test_split
+#from sklearn.model_selection import train_test_split
 from util import get_normalized_data
 
+if tf.__version__.startswith('2'):
+    tf.compat.v1.disable_eager_execution()
 
 def init_weight(M1, M2):
   return np.random.randn(M1, M2) * np.sqrt(2.0 / M1)
@@ -38,13 +40,11 @@ def forward(self, X, is_training, decay=0.9):
     activation = tf.matmul(X, self.W)
     if is_training:
       batch_mean, batch_var = tf.nn.moments(activation, [0])
-      update_running_mean = tf.assign(
-        self.running_mean,
-        self.running_mean * decay + batch_mean * (1 - decay)
+      update_running_mean = self.running_mean.assign(
+      self.running_mean * decay + batch_mean * (1 - decay)
       )
-      update_running_var = tf.assign(
-        self.running_var,
-        self.running_var * decay + batch_var * (1 - decay)
+      update_running_var = self.running_var.assign(
+      self.running_var * decay + batch_var * (1 - decay)
       )
 
       with tf.control_dependencies([update_running_mean, update_running_var]):
@@ -115,8 +115,8 @@ def fit(self, X, Y, Xtest, Ytest, activation=tf.nn.relu, learning_rate=1e-2, epo
     # for train and test (prediction)
 
     # set up theano functions and variables
-    tfX = tf.placeholder(tf.float32, shape=(None, D), name='X')
-    tfY = tf.placeholder(tf.int32, shape=(None,), name='Y')
+    tfX = tf.compat.v1.placeholder(tf.float32, shape=(None, D), name='X')
+    tfY = tf.compat.v1.placeholder(tf.int32, shape=(None,), name='Y')
 
     # for later use
     self.tfX = tfX
@@ -131,7 +131,7 @@ def fit(self, X, Y, Xtest, Ytest, activation=tf.nn.relu, learning_rate=1e-2, epo
     )
     # train_op = tf.train.AdamOptimizer(learning_rate).minimize(cost)
     # train_op = tf.train.RMSPropOptimizer(learning_rate, decay=0.99, momentum=0.9).minimize(cost)
-    train_op = tf.train.MomentumOptimizer(learning_rate, momentum=0.9, use_nesterov=True).minimize(cost)
+    train_op = tf.compat.v1.train.MomentumOptimizer(learning_rate, momentum=0.9, use_nesterov=True).minimize(cost)
     # train_op = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
 
     # for testing
@@ -141,7 +141,7 @@ def fit(self, X, Y, Xtest, Ytest, activation=tf.nn.relu, learning_rate=1e-2, epo
     # accuracy = tf.reduce_mean(1.0*(tfY == tf.argmax(logits, 1)))
 
     # init the variables
-    self.session.run(tf.global_variables_initializer())
+    self.session.run(tf.compat.v1.global_variables_initializer())
 
     n_batches = N // batch_sz
     costs = []
@@ -187,7 +187,7 @@ def main():
 
   ann = ANN([500, 300])
 
-  session = tf.InteractiveSession()
+  session = tf.compat.v1.InteractiveSession()
   ann.set_session(session)
 
   ann.fit(Xtrain, Ytrain, Xtest, Ytest, show_fig=True)

ann_class2/dropout_tensorflow.py

@@ -13,6 +13,8 @@
 from util import get_normalized_data
 from sklearn.utils import shuffle
 
+if tf.__version__.startswith('2'):
+    tf.compat.v1.disable_eager_execution()
 
 class HiddenLayer(object):
     def __init__(self, M1, M2):
@@ -59,8 +61,8 @@ def fit(self, X, Y, Xvalid, Yvalid, lr=1e-4, mu=0.9, decay=0.9, epochs=15, batch
             self.params += h.params
 
         # set up theano functions and variables
-        inputs = tf.placeholder(tf.float32, shape=(None, D), name='inputs')
-        labels = tf.placeholder(tf.int64, shape=(None,), name='labels')
+        inputs = tf.compat.v1.placeholder(tf.float32, shape=(None, D), name='inputs')
+        labels = tf.compat.v1.placeholder(tf.int64, shape=(None,), name='labels')
         logits = self.forward(inputs)
 
         cost = tf.reduce_mean(
@@ -69,7 +71,7 @@ def fit(self, X, Y, Xvalid, Yvalid, lr=1e-4, mu=0.9, decay=0.9, epochs=15, batch
                 labels=labels
             )
         )
-        train_op = tf.train.RMSPropOptimizer(lr, decay=decay, momentum=mu).minimize(cost)
+        train_op = tf.compat.v1.train.RMSPropOptimizer(lr, decay=decay, momentum=mu).minimize(cost)
         # train_op = tf.train.MomentumOptimizer(lr, momentum=mu).minimize(cost)
         # train_op = tf.train.AdamOptimizer(lr).minimize(cost)
         prediction = self.predict(inputs)
@@ -85,8 +87,8 @@ def fit(self, X, Y, Xvalid, Yvalid, lr=1e-4, mu=0.9, decay=0.9, epochs=15, batch
 
         n_batches = N // batch_sz
         costs = []
-        init = tf.global_variables_initializer()
-        with tf.Session() as session:
+        init = tf.compat.v1.global_variables_initializer()
+        with tf.compat.v1.Session() as session:
             session.run(init)
             for i in range(epochs):
                 print("epoch:", i, "n_batches:", n_batches)

ann_class2/keras_functional.py

@@ -5,8 +5,8 @@
 # Note: you may need to update your version of future
 # sudo pip install -U future
 
-from keras.models import Model
-from keras.layers import Dense, Input
+from tensorflow.keras.models import Model #type: ignore
+from tensorflow.keras.layers import Dense, Input #type: ignore
 from util import get_normalized_data, y2indicator
 
 import matplotlib.pyplot as plt

ann_class2/pytorch_batchnorm.py

@@ -37,9 +37,11 @@
 model.add_module("dense1", torch.nn.Linear(D, 500))
 model.add_module("bn1", torch.nn.BatchNorm1d(500))
 model.add_module("relu1", torch.nn.ReLU())
+model.add_module("dropout1", torch.nn.Dropout(p=0.2))
 model.add_module("dense2", torch.nn.Linear(500, 300))
 model.add_module("bn2", torch.nn.BatchNorm1d(300))
 model.add_module("relu2", torch.nn.ReLU())
+model.add_module("dropout2", torch.nn.Dropout(p=0.2))
 model.add_module("dense3", torch.nn.Linear(300, K))
 # Note: no final softmax!
 # just like Tensorflow, it's included in cross-entropy function

ann_class2/tensorflow2.py

@@ -12,11 +12,12 @@
 
 import numpy as np
 import tensorflow as tf
-
 import matplotlib.pyplot as plt
-
 from util import get_normalized_data, y2indicator
 
+if tf.__version__.startswith('2'):
+    tf.compat.v1.disable_eager_execution()
+
 
 def error_rate(p, t):
     return np.mean(p != t)
@@ -31,7 +32,7 @@ def main():
     print_period = 50
 
     lr = 0.00004
-    reg = 0.01
+    #reg = 0.01
 
     Ytrain_ind = y2indicator(Ytrain)
     Ytest_ind = y2indicator(Ytest)
@@ -53,8 +54,8 @@ def main():
 
 
     # define variables and expressions
-    X = tf.placeholder(tf.float32, shape=(None, D), name='X')
-    T = tf.placeholder(tf.float32, shape=(None, K), name='T')
+    X = tf.compat.v1.placeholder(tf.float32, shape=(None, D), name='X')
+    T = tf.compat.v1.placeholder(tf.float32, shape=(None, K), name='T')
     W1 = tf.Variable(W1_init.astype(np.float32))
     b1 = tf.Variable(b1_init.astype(np.float32))
     W2 = tf.Variable(W2_init.astype(np.float32))
@@ -70,19 +71,19 @@ def main():
     # softmax_cross_entropy_with_logits take in the "logits"
     # if you wanted to know the actual output of the neural net,
     # you could pass "Yish" into tf.nn.softmax(logits)
-    cost = tf.reduce_sum(tf.nn.softmax_cross_entropy_with_logits_v2(logits=Yish, labels=T))
+    cost = tf.reduce_sum(tf.nn.softmax_cross_entropy_with_logits(logits=Yish, labels=T))
 
     # we choose the optimizer but don't implement the algorithm ourselves
     # let's go with RMSprop, since we just learned about it.
     # it includes momentum!
-    train_op = tf.train.RMSPropOptimizer(lr, decay=0.99, momentum=0.9).minimize(cost)
+    train_op = tf.compat.v1.train.RMSPropOptimizer(lr, decay=0.99, momentum=0.9).minimize(cost)
 
     # we'll use this to calculate the error rate
     predict_op = tf.argmax(Yish, 1)
 
     costs = []
-    init = tf.global_variables_initializer()
-    with tf.Session() as session:
+    init = tf.compat.v1.global_variables_initializer()
+    with tf.compat.v1.Session() as session:
         session.run(init)
 
         for i in range(max_iter):

ann_class2/util.py

@@ -15,7 +15,7 @@
 import pandas as pd
 import matplotlib.pyplot as plt
 from sklearn.decomposition import PCA
-from sklearn.linear_model import LogisticRegression
+#from sklearn.linear_model import LogisticRegression
 
 
 def get_clouds():
@@ -70,14 +70,14 @@ def get_spiral():
 def get_transformed_data():
     print("Reading in and transforming data...")
 
-    if not os.path.exists('../large_files/train.csv'):
-        print('Looking for ../large_files/train.csv')
+    if not os.path.exists('.\\large_files\\digit-recognizer\\train.csv'):
+        print('Looking for .\\large_files\\digit-recognizer\\train.csv')
         print('You have not downloaded the data and/or not placed the files in the correct location.')
         print('Please get the data from: https://www.kaggle.com/c/digit-recognizer')
         print('Place train.csv in the folder large_files adjacent to the class folder')
         exit()
 
-    df = pd.read_csv('../large_files/train.csv')
+    df = pd.read_csv('.\\large_files\\digit-recognizer\\train.csv')
     data = df.values.astype(np.float32)
     np.random.shuffle(data)
 
@@ -117,14 +117,14 @@ def get_transformed_data():
 def get_normalized_data():
     print("Reading in and transforming data...")
 
-    if not os.path.exists('../large_files/train.csv'):
-        print('Looking for ../large_files/train.csv')
+    if not os.path.exists('.\\large_files\\digit-recognizer\\train.csv'):
+        print('Looking for .\\large_files\\digit-recognizer\\train.csv')
         print('You have not downloaded the data and/or not placed the files in the correct location.')
         print('Please get the data from: https://www.kaggle.com/c/digit-recognizer')
         print('Place train.csv in the folder large_files adjacent to the class folder')
         exit()
 
-    df = pd.read_csv('../large_files/train.csv')
+    df = pd.read_csv('.\\large_files\\digit-recognizer\\train.csv')
     data = df.values.astype(np.float32)
     np.random.shuffle(data)
     X = data[:, 1:]

cnn_class2/class_activation_maps.py

@@ -6,9 +6,9 @@
 # Note: you may need to update your version of future
 # sudo pip install -U future
 
-from keras.models import Model
-from keras.applications.resnet50 import ResNet50, preprocess_input, decode_predictions
-from keras.preprocessing import image
+from tensorflow.keras.models import Model #type: ignore
+from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input, decode_predictions #type: ignore
+from tensorflow.keras.preprocessing import image #type: ignore
 
 import numpy as np
 import scipy as sp
@@ -19,10 +19,10 @@
 
 
 # get the image files
-# http://www.vision.caltech.edu/Image_Datasets/Caltech101/
-# http://www.vision.caltech.edu/Image_Datasets/Caltech256/
-image_files = glob('../large_files/256_ObjectCategories/*/*.jp*g')
-image_files += glob('../large_files/101_ObjectCategories/*/*.jp*g')
+# http://www.vision.caltech.edu/datasets/Caltech101
+# http://www.vision.caltech.edu/datasets/Caltech256/
+image_files = glob('.\\large_files\\256_ObjectCategories\\*\\*.jp*g')
+image_files += glob('.\\large_files\\101_ObjectCategories\\*\\*.jp*g')
 
 
 
@@ -39,13 +39,13 @@
 resnet.summary()
 
 # make a model to get output before flatten
-activation_layer = resnet.get_layer('activation_49')
+activation_layer = resnet.get_layer('conv5_block3_out')
 
 # create a model object
 model = Model(inputs=resnet.input, outputs=activation_layer.output)
 
 # get the feature map weights
-final_dense = resnet.get_layer('fc1000')
+final_dense = resnet.get_layer('predictions')
 W = final_dense.get_weights()[0]
 
 

cnn_class2/make_limited_datasets.py

@@ -10,7 +10,7 @@ def link(src, dst):
   if not os.path.exists(dst):
     os.symlink(src, dst, target_is_directory=True)
 
-mkdir('../large_files/fruits-360-small')
+mkdir('.\\large_files\\fruits-360-small')
 
 
 classes = [
@@ -24,16 +24,16 @@ def link(src, dst):
   'Raspberry'
 ]
 
-train_path_from = os.path.abspath('../large_files/fruits-360/Training')
-valid_path_from = os.path.abspath('../large_files/fruits-360/Validation')
+train_path_from = os.path.abspath('.\\large_files\\fruits-360\\Training')
+valid_path_from = os.path.abspath('\\large_files\\fruits-360\\Validation')
 
-train_path_to = os.path.abspath('../large_files/fruits-360-small/Training')
-valid_path_to = os.path.abspath('../large_files/fruits-360-small/Validation')
+train_path_to = os.path.abspath('.\\large_files\\fruits-360-small\\Training')
+valid_path_to = os.path.abspath('.\\large_files\\fruits-360-small\\Validation')
 
 mkdir(train_path_to)
 mkdir(valid_path_to)
 
 
 for c in classes:
-  link(train_path_from + '/' + c, train_path_to + '/' + c)
-  link(valid_path_from + '/' + c, valid_path_to + '/' + c)
+  link(train_path_from + '\\' + c, train_path_to + '\\' + c)
+  link(valid_path_from + '\\' + c, valid_path_to + '\\' + c)