├── .github
└── ISSUE_TEMPLATE
│ └── feature_request.md
├── 1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning
├── Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning Certificate.pdf
├── Week 1
│ ├── Course 1 Week 1.ipynb
│ ├── Week 1 Quiz.pdf
│ └── Week 1 Quiz.png
├── Week 2
│ ├── Course 1 Week 2.ipynb
│ ├── Week 2 Quiz.pdf
│ └── Week 2 Quiz.png
├── Week 3
│ ├── Course 1 Week 3.ipynb
│ ├── Week 3 Quiz.pdf
│ └── Week 3 Quiz.png
└── Week 4
│ ├── Course 1 Week 4.ipynb
│ ├── Week 4 Quiz.pdf
│ └── Week 4 Quiz.png
├── 2 - Convolutional Neural Networks in TensorFlow
├── Convolutional Neural Networks in TensorFlow Certificate.pdf
├── Week 1
│ ├── Course 2 Week 1.ipynb
│ ├── Week 1 Quiz.pdf
│ └── Week 1 Quiz.png
├── Week 2
│ ├── Course 2 Week 2.ipynb
│ ├── Week 2 Quiz.pdf
│ └── Week 2 Quiz.png
├── Week 3
│ ├── Course 2 Week 3.ipynb
│ ├── Week 3 Quiz.pdf
│ └── Week 3 Quiz.png
└── Week 4
│ ├── Course 2 Week 4.ipynb
│ ├── Week 4 Quiz.pdf
│ └── Week 4 Quiz.png
├── 3 - Natural Langu age Processing in TensorFlow
├── Natural Langu age Processing in TensorFlow.pdf
├── Week 1
│ ├── Course 3 Week 1.ipynb
│ ├── Week 1 Quiz.pdf
│ └── Week 1 Quiz.png
├── Week 2
│ ├── Course 3 Week 2.ipynb
│ ├── Week 2 Quiz.pdf
│ └── Week 2 Quiz.png
├── Week 3
│ ├── Course 3 Week 3.ipynb
│ ├── Week 3 Quiz.pdf
│ └── Week 3 Quiz.png
└── Week 4
│ ├── Course 3 Week 4.ipynb
│ ├── Week 4 Quiz.pdf
│ └── Week 4 Quiz.png
├── 4 - Sequences, Time Series and Prediction
├── Sequ ences, Time Series and Prediction Certificate.pdf
├── Week 1
│ ├── Course 4 Week 1.ipynb
│ ├── Week 1 Quiz.pdf
│ └── Week 1 Quiz.png
├── Week 2
│ ├── Course 4 Week 2.ipynb
│ ├── Week 2 Quiz.pdf
│ └── Week 2 Quiz.png
├── Week 3
│ ├── Course 4 Week 3.ipynb
│ ├── Week 3 Quiz.pdf
│ └── Week 3 Quiz.png
└── Week 4
│ ├── Course 4 Week 4.ipynb
│ ├── Week 4 Quiz.pdf
│ └── Week 4 Quiz.png
├── CODE_OF_CONDUCT.md
├── CONTRIBUTING.md
├── DeepLearning.AI
TensorFlow Developer Professional Certificate.pdf
├── DeepLearning.AI TensorFlow Developer Course Certificate.png
├── LICENSE
└── README.md
/.github/ISSUE_TEMPLATE/feature_request.md:
--------------------------------------------------------------------------------
1 | ---
2 | name: Feature request
3 | about: Suggest an idea for this project
4 | title: ''
5 | labels: ''
6 | assignees: ''
7 |
8 | ---
9 |
10 | **Is your feature request related to a problem? Please describe.**
11 | A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
12 |
13 | **Describe the solution you'd like**
14 | A clear and concise description of what you want to happen.
15 |
16 | **Describe alternatives you've considered**
17 | A clear and concise description of any alternative solutions or features you've considered.
18 |
19 | **Additional context**
20 | Add any other context or screenshots about the feature request here.
21 |
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning Certificate.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning Certificate.pdf
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 1/Week 1 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 1/Week 1 Quiz.pdf
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 1/Week 1 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 1/Week 1 Quiz.png
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 2/Course 1 Week 2.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "Exercise2-Answer.ipynb",
7 | "provenance": [],
8 | "collapsed_sections": []
9 | },
10 | "kernelspec": {
11 | "name": "python3",
12 | "display_name": "Python 3"
13 | }
14 | },
15 | "cells": [
16 | {
17 | "cell_type": "code",
18 | "metadata": {
19 | "id": "rEHcB3kqyHZ6",
20 | "colab_type": "code",
21 | "colab": {}
22 | },
23 | "source": [
24 | "import tensorflow as tf\n",
25 | "\n",
26 | "class myCallback(tf.keras.callbacks.Callback):\n",
27 | " def on_epoch_end(self, epoch, logs={}):\n",
28 | " if(logs.get('acc')>0.99):\n",
29 | " print(\"\\nReached 99% accuracy so cancelling training!\")\n",
30 | " self.model.stop_training = True\n",
31 | "\n",
32 | "mnist = tf.keras.datasets.mnist\n",
33 | "\n",
34 | "(x_train, y_train),(x_test, y_test) = mnist.load_data()\n",
35 | "x_train, x_test = x_train / 255.0, x_test / 255.0\n",
36 | "\n",
37 | "callbacks = myCallback()\n",
38 | "\n",
39 | "model = tf.keras.models.Sequential([\n",
40 | " tf.keras.layers.Flatten(input_shape=(28, 28)),\n",
41 | " tf.keras.layers.Dense(512, activation=tf.nn.relu),\n",
42 | " tf.keras.layers.Dense(10, activation=tf.nn.softmax)\n",
43 | "])\n",
44 | "model.compile(optimizer='adam',\n",
45 | " loss='sparse_categorical_crossentropy',\n",
46 | " metrics=['accuracy'])\n",
47 | "\n",
48 | "model.fit(x_train, y_train, epochs=10, callbacks=[callbacks])"
49 | ],
50 | "execution_count": 0,
51 | "outputs": []
52 | }
53 | ]
54 | }
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 2/Week 2 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 2/Week 2 Quiz.pdf
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 2/Week 2 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 2/Week 2 Quiz.png
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 3/Course 1 Week 3.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "code",
5 | "execution_count": 0,
6 | "metadata": {
7 | "colab": {},
8 | "colab_type": "code",
9 | "id": "22hBZbxx98IS"
10 | },
11 | "outputs": [],
12 | "source": [
13 | "import tensorflow as tf\n",
14 | "\n",
15 | "class myCallback(tf.keras.callbacks.Callback):\n",
16 | " def on_epoch_end(self, epoch, logs={}):\n",
17 | " if(logs.get('acc')>0.998):\n",
18 | " print(\"\\nReached 99.8% accuracy so cancelling training!\")\n",
19 | " self.model.stop_training = True\n",
20 | "\n",
21 | "callbacks = myCallback()\n",
22 | "mnist = tf.keras.datasets.mnist\n",
23 | "(training_images, training_labels), (test_images, test_labels) = mnist.load_data()\n",
24 | "training_images=training_images.reshape(60000, 28, 28, 1)\n",
25 | "training_images=training_images / 255.0\n",
26 | "test_images = test_images.reshape(10000, 28, 28, 1)\n",
27 | "test_images=test_images/255.0\n",
28 | "model = tf.keras.models.Sequential([\n",
29 | " tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(28, 28, 1)),\n",
30 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
31 | " tf.keras.layers.Flatten(),\n",
32 | " tf.keras.layers.Dense(128, activation='relu'),\n",
33 | " tf.keras.layers.Dense(10, activation='softmax')\n",
34 | "])\n",
35 | "model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
36 | "model.fit(training_images, training_labels, epochs=10, callbacks=[callbacks])\n"
37 | ]
38 | }
39 | ],
40 | "metadata": {
41 | "colab": {
42 | "name": "Exercise 2 - Answer.ipynb",
43 | "provenance": []
44 | },
45 | "kernelspec": {
46 | "display_name": "Python 3",
47 | "language": "python",
48 | "name": "python3"
49 | },
50 | "language_info": {
51 | "codemirror_mode": {
52 | "name": "ipython",
53 | "version": 3
54 | },
55 | "file_extension": ".py",
56 | "mimetype": "text/x-python",
57 | "name": "python",
58 | "nbconvert_exporter": "python",
59 | "pygments_lexer": "ipython3",
60 | "version": "3.5.6"
61 | }
62 | },
63 | "nbformat": 4,
64 | "nbformat_minor": 1
65 | }
66 |
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 3/Week 3 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 3/Week 3 Quiz.pdf
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 3/Week 3 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 3/Week 3 Quiz.png
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 4/Course 1 Week 4.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "code",
5 | "execution_count": 0,
6 | "metadata": {
7 | "colab": {},
8 | "colab_type": "code",
9 | "id": "3NFuMFYXtwsT"
10 | },
11 | "outputs": [],
12 | "source": [
13 | "import tensorflow as tf\n",
14 | "import os\n",
15 | "import zipfile\n",
16 | "\n",
17 | "DESIRED_ACCURACY = 0.999\n",
18 | "\n",
19 | "!wget --no-check-certificate \\\n",
20 | " \"https://storage.googleapis.com/laurencemoroney-blog.appspot.com/happy-or-sad.zip\" \\\n",
21 | " -O \"/tmp/happy-or-sad.zip\"\n",
22 | "\n",
23 | "zip_ref = zipfile.ZipFile(\"/tmp/happy-or-sad.zip\", 'r')\n",
24 | "zip_ref.extractall(\"/tmp/h-or-s\")\n",
25 | "zip_ref.close()\n",
26 | "\n",
27 | "class myCallback(tf.keras.callbacks.Callback):\n",
28 | " def on_epoch_end(self, epoch, logs={}):\n",
29 | " if(logs.get('acc')>DESIRED_ACCURACY):\n",
30 | " print(\"\\nReached 99.9% accuracy so cancelling training!\")\n",
31 | " self.model.stop_training = True\n",
32 | "\n",
33 | "callbacks = myCallback()\n"
34 | ]
35 | },
36 | {
37 | "cell_type": "code",
38 | "execution_count": 0,
39 | "metadata": {
40 | "colab": {},
41 | "colab_type": "code",
42 | "id": "eUcNTpra1FK0"
43 | },
44 | "outputs": [],
45 | "source": [
46 | "model = tf.keras.models.Sequential([\n",
47 | " tf.keras.layers.Conv2D(16, (3,3), activation='relu', input_shape=(150, 150, 3)),\n",
48 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
49 | " tf.keras.layers.Conv2D(32, (3,3), activation='relu'),\n",
50 | " tf.keras.layers.MaxPooling2D(2,2),\n",
51 | " tf.keras.layers.Conv2D(32, (3,3), activation='relu'),\n",
52 | " tf.keras.layers.MaxPooling2D(2,2),\n",
53 | " tf.keras.layers.Flatten(),\n",
54 | " tf.keras.layers.Dense(512, activation='relu'),\n",
55 | " tf.keras.layers.Dense(1, activation='sigmoid')\n",
56 | "])\n",
57 | "\n",
58 | "from tensorflow.keras.optimizers import RMSprop\n",
59 | "\n",
60 | "model.compile(loss='binary_crossentropy',\n",
61 | " optimizer=RMSprop(lr=0.001),\n",
62 | " metrics=['acc'])"
63 | ]
64 | },
65 | {
66 | "cell_type": "code",
67 | "execution_count": 0,
68 | "metadata": {
69 | "colab": {},
70 | "colab_type": "code",
71 | "id": "sSaPPUe_z_OU"
72 | },
73 | "outputs": [],
74 | "source": [
75 | "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
76 | "\n",
77 | "train_datagen = ImageDataGenerator(rescale=1/255)\n",
78 | "\n",
79 | "train_generator = train_datagen.flow_from_directory(\n",
80 | " \"/tmp/h-or-s\", \n",
81 | " target_size=(150, 150), \n",
82 | " batch_size=10,\n",
83 | " class_mode='binary')\n",
84 | "\n",
85 | "# Expected output: 'Found 80 images belonging to 2 classes'"
86 | ]
87 | },
88 | {
89 | "cell_type": "code",
90 | "execution_count": 0,
91 | "metadata": {
92 | "colab": {},
93 | "colab_type": "code",
94 | "id": "0imravDn0Ajz"
95 | },
96 | "outputs": [],
97 | "source": [
98 | "history = model.fit_generator(\n",
99 | " train_generator,\n",
100 | " steps_per_epoch=2, \n",
101 | " epochs=15,\n",
102 | " verbose=1,\n",
103 | " callbacks=[callbacks])"
104 | ]
105 | }
106 | ],
107 | "metadata": {
108 | "accelerator": "GPU",
109 | "colab": {
110 | "name": "Exercise4-Answer.ipynb",
111 | "provenance": []
112 | },
113 | "kernelspec": {
114 | "display_name": "Python 3",
115 | "language": "python",
116 | "name": "python3"
117 | },
118 | "language_info": {
119 | "codemirror_mode": {
120 | "name": "ipython",
121 | "version": 3
122 | },
123 | "file_extension": ".py",
124 | "mimetype": "text/x-python",
125 | "name": "python",
126 | "nbconvert_exporter": "python",
127 | "pygments_lexer": "ipython3",
128 | "version": "3.5.6"
129 | }
130 | },
131 | "nbformat": 4,
132 | "nbformat_minor": 1
133 | }
134 |
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 4/Week 4 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 4/Week 4 Quiz.pdf
--------------------------------------------------------------------------------
/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 4/Week 4 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/1 - Introduction to TensorFlow for Artificial
Intelligence, Machine Learning, and Deep
Learning/Week 4/Week 4 Quiz.png
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Convolutional Neural Networks in TensorFlow Certificate.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/2 - Convolutional Neural Networks in TensorFlow/Convolutional Neural Networks in TensorFlow Certificate.pdf
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 1/Course 2 Week 1.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "code",
5 | "execution_count": 0,
6 | "metadata": {
7 | "colab": {},
8 | "colab_type": "code",
9 | "id": "dn-6c02VmqiN"
10 | },
11 | "outputs": [],
12 | "source": [
13 | "import os\n",
14 | "import zipfile\n",
15 | "import random\n",
16 | "import tensorflow as tf\n",
17 | "from tensorflow.keras.optimizers import RMSprop\n",
18 | "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
19 | "from shutil import copyfile"
20 | ]
21 | },
22 | {
23 | "cell_type": "code",
24 | "execution_count": 0,
25 | "metadata": {
26 | "colab": {},
27 | "colab_type": "code",
28 | "id": "3sd9dQWa23aj"
29 | },
30 | "outputs": [],
31 | "source": [
32 | "# If the URL doesn't work, visit https://www.microsoft.com/en-us/download/confirmation.aspx?id=54765\n",
33 | "# And right click on the 'Download Manually' link to get a new URL to the dataset\n",
34 | "\n",
35 | "# Note: This is a very large dataset and will take time to download\n",
36 | "\n",
37 | "!wget --no-check-certificate \\\n",
38 | " \"https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip\" \\\n",
39 | " -O \"/tmp/cats-and-dogs.zip\"\n",
40 | "\n",
41 | "local_zip = '/tmp/cats-and-dogs.zip'\n",
42 | "zip_ref = zipfile.ZipFile(local_zip, 'r')\n",
43 | "zip_ref.extractall('/tmp')\n",
44 | "zip_ref.close()\n"
45 | ]
46 | },
47 | {
48 | "cell_type": "code",
49 | "execution_count": 0,
50 | "metadata": {
51 | "colab": {},
52 | "colab_type": "code",
53 | "id": "DM851ZmN28J3"
54 | },
55 | "outputs": [],
56 | "source": [
57 | "print(len(os.listdir('/tmp/PetImages/Cat/')))\n",
58 | "print(len(os.listdir('/tmp/PetImages/Dog/')))\n",
59 | "\n",
60 | "# Expected Output:\n",
61 | "# 12501\n",
62 | "# 12501"
63 | ]
64 | },
65 | {
66 | "cell_type": "code",
67 | "execution_count": 0,
68 | "metadata": {
69 | "colab": {},
70 | "colab_type": "code",
71 | "id": "F-QkLjxpmyK2"
72 | },
73 | "outputs": [],
74 | "source": [
75 | "try:\n",
76 | " os.mkdir('/tmp/cats-v-dogs')\n",
77 | " os.mkdir('/tmp/cats-v-dogs/training')\n",
78 | " os.mkdir('/tmp/cats-v-dogs/testing')\n",
79 | " os.mkdir('/tmp/cats-v-dogs/training/cats')\n",
80 | " os.mkdir('/tmp/cats-v-dogs/training/dogs')\n",
81 | " os.mkdir('/tmp/cats-v-dogs/testing/cats')\n",
82 | " os.mkdir('/tmp/cats-v-dogs/testing/dogs')\n",
83 | "except OSError:\n",
84 | " pass"
85 | ]
86 | },
87 | {
88 | "cell_type": "code",
89 | "execution_count": 0,
90 | "metadata": {
91 | "colab": {},
92 | "colab_type": "code",
93 | "id": "zvSODo0f9LaU"
94 | },
95 | "outputs": [],
96 | "source": [
97 | "def split_data(SOURCE, TRAINING, TESTING, SPLIT_SIZE):\n",
98 | " files = []\n",
99 | " for filename in os.listdir(SOURCE):\n",
100 | " file = SOURCE + filename\n",
101 | " if os.path.getsize(file) > 0:\n",
102 | " files.append(filename)\n",
103 | " else:\n",
104 | " print(filename + \" is zero length, so ignoring.\")\n",
105 | "\n",
106 | " training_length = int(len(files) * SPLIT_SIZE)\n",
107 | " testing_length = int(len(files) - training_length)\n",
108 | " shuffled_set = random.sample(files, len(files))\n",
109 | " training_set = shuffled_set[0:training_length]\n",
110 | " testing_set = shuffled_set[-testing_length:]\n",
111 | "\n",
112 | " for filename in training_set:\n",
113 | " this_file = SOURCE + filename\n",
114 | " destination = TRAINING + filename\n",
115 | " copyfile(this_file, destination)\n",
116 | "\n",
117 | " for filename in testing_set:\n",
118 | " this_file = SOURCE + filename\n",
119 | " destination = TESTING + filename\n",
120 | " copyfile(this_file, destination)\n",
121 | "\n",
122 | "\n",
123 | "CAT_SOURCE_DIR = \"/tmp/PetImages/Cat/\"\n",
124 | "TRAINING_CATS_DIR = \"/tmp/cats-v-dogs/training/cats/\"\n",
125 | "TESTING_CATS_DIR = \"/tmp/cats-v-dogs/testing/cats/\"\n",
126 | "DOG_SOURCE_DIR = \"/tmp/PetImages/Dog/\"\n",
127 | "TRAINING_DOGS_DIR = \"/tmp/cats-v-dogs/training/dogs/\"\n",
128 | "TESTING_DOGS_DIR = \"/tmp/cats-v-dogs/testing/dogs/\"\n",
129 | "\n",
130 | "split_size = .9\n",
131 | "split_data(CAT_SOURCE_DIR, TRAINING_CATS_DIR, TESTING_CATS_DIR, split_size)\n",
132 | "split_data(DOG_SOURCE_DIR, TRAINING_DOGS_DIR, TESTING_DOGS_DIR, split_size)\n",
133 | "\n",
134 | "# Expected output\n",
135 | "# 666.jpg is zero length, so ignoring\n",
136 | "# 11702.jpg is zero length, so ignoring"
137 | ]
138 | },
139 | {
140 | "cell_type": "code",
141 | "execution_count": 0,
142 | "metadata": {
143 | "colab": {},
144 | "colab_type": "code",
145 | "id": "hwHXFhVG3786"
146 | },
147 | "outputs": [],
148 | "source": [
149 | "print(len(os.listdir('/tmp/cats-v-dogs/training/cats/')))\n",
150 | "print(len(os.listdir('/tmp/cats-v-dogs/training/dogs/')))\n",
151 | "print(len(os.listdir('/tmp/cats-v-dogs/testing/cats/')))\n",
152 | "print(len(os.listdir('/tmp/cats-v-dogs/testing/dogs/')))\n",
153 | "\n",
154 | "# Expected output:\n",
155 | "# 11250\n",
156 | "# 11250\n",
157 | "# 1250\n",
158 | "# 1250"
159 | ]
160 | },
161 | {
162 | "cell_type": "code",
163 | "execution_count": 0,
164 | "metadata": {
165 | "colab": {},
166 | "colab_type": "code",
167 | "id": "-BQrav4anTmj"
168 | },
169 | "outputs": [],
170 | "source": [
171 | "model = tf.keras.models.Sequential([\n",
172 | " tf.keras.layers.Conv2D(16, (3, 3), activation='relu', input_shape=(150, 150, 3)),\n",
173 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
174 | " tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),\n",
175 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
176 | " tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),\n",
177 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
178 | " tf.keras.layers.Flatten(),\n",
179 | " tf.keras.layers.Dense(512, activation='relu'),\n",
180 | " tf.keras.layers.Dense(1, activation='sigmoid')\n",
181 | "])\n",
182 | "\n",
183 | "model.compile(optimizer=RMSprop(lr=0.001), loss='binary_crossentropy', metrics=['acc'])\n"
184 | ]
185 | },
186 | {
187 | "cell_type": "code",
188 | "execution_count": 0,
189 | "metadata": {
190 | "colab": {},
191 | "colab_type": "code",
192 | "id": "fQrZfVgz4j2g"
193 | },
194 | "outputs": [],
195 | "source": [
196 | "\n",
197 | "TRAINING_DIR = \"/tmp/cats-v-dogs/training/\"\n",
198 | "train_datagen = ImageDataGenerator(rescale=1.0/255.)\n",
199 | "train_generator = train_datagen.flow_from_directory(TRAINING_DIR,\n",
200 | " batch_size=100,\n",
201 | " class_mode='binary',\n",
202 | " target_size=(150, 150))\n",
203 | "\n",
204 | "VALIDATION_DIR = \"/tmp/cats-v-dogs/testing/\"\n",
205 | "validation_datagen = ImageDataGenerator(rescale=1.0/255.)\n",
206 | "validation_generator = validation_datagen.flow_from_directory(VALIDATION_DIR,\n",
207 | " batch_size=100,\n",
208 | " class_mode='binary',\n",
209 | " target_size=(150, 150))\n",
210 | "\n",
211 | "# Expected Output:\n",
212 | "# Found 22498 images belonging to 2 classes.\n",
213 | "# Found 2500 images belonging to 2 classes."
214 | ]
215 | },
216 | {
217 | "cell_type": "code",
218 | "execution_count": 0,
219 | "metadata": {
220 | "colab": {},
221 | "colab_type": "code",
222 | "id": "5qE1G6JB4fMn"
223 | },
224 | "outputs": [],
225 | "source": [
226 | "# Note that this may take some time.\n",
227 | "history = model.fit_generator(train_generator,\n",
228 | " epochs=50,\n",
229 | " verbose=1,\n",
230 | " validation_data=validation_generator)"
231 | ]
232 | },
233 | {
234 | "cell_type": "code",
235 | "execution_count": 0,
236 | "metadata": {
237 | "colab": {},
238 | "colab_type": "code",
239 | "id": "MWZrJN4-65RC"
240 | },
241 | "outputs": [],
242 | "source": [
243 | "%matplotlib inline\n",
244 | "\n",
245 | "import matplotlib.image as mpimg\n",
246 | "import matplotlib.pyplot as plt\n",
247 | "\n",
248 | "#-----------------------------------------------------------\n",
249 | "# Retrieve a list of list results on training and test data\n",
250 | "# sets for each training epoch\n",
251 | "#-----------------------------------------------------------\n",
252 | "acc=history.history['acc']\n",
253 | "val_acc=history.history['val_acc']\n",
254 | "loss=history.history['loss']\n",
255 | "val_loss=history.history['val_loss']\n",
256 | "\n",
257 | "epochs=range(len(acc)) # Get number of epochs\n",
258 | "\n",
259 | "#------------------------------------------------\n",
260 | "# Plot training and validation accuracy per epoch\n",
261 | "#------------------------------------------------\n",
262 | "plt.plot(epochs, acc, 'r', \"Training Accuracy\")\n",
263 | "plt.plot(epochs, val_acc, 'b', \"Validation Accuracy\")\n",
264 | "plt.title('Training and validation accuracy')\n",
265 | "plt.figure()\n",
266 | "\n",
267 | "#------------------------------------------------\n",
268 | "# Plot training and validation loss per epoch\n",
269 | "#------------------------------------------------\n",
270 | "plt.plot(epochs, loss, 'r', \"Training Loss\")\n",
271 | "plt.plot(epochs, val_loss, 'b', \"Validation Loss\")\n",
272 | "plt.figure()\n",
273 | "\n",
274 | "\n",
275 | "# Desired output. Charts with training and validation metrics. No crash :)"
276 | ]
277 | },
278 | {
279 | "cell_type": "code",
280 | "execution_count": 0,
281 | "metadata": {
282 | "colab": {},
283 | "colab_type": "code",
284 | "id": "LqL6FYUrtXpf"
285 | },
286 | "outputs": [],
287 | "source": [
288 | "# Here's a codeblock just for fun. You should be able to upload an image here \n",
289 | "# and have it classified without crashing\n",
290 | "import numpy as np\n",
291 | "from google.colab import files\n",
292 | "from keras.preprocessing import image\n",
293 | "\n",
294 | "uploaded = files.upload()\n",
295 | "\n",
296 | "for fn in uploaded.keys():\n",
297 | " \n",
298 | " # predicting images\n",
299 | " path = '/content/' + fn\n",
300 | " img = image.load_img(path, target_size=(150, 150))\n",
301 | " x = image.img_to_array(img)\n",
302 | " x = np.expand_dims(x, axis=0)\n",
303 | "\n",
304 | " images = np.vstack([x])\n",
305 | " classes = model.predict(images, batch_size=10)\n",
306 | " print(classes[0])\n",
307 | " if classes[0]>0.5:\n",
308 | " print(fn + \" is a dog\")\n",
309 | " else:\n",
310 | " print(fn + \" is a cat\")"
311 | ]
312 | }
313 | ],
314 | "metadata": {
315 | "accelerator": "GPU",
316 | "colab": {
317 | "name": "Exercise 5 - Answer.ipynb",
318 | "provenance": []
319 | },
320 | "kernelspec": {
321 | "display_name": "Python 3",
322 | "language": "python",
323 | "name": "python3"
324 | },
325 | "language_info": {
326 | "codemirror_mode": {
327 | "name": "ipython",
328 | "version": 3
329 | },
330 | "file_extension": ".py",
331 | "mimetype": "text/x-python",
332 | "name": "python",
333 | "nbconvert_exporter": "python",
334 | "pygments_lexer": "ipython3",
335 | "version": "3.5.6"
336 | }
337 | },
338 | "nbformat": 4,
339 | "nbformat_minor": 1
340 | }
341 |
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 1/Week 1 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/2 - Convolutional Neural Networks in TensorFlow/Week 1/Week 1 Quiz.pdf
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 1/Week 1 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/2 - Convolutional Neural Networks in TensorFlow/Week 1/Week 1 Quiz.png
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 2/Course 2 Week 2.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "code",
5 | "execution_count": 0,
6 | "metadata": {
7 | "colab": {},
8 | "colab_type": "code",
9 | "id": "dn-6c02VmqiN"
10 | },
11 | "outputs": [],
12 | "source": [
13 | "import os\n",
14 | "import zipfile\n",
15 | "import random\n",
16 | "import tensorflow as tf\n",
17 | "from tensorflow.keras.optimizers import RMSprop\n",
18 | "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
19 | "from shutil import copyfile"
20 | ]
21 | },
22 | {
23 | "cell_type": "code",
24 | "execution_count": 0,
25 | "metadata": {
26 | "colab": {},
27 | "colab_type": "code",
28 | "id": "3sd9dQWa23aj"
29 | },
30 | "outputs": [],
31 | "source": [
32 | "# If the URL doesn't work, visit https://www.microsoft.com/en-us/download/confirmation.aspx?id=54765\n",
33 | "# And right click on the 'Download Manually' link to get a new URL to the dataset\n",
34 | "\n",
35 | "# Note: This is a very large dataset and will take time to download\n",
36 | "\n",
37 | "!wget --no-check-certificate \\\n",
38 | " \"https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip\" \\\n",
39 | " -O \"/tmp/cats-and-dogs.zip\"\n",
40 | "\n",
41 | "local_zip = '/tmp/cats-and-dogs.zip'\n",
42 | "zip_ref = zipfile.ZipFile(local_zip, 'r')\n",
43 | "zip_ref.extractall('/tmp')\n",
44 | "zip_ref.close()\n"
45 | ]
46 | },
47 | {
48 | "cell_type": "code",
49 | "execution_count": 0,
50 | "metadata": {
51 | "colab": {},
52 | "colab_type": "code",
53 | "id": "DM851ZmN28J3"
54 | },
55 | "outputs": [],
56 | "source": [
57 | "print(len(os.listdir('/tmp/PetImages/Cat/')))\n",
58 | "print(len(os.listdir('/tmp/PetImages/Dog/')))\n",
59 | "\n",
60 | "# Expected Output:\n",
61 | "# 12501\n",
62 | "# 12501"
63 | ]
64 | },
65 | {
66 | "cell_type": "code",
67 | "execution_count": 0,
68 | "metadata": {
69 | "colab": {},
70 | "colab_type": "code",
71 | "id": "F-QkLjxpmyK2"
72 | },
73 | "outputs": [],
74 | "source": [
75 | "try:\n",
76 | " os.mkdir('/tmp/cats-v-dogs')\n",
77 | " os.mkdir('/tmp/cats-v-dogs/training')\n",
78 | " os.mkdir('/tmp/cats-v-dogs/testing')\n",
79 | " os.mkdir('/tmp/cats-v-dogs/training/cats')\n",
80 | " os.mkdir('/tmp/cats-v-dogs/training/dogs')\n",
81 | " os.mkdir('/tmp/cats-v-dogs/testing/cats')\n",
82 | " os.mkdir('/tmp/cats-v-dogs/testing/dogs')\n",
83 | "except OSError:\n",
84 | " pass"
85 | ]
86 | },
87 | {
88 | "cell_type": "code",
89 | "execution_count": 0,
90 | "metadata": {
91 | "colab": {},
92 | "colab_type": "code",
93 | "id": "zvSODo0f9LaU"
94 | },
95 | "outputs": [],
96 | "source": [
97 | "def split_data(SOURCE, TRAINING, TESTING, SPLIT_SIZE):\n",
98 | " files = []\n",
99 | " for filename in os.listdir(SOURCE):\n",
100 | " file = SOURCE + filename\n",
101 | " if os.path.getsize(file) > 0:\n",
102 | " files.append(filename)\n",
103 | " else:\n",
104 | " print(filename + \" is zero length, so ignoring.\")\n",
105 | "\n",
106 | " training_length = int(len(files) * SPLIT_SIZE)\n",
107 | " testing_length = int(len(files) - training_length)\n",
108 | " shuffled_set = random.sample(files, len(files))\n",
109 | " training_set = shuffled_set[0:training_length]\n",
110 | " testing_set = shuffled_set[:testing_length]\n",
111 | "\n",
112 | " for filename in training_set:\n",
113 | " this_file = SOURCE + filename\n",
114 | " destination = TRAINING + filename\n",
115 | " copyfile(this_file, destination)\n",
116 | "\n",
117 | " for filename in testing_set:\n",
118 | " this_file = SOURCE + filename\n",
119 | " destination = TESTING + filename\n",
120 | " copyfile(this_file, destination)\n",
121 | "\n",
122 | "\n",
123 | "CAT_SOURCE_DIR = \"/tmp/PetImages/Cat/\"\n",
124 | "TRAINING_CATS_DIR = \"/tmp/cats-v-dogs/training/cats/\"\n",
125 | "TESTING_CATS_DIR = \"/tmp/cats-v-dogs/testing/cats/\"\n",
126 | "DOG_SOURCE_DIR = \"/tmp/PetImages/Dog/\"\n",
127 | "TRAINING_DOGS_DIR = \"/tmp/cats-v-dogs/training/dogs/\"\n",
128 | "TESTING_DOGS_DIR = \"/tmp/cats-v-dogs/testing/dogs/\"\n",
129 | "\n",
130 | "split_size = .9\n",
131 | "split_data(CAT_SOURCE_DIR, TRAINING_CATS_DIR, TESTING_CATS_DIR, split_size)\n",
132 | "split_data(DOG_SOURCE_DIR, TRAINING_DOGS_DIR, TESTING_DOGS_DIR, split_size)\n",
133 | "\n",
134 | "# Expected output\n",
135 | "# 666.jpg is zero length, so ignoring\n",
136 | "# 11702.jpg is zero length, so ignoring"
137 | ]
138 | },
139 | {
140 | "cell_type": "code",
141 | "execution_count": 0,
142 | "metadata": {
143 | "colab": {},
144 | "colab_type": "code",
145 | "id": "hwHXFhVG3786"
146 | },
147 | "outputs": [],
148 | "source": [
149 | "print(len(os.listdir('/tmp/cats-v-dogs/training/cats/')))\n",
150 | "print(len(os.listdir('/tmp/cats-v-dogs/training/dogs/')))\n",
151 | "print(len(os.listdir('/tmp/cats-v-dogs/testing/cats/')))\n",
152 | "print(len(os.listdir('/tmp/cats-v-dogs/testing/dogs/')))\n",
153 | "\n",
154 | "# Expected output:\n",
155 | "# 11250\n",
156 | "# 11250\n",
157 | "# 1250\n",
158 | "# 1250"
159 | ]
160 | },
161 | {
162 | "cell_type": "code",
163 | "execution_count": 0,
164 | "metadata": {
165 | "colab": {},
166 | "colab_type": "code",
167 | "id": "-BQrav4anTmj"
168 | },
169 | "outputs": [],
170 | "source": [
171 | "model = tf.keras.models.Sequential([\n",
172 | " tf.keras.layers.Conv2D(16, (3, 3), activation='relu', input_shape=(150, 150, 3)),\n",
173 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
174 | " tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),\n",
175 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
176 | " tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),\n",
177 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
178 | " tf.keras.layers.Flatten(),\n",
179 | " tf.keras.layers.Dense(512, activation='relu'),\n",
180 | " tf.keras.layers.Dense(1, activation='sigmoid')\n",
181 | "])\n",
182 | "\n",
183 | "model.compile(optimizer=RMSprop(lr=0.001), loss='binary_crossentropy', metrics=['acc'])\n"
184 | ]
185 | },
186 | {
187 | "cell_type": "code",
188 | "execution_count": 0,
189 | "metadata": {
190 | "colab": {},
191 | "colab_type": "code",
192 | "id": "fQrZfVgz4j2g"
193 | },
194 | "outputs": [],
195 | "source": [
196 | "\n",
197 | "TRAINING_DIR = \"/tmp/cats-v-dogs/training/\"\n",
198 | "# Experiment with your own parameters here to really try to drive it to 99.9% accuracy or better\n",
199 | "train_datagen = ImageDataGenerator(rescale=1./255,\n",
200 | " rotation_range=40,\n",
201 | " width_shift_range=0.2,\n",
202 | " height_shift_range=0.2,\n",
203 | " shear_range=0.2,\n",
204 | " zoom_range=0.2,\n",
205 | " horizontal_flip=True,\n",
206 | " fill_mode='nearest')\n",
207 | "train_generator = train_datagen.flow_from_directory(TRAINING_DIR,\n",
208 | " batch_size=100,\n",
209 | " class_mode='binary',\n",
210 | " target_size=(150, 150))\n",
211 | "\n",
212 | "VALIDATION_DIR = \"/tmp/cats-v-dogs/testing/\"\n",
213 | "# Experiment with your own parameters here to really try to drive it to 99.9% accuracy or better\n",
214 | "validation_datagen = ImageDataGenerator(rescale=1./255,\n",
215 | " rotation_range=40,\n",
216 | " width_shift_range=0.2,\n",
217 | " height_shift_range=0.2,\n",
218 | " shear_range=0.2,\n",
219 | " zoom_range=0.2,\n",
220 | " horizontal_flip=True,\n",
221 | " fill_mode='nearest')\n",
222 | "validation_generator = validation_datagen.flow_from_directory(VALIDATION_DIR,\n",
223 | " batch_size=100,\n",
224 | " class_mode='binary',\n",
225 | " target_size=(150, 150))\n",
226 | "\n",
227 | "# Expected Output:\n",
228 | "# Found 22498 images belonging to 2 classes.\n",
229 | "# Found 2500 images belonging to 2 classes."
230 | ]
231 | },
232 | {
233 | "cell_type": "code",
234 | "execution_count": 0,
235 | "metadata": {
236 | "colab": {},
237 | "colab_type": "code",
238 | "id": "5qE1G6JB4fMn"
239 | },
240 | "outputs": [],
241 | "source": [
242 | "# Note that this may take some time.\n",
243 | "history = model.fit_generator(train_generator,\n",
244 | " epochs=15,\n",
245 | " verbose=1,\n",
246 | " validation_data=validation_generator)"
247 | ]
248 | },
249 | {
250 | "cell_type": "code",
251 | "execution_count": 0,
252 | "metadata": {
253 | "colab": {},
254 | "colab_type": "code",
255 | "id": "MWZrJN4-65RC"
256 | },
257 | "outputs": [],
258 | "source": [
259 | "%matplotlib inline\n",
260 | "\n",
261 | "import matplotlib.image as mpimg\n",
262 | "import matplotlib.pyplot as plt\n",
263 | "\n",
264 | "#-----------------------------------------------------------\n",
265 | "# Retrieve a list of list results on training and test data\n",
266 | "# sets for each training epoch\n",
267 | "#-----------------------------------------------------------\n",
268 | "acc=history.history['acc']\n",
269 | "val_acc=history.history['val_acc']\n",
270 | "loss=history.history['loss']\n",
271 | "val_loss=history.history['val_loss']\n",
272 | "\n",
273 | "epochs=range(len(acc)) # Get number of epochs\n",
274 | "\n",
275 | "#------------------------------------------------\n",
276 | "# Plot training and validation accuracy per epoch\n",
277 | "#------------------------------------------------\n",
278 | "plt.plot(epochs, acc, 'r', \"Training Accuracy\")\n",
279 | "plt.plot(epochs, val_acc, 'b', \"Validation Accuracy\")\n",
280 | "plt.title('Training and validation accuracy')\n",
281 | "plt.figure()\n",
282 | "\n",
283 | "#------------------------------------------------\n",
284 | "# Plot training and validation loss per epoch\n",
285 | "#------------------------------------------------\n",
286 | "plt.plot(epochs, loss, 'r', \"Training Loss\")\n",
287 | "plt.plot(epochs, val_loss, 'b', \"Validation Loss\")\n",
288 | "plt.figure()\n",
289 | "\n",
290 | "\n",
291 | "# Desired output. Charts with training and validation metrics. No crash :)"
292 | ]
293 | },
294 | {
295 | "cell_type": "code",
296 | "execution_count": 0,
297 | "metadata": {
298 | "colab": {},
299 | "colab_type": "code",
300 | "id": "LqL6FYUrtXpf"
301 | },
302 | "outputs": [],
303 | "source": [
304 | "# Here's a codeblock just for fun. You should be able to upload an image here \n",
305 | "# and have it classified without crashing\n",
306 | "import numpy as np\n",
307 | "from google.colab import files\n",
308 | "from keras.preprocessing import image\n",
309 | "\n",
310 | "uploaded = files.upload()\n",
311 | "\n",
312 | "for fn in uploaded.keys():\n",
313 | " \n",
314 | " # predicting images\n",
315 | " path = '/content/' + fn\n",
316 | " img = image.load_img(path, target_size=(150, 150))\n",
317 | " x = image.img_to_array(img)\n",
318 | " x = np.expand_dims(x, axis=0)\n",
319 | "\n",
320 | " images = np.vstack([x])\n",
321 | " classes = model.predict(images, batch_size=10)\n",
322 | " print(classes[0])\n",
323 | " if classes[0]>0.5:\n",
324 | " print(fn + \" is a dog\")\n",
325 | " else:\n",
326 | " print(fn + \" is a cat\")"
327 | ]
328 | }
329 | ],
330 | "metadata": {
331 | "accelerator": "GPU",
332 | "colab": {
333 | "name": "Exercise 6 - Answer.ipynb",
334 | "provenance": []
335 | },
336 | "kernelspec": {
337 | "display_name": "Python 3",
338 | "language": "python",
339 | "name": "python3"
340 | },
341 | "language_info": {
342 | "codemirror_mode": {
343 | "name": "ipython",
344 | "version": 3
345 | },
346 | "file_extension": ".py",
347 | "mimetype": "text/x-python",
348 | "name": "python",
349 | "nbconvert_exporter": "python",
350 | "pygments_lexer": "ipython3",
351 | "version": "3.5.6"
352 | }
353 | },
354 | "nbformat": 4,
355 | "nbformat_minor": 1
356 | }
357 |
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 2/Week 2 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/2 - Convolutional Neural Networks in TensorFlow/Week 2/Week 2 Quiz.pdf
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 2/Week 2 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/2 - Convolutional Neural Networks in TensorFlow/Week 2/Week 2 Quiz.png
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 3/Week 3 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/2 - Convolutional Neural Networks in TensorFlow/Week 3/Week 3 Quiz.pdf
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 3/Week 3 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/2 - Convolutional Neural Networks in TensorFlow/Week 3/Week 3 Quiz.png
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 4/Course 2 Week 4.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "code",
5 | "execution_count": 0,
6 | "metadata": {
7 | "colab": {},
8 | "colab_type": "code",
9 | "id": "wYtuKeK0dImp"
10 | },
11 | "outputs": [],
12 | "source": [
13 | "import csv\n",
14 | "import numpy as np\n",
15 | "import tensorflow as tf\n",
16 | "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
17 | "from google.colab import files"
18 | ]
19 | },
20 | {
21 | "cell_type": "markdown",
22 | "metadata": {
23 | "colab_type": "text",
24 | "id": "EmMyh9_mkDHF"
25 | },
26 | "source": [
27 | "The data for this exercise is available at: https://www.kaggle.com/datamunge/sign-language-mnist/home\n",
28 | "\n",
29 | "Sign up and download to find 2 CSV files: sign_mnist_test.csv and sign_mnist_train.csv -- You will upload both of them using this button before you can continue.\n"
30 | ]
31 | },
32 | {
33 | "cell_type": "code",
34 | "execution_count": 0,
35 | "metadata": {
36 | "colab": {
37 | "height": 106
38 | },
39 | "colab_type": "code",
40 | "id": "IcLOZlnnc_N7",
41 | "outputId": "f902689f-06ab-422b-a15d-ceee438a19cb"
42 | },
43 | "outputs": [
44 | {
45 | "data": {
46 | "text/html": [
47 | "\n",
48 | " \n",
49 | " \n",
53 | " "
54 | ],
55 | "text/plain": [
56 | ""
57 | ]
58 | },
59 | "metadata": {
60 | "tags": []
61 | },
62 | "output_type": "display_data"
63 | },
64 | {
65 | "name": "stdout",
66 | "output_type": "stream",
67 | "text": [
68 | "Saving sign_mnist_test.csv to sign_mnist_test.csv\n",
69 | "Saving sign_mnist_train.csv to sign_mnist_train.csv\n"
70 | ]
71 | }
72 | ],
73 | "source": [
74 | "uploaded=files.upload()"
75 | ]
76 | },
77 | {
78 | "cell_type": "code",
79 | "execution_count": 0,
80 | "metadata": {
81 | "colab": {
82 | "height": 86
83 | },
84 | "colab_type": "code",
85 | "id": "4kxw-_rmcnVu",
86 | "outputId": "3d62714a-acc3-4aef-98ec-10fee8e7ab50"
87 | },
88 | "outputs": [
89 | {
90 | "name": "stdout",
91 | "output_type": "stream",
92 | "text": [
93 | "(27455, 28, 28)\n",
94 | "(27455,)\n",
95 | "(7172, 28, 28)\n",
96 | "(7172,)\n"
97 | ]
98 | }
99 | ],
100 | "source": [
101 | "def get_data(filename):\n",
102 | " with open(filename) as training_file:\n",
103 | " csv_reader = csv.reader(training_file, delimiter=',')\n",
104 | " first_line = True\n",
105 | " temp_images = []\n",
106 | " temp_labels = []\n",
107 | " for row in csv_reader:\n",
108 | " if first_line:\n",
109 | " # print(\"Ignoring first line\")\n",
110 | " first_line = False\n",
111 | " else:\n",
112 | " temp_labels.append(row[0])\n",
113 | " image_data = row[1:785]\n",
114 | " image_data_as_array = np.array_split(image_data, 28)\n",
115 | " temp_images.append(image_data_as_array)\n",
116 | " images = np.array(temp_images).astype('float')\n",
117 | " labels = np.array(temp_labels).astype('float')\n",
118 | " return images, labels\n",
119 | "\n",
120 | "\n",
121 | "training_images, training_labels = get_data('sign_mnist_train.csv')\n",
122 | "testing_images, testing_labels = get_data('sign_mnist_test.csv')\n",
123 | "\n",
124 | "print(training_images.shape)\n",
125 | "print(training_labels.shape)\n",
126 | "print(testing_images.shape)\n",
127 | "print(testing_labels.shape)\n"
128 | ]
129 | },
130 | {
131 | "cell_type": "code",
132 | "execution_count": 0,
133 | "metadata": {
134 | "colab": {
135 | "height": 52
136 | },
137 | "colab_type": "code",
138 | "id": "awoqRpyZdQkD",
139 | "outputId": "a223a6f6-29f2-4f5f-8ccf-80f36d3368d1"
140 | },
141 | "outputs": [
142 | {
143 | "name": "stdout",
144 | "output_type": "stream",
145 | "text": [
146 | "(27455, 28, 28, 1)\n",
147 | "(7172, 28, 28, 1)\n"
148 | ]
149 | }
150 | ],
151 | "source": [
152 | "training_images = np.expand_dims(training_images, axis=3)\n",
153 | "testing_images = np.expand_dims(testing_images, axis=3)\n",
154 | "\n",
155 | "train_datagen = ImageDataGenerator(\n",
156 | " rescale=1. / 255,\n",
157 | " rotation_range=40,\n",
158 | " width_shift_range=0.2,\n",
159 | " height_shift_range=0.2,\n",
160 | " shear_range=0.2,\n",
161 | " zoom_range=0.2,\n",
162 | " horizontal_flip=True,\n",
163 | " fill_mode='nearest')\n",
164 | "\n",
165 | "validation_datagen = ImageDataGenerator(\n",
166 | " rescale=1. / 255)\n",
167 | "\n",
168 | "print(training_images.shape)\n",
169 | "print(testing_images.shape)"
170 | ]
171 | },
172 | {
173 | "cell_type": "code",
174 | "execution_count": 0,
175 | "metadata": {
176 | "colab": {
177 | "height": 570
178 | },
179 | "colab_type": "code",
180 | "id": "Rmb7S32cgRqS",
181 | "outputId": "d1cbfc47-3a0a-4605-f1be-fa968032283d"
182 | },
183 | "outputs": [
184 | {
185 | "name": "stdout",
186 | "output_type": "stream",
187 | "text": [
188 | "Epoch 1/15\n",
189 | "857/857 [==============================] - 21s 24ms/step - loss: 2.8540 - acc: 0.1562 - val_loss: 1.9644 - val_acc: 0.3100\n",
190 | "Epoch 2/15\n",
191 | "857/857 [==============================] - 46s 54ms/step - loss: 2.1131 - acc: 0.2188 - val_loss: 1.5558 - val_acc: 0.4855\n",
192 | "Epoch 3/15\n",
193 | "857/857 [==============================] - 40s 47ms/step - loss: 1.7423 - acc: 0.3438 - val_loss: 1.1643 - val_acc: 0.6115\n",
194 | "Epoch 4/15\n",
195 | "857/857 [==============================] - 30s 35ms/step - loss: 1.4933 - acc: 0.4688 - val_loss: 1.1572 - val_acc: 0.6064\n",
196 | "Epoch 5/15\n",
197 | "857/857 [==============================] - 22s 26ms/step - loss: 1.3521 - acc: 0.7500 - val_loss: 0.8973 - val_acc: 0.7167\n",
198 | "Epoch 6/15\n",
199 | "857/857 [==============================] - 21s 24ms/step - loss: 1.2332 - acc: 0.5625 - val_loss: 0.8082 - val_acc: 0.7200\n",
200 | "Epoch 7/15\n",
201 | "857/857 [==============================] - 44s 51ms/step - loss: 1.1631 - acc: 0.5938 - val_loss: 0.8671 - val_acc: 0.7352\n",
202 | "Epoch 8/15\n",
203 | "857/857 [==============================] - 58s 67ms/step - loss: 1.0857 - acc: 0.7188 - val_loss: 0.7608 - val_acc: 0.7949\n",
204 | "Epoch 9/15\n",
205 | "857/857 [==============================] - 23s 26ms/step - loss: 1.0197 - acc: 0.6562 - val_loss: 0.6978 - val_acc: 0.7674\n",
206 | "Epoch 10/15\n",
207 | "857/857 [==============================] - 28s 33ms/step - loss: 0.9711 - acc: 0.6875 - val_loss: 0.7027 - val_acc: 0.7984\n",
208 | "Epoch 11/15\n",
209 | "857/857 [==============================] - 53s 61ms/step - loss: 0.9076 - acc: 0.5625 - val_loss: 0.5784 - val_acc: 0.8238\n",
210 | "Epoch 12/15\n",
211 | "857/857 [==============================] - 64s 75ms/step - loss: 0.8764 - acc: 0.5938 - val_loss: 0.6079 - val_acc: 0.8133\n",
212 | "Epoch 13/15\n",
213 | "857/857 [==============================] - 28s 33ms/step - loss: 0.8410 - acc: 0.7500 - val_loss: 0.4547 - val_acc: 0.8182\n",
214 | "Epoch 14/15\n",
215 | "857/857 [==============================] - 22s 26ms/step - loss: 0.8045 - acc: 0.5312 - val_loss: 0.2415 - val_acc: 0.8496\n",
216 | "Epoch 15/15\n",
217 | "857/857 [==============================] - 47s 55ms/step - loss: 0.7836 - acc: 0.7188 - val_loss: 0.3857 - val_acc: 0.8425\n",
218 | "7172/7172 [==============================] - 4s 596us/step - loss: 6.9243 - acc: 0.5661\n"
219 | ]
220 | },
221 | {
222 | "data": {
223 | "text/plain": [
224 | "[6.92426086682151, 0.56609035]"
225 | ]
226 | },
227 | "execution_count": 5,
228 | "metadata": {
229 | "tags": []
230 | },
231 | "output_type": "execute_result"
232 | }
233 | ],
234 | "source": [
235 | "model = tf.keras.models.Sequential([\n",
236 | " tf.keras.layers.Conv2D(64, (3, 3), activation='relu', input_shape=(28, 28, 1)),\n",
237 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
238 | " tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),\n",
239 | " tf.keras.layers.MaxPooling2D(2, 2),\n",
240 | " tf.keras.layers.Flatten(),\n",
241 | " tf.keras.layers.Dense(128, activation=tf.nn.relu),\n",
242 | " tf.keras.layers.Dense(26, activation=tf.nn.softmax)])\n",
243 | "\n",
244 | "model.compile(optimizer = tf.train.AdamOptimizer(),\n",
245 | " loss = 'sparse_categorical_crossentropy',\n",
246 | " metrics=['accuracy'])\n",
247 | "\n",
248 | "history = model.fit_generator(train_datagen.flow(training_images, training_labels, batch_size=32),\n",
249 | " steps_per_epoch=len(training_images) / 32,\n",
250 | " epochs=15,\n",
251 | " validation_data=validation_datagen.flow(testing_images, testing_labels, batch_size=32),\n",
252 | " validation_steps=len(testing_images) / 32)\n",
253 | "\n",
254 | "model.evaluate(testing_images, testing_labels)\n"
255 | ]
256 | },
257 | {
258 | "cell_type": "code",
259 | "execution_count": 0,
260 | "metadata": {
261 | "colab": {
262 | "height": 561
263 | },
264 | "colab_type": "code",
265 | "id": "_Q3Zpr46dsij",
266 | "outputId": "fd4001fb-9a21-4192-dbdb-9a2f2174e769"
267 | },
268 | "outputs": [
269 | {
270 | "data": {
271 | "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEQCAYAAABY5nToAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n",
272 | "text/plain": [
273 | ""
274 | ]
275 | },
276 | "metadata": {
277 | "tags": []
278 | },
279 | "output_type": "display_data"
280 | },
281 | {
282 | "data": {
283 | "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEQCAYAAABY5nToAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEMufiEiDWP5ERBr0X+qpJyKRhKK8AAAAAElFTkSuQmCC\n",
284 | "text/plain": [
285 | ""
286 | ]
287 | },
288 | "metadata": {
289 | "tags": []
290 | },
291 | "output_type": "display_data"
292 | }
293 | ],
294 | "source": [
295 | "import matplotlib.pyplot as plt\n",
296 | "acc = history.history['acc']\n",
297 | "val_acc = history.history['val_acc']\n",
298 | "loss = history.history['loss']\n",
299 | "val_loss = history.history['val_loss']\n",
300 | "\n",
301 | "epochs = range(len(acc))\n",
302 | "\n",
303 | "plt.plot(epochs, acc, 'r', label='Training accuracy')\n",
304 | "plt.plot(epochs, val_acc, 'b', label='Validation accuracy')\n",
305 | "plt.title('Training and validation accuracy')\n",
306 | "plt.legend()\n",
307 | "plt.figure()\n",
308 | "\n",
309 | "plt.plot(epochs, loss, 'r', label='Training Loss')\n",
310 | "plt.plot(epochs, val_loss, 'b', label='Validation Loss')\n",
311 | "plt.title('Training and validation loss')\n",
312 | "plt.legend()\n",
313 | "\n",
314 | "plt.show()"
315 | ]
316 | }
317 | ],
318 | "metadata": {
319 | "colab": {
320 | "name": "Exercise 8 - Answer.ipynb",
321 | "provenance": []
322 | },
323 | "kernelspec": {
324 | "display_name": "Python 3",
325 | "language": "python",
326 | "name": "python3"
327 | },
328 | "language_info": {
329 | "codemirror_mode": {
330 | "name": "ipython",
331 | "version": 3
332 | },
333 | "file_extension": ".py",
334 | "mimetype": "text/x-python",
335 | "name": "python",
336 | "nbconvert_exporter": "python",
337 | "pygments_lexer": "ipython3",
338 | "version": "3.5.6"
339 | }
340 | },
341 | "nbformat": 4,
342 | "nbformat_minor": 1
343 | }
344 |
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 4/Week 4 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/2 - Convolutional Neural Networks in TensorFlow/Week 4/Week 4 Quiz.pdf
--------------------------------------------------------------------------------
/2 - Convolutional Neural Networks in TensorFlow/Week 4/Week 4 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/2 - Convolutional Neural Networks in TensorFlow/Week 4/Week 4 Quiz.png
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Natural Langu age Processing in TensorFlow.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/3 - Natural Langu age Processing in TensorFlow/Natural Langu age Processing in TensorFlow.pdf
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 1/Course 3 Week 1.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "Exercise-answer.ipynb",
7 | "provenance": []
8 | },
9 | "kernelspec": {
10 | "name": "python3",
11 | "display_name": "Python 3"
12 | }
13 | },
14 | "cells": [
15 | {
16 | "cell_type": "code",
17 | "metadata": {
18 | "id": "zrZevCPJ92HG",
19 | "colab_type": "code",
20 | "colab": {}
21 | },
22 | "source": [
23 | "!wget --no-check-certificate \\\n",
24 | " https://storage.googleapis.com/laurencemoroney-blog.appspot.com/bbc-text.csv \\\n",
25 | " -O /tmp/bbc-text.csv\n",
26 | "\n",
27 | " \n",
28 | "import csv\n",
29 | "from tensorflow.keras.preprocessing.text import Tokenizer\n",
30 | "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
31 | "\n",
32 | "\n",
33 | "\n",
34 | "#Stopwords list from https://github.com/Yoast/YoastSEO.js/blob/develop/src/config/stopwords.js\n",
35 | "stopwords = [ \"a\", \"about\", \"above\", \"after\", \"again\", \"against\", \"all\", \"am\", \"an\", \"and\", \"any\", \"are\", \"as\", \"at\", \"be\", \"because\", \"been\", \"before\", \"being\", \"below\", \"between\", \"both\", \"but\", \"by\", \"could\", \"did\", \"do\", \"does\", \"doing\", \"down\", \"during\", \"each\", \"few\", \"for\", \"from\", \"further\", \"had\", \"has\", \"have\", \"having\", \"he\", \"he'd\", \"he'll\", \"he's\", \"her\", \"here\", \"here's\", \"hers\", \"herself\", \"him\", \"himself\", \"his\", \"how\", \"how's\", \"i\", \"i'd\", \"i'll\", \"i'm\", \"i've\", \"if\", \"in\", \"into\", \"is\", \"it\", \"it's\", \"its\", \"itself\", \"let's\", \"me\", \"more\", \"most\", \"my\", \"myself\", \"nor\", \"of\", \"on\", \"once\", \"only\", \"or\", \"other\", \"ought\", \"our\", \"ours\", \"ourselves\", \"out\", \"over\", \"own\", \"same\", \"she\", \"she'd\", \"she'll\", \"she's\", \"should\", \"so\", \"some\", \"such\", \"than\", \"that\", \"that's\", \"the\", \"their\", \"theirs\", \"them\", \"themselves\", \"then\", \"there\", \"there's\", \"these\", \"they\", \"they'd\", \"they'll\", \"they're\", \"they've\", \"this\", \"those\", \"through\", \"to\", \"too\", \"under\", \"until\", \"up\", \"very\", \"was\", \"we\", \"we'd\", \"we'll\", \"we're\", \"we've\", \"were\", \"what\", \"what's\", \"when\", \"when's\", \"where\", \"where's\", \"which\", \"while\", \"who\", \"who's\", \"whom\", \"why\", \"why's\", \"with\", \"would\", \"you\", \"you'd\", \"you'll\", \"you're\", \"you've\", \"your\", \"yours\", \"yourself\", \"yourselves\" ]\n"
36 | ],
37 | "execution_count": 0,
38 | "outputs": []
39 | },
40 | {
41 | "cell_type": "code",
42 | "metadata": {
43 | "id": "1rmYBjsyCv3K",
44 | "colab_type": "code",
45 | "colab": {}
46 | },
47 | "source": [
48 | "sentences = []\n",
49 | "labels = []\n",
50 | "with open(\"/tmp/bbc-text.csv\", 'r') as csvfile:\n",
51 | " reader = csv.reader(csvfile, delimiter=',')\n",
52 | " next(reader)\n",
53 | " for row in reader:\n",
54 | " labels.append(row[0])\n",
55 | " sentence = row[1]\n",
56 | " for word in stopwords:\n",
57 | " token = \" \" + word + \" \"\n",
58 | " sentence = sentence.replace(token, \" \")\n",
59 | " sentence = sentence.replace(\" \", \" \")\n",
60 | " sentences.append(sentence)\n",
61 | "\n",
62 | "\n",
63 | "print(len(sentences))\n",
64 | "print(sentences[0])\n",
65 | "\n",
66 | "#Expected output\n",
67 | "# 2225\n",
68 | "# tv future hands viewers home theatre systems plasma high-definition tvs digital video recorders moving living room way people watch tv will radically different five years time. according expert panel gathered annual consumer electronics show las vegas discuss new technologies will impact one favourite pastimes. us leading trend programmes content will delivered viewers via home networks cable satellite telecoms companies broadband service providers front rooms portable devices. one talked-about technologies ces digital personal video recorders (dvr pvr). set-top boxes like us s tivo uk s sky+ system allow people record store play pause forward wind tv programmes want. essentially technology allows much personalised tv. also built-in high-definition tv sets big business japan us slower take off europe lack high-definition programming. not can people forward wind adverts can also forget abiding network channel schedules putting together a-la-carte entertainment. us networks cable satellite companies worried means terms advertising revenues well brand identity viewer loyalty channels. although us leads technology moment also concern raised europe particularly growing uptake services like sky+. happens today will see nine months years time uk adam hume bbc broadcast s futurologist told bbc news website. likes bbc no issues lost advertising revenue yet. pressing issue moment commercial uk broadcasters brand loyalty important everyone. will talking content brands rather network brands said tim hanlon brand communications firm starcom mediavest. reality broadband connections anybody can producer content. added: challenge now hard promote programme much choice. means said stacey jolna senior vice president tv guide tv group way people find content want watch simplified tv viewers. means networks us terms channels take leaf google s book search engine future instead scheduler help people find want watch. kind channel model might work younger ipod generation used taking control gadgets play them. might not suit everyone panel recognised. older generations comfortable familiar schedules channel brands know getting. perhaps not want much choice put hands mr hanlon suggested. end kids just diapers pushing buttons already - everything possible available said mr hanlon. ultimately consumer will tell market want. 50 000 new gadgets technologies showcased ces many enhancing tv-watching experience. high-definition tv sets everywhere many new models lcd (liquid crystal display) tvs launched dvr capability built instead external boxes. one example launched show humax s 26-inch lcd tv 80-hour tivo dvr dvd recorder. one us s biggest satellite tv companies directtv even launched branded dvr show 100-hours recording capability instant replay search function. set can pause rewind tv 90 hours. microsoft chief bill gates announced pre-show keynote speech partnership tivo called tivotogo means people can play recorded programmes windows pcs mobile devices. reflect increasing trend freeing multimedia people can watch want want."
69 | ],
70 | "execution_count": 0,
71 | "outputs": []
72 | },
73 | {
74 | "cell_type": "code",
75 | "metadata": {
76 | "id": "9LhzBBgSC3S5",
77 | "colab_type": "code",
78 | "colab": {}
79 | },
80 | "source": [
81 | "tokenizer = Tokenizer(oov_token=\"\")\n",
82 | "tokenizer.fit_on_texts(sentences)\n",
83 | "word_index = tokenizer.word_index\n",
84 | "print(len(word_index))\n",
85 | "# Expected output\n",
86 | "# 29714"
87 | ],
88 | "execution_count": 0,
89 | "outputs": []
90 | },
91 | {
92 | "cell_type": "code",
93 | "metadata": {
94 | "id": "1Gr3dbQfC5VR",
95 | "colab_type": "code",
96 | "colab": {}
97 | },
98 | "source": [
99 | "sequences = tokenizer.texts_to_sequences(sentences)\n",
100 | "padded = pad_sequences(sequences, padding='post')\n",
101 | "print(padded[0])\n",
102 | "print(padded.shape)\n",
103 | "\n",
104 | "# Expected output\n",
105 | "# [ 96 176 1158 ... 0 0 0]\n",
106 | "# (2225, 2442)"
107 | ],
108 | "execution_count": 0,
109 | "outputs": []
110 | },
111 | {
112 | "cell_type": "code",
113 | "metadata": {
114 | "id": "fZufOahzC6yx",
115 | "colab_type": "code",
116 | "colab": {}
117 | },
118 | "source": [
119 | "label_tokenizer = Tokenizer()\n",
120 | "label_tokenizer.fit_on_texts(labels)\n",
121 | "label_word_index = label_tokenizer.word_index\n",
122 | "label_seq = label_tokenizer.texts_to_sequences(labels)\n",
123 | "print(label_seq)\n",
124 | "print(label_word_index)\n",
125 | "# Expected Output\n",
126 | "# [[4], [2], [1], [1], [5], [3], [3], [1], [1], [5], [5], [2], [2], [3], [1], [2], [3], [1], [2], [4], [4], [4], [1], [1], [4], [1], [5], [4], [3], [5], [3], [4], [5], [5], [2], [3], [4], [5], [3], [2], [3], [1], [2], [1], [4], [5], [3], [3], [3], [2], [1], [3], [2], [2], [1], [3], [2], [1], [1], [2], [2], [1], [2], [1], [2], [4], [2], [5], [4], [2], [3], [2], [3], [1], [2], [4], [2], [1], [1], [2], [2], [1], [3], [2], [5], [3], [3], [2], [5], [2], [1], [1], [3], [1], [3], [1], [2], [1], [2], [5], [5], [1], [2], [3], [3], [4], [1], [5], [1], [4], [2], [5], [1], [5], [1], [5], [5], [3], [1], [1], [5], [3], [2], [4], [2], [2], [4], [1], [3], [1], [4], [5], [1], [2], [2], [4], [5], [4], [1], [2], [2], [2], [4], [1], [4], [2], [1], [5], [1], [4], [1], [4], [3], [2], [4], [5], [1], [2], [3], [2], [5], [3], [3], [5], [3], [2], [5], [3], [3], [5], [3], [1], [2], [3], [3], [2], [5], [1], [2], [2], [1], [4], [1], [4], [4], [1], [2], [1], [3], [5], [3], [2], [3], [2], [4], [3], [5], [3], [4], [2], [1], [2], [1], [4], [5], [2], [3], [3], [5], [1], [5], [3], [1], [5], [1], [1], [5], [1], [3], [3], [5], [4], [1], [3], [2], [5], [4], [1], [4], [1], [5], [3], [1], [5], [4], [2], [4], [2], [2], [4], [2], [1], [2], [1], [2], [1], [5], [2], [2], [5], [1], [1], [3], [4], [3], [3], [3], [4], [1], [4], [3], [2], [4], [5], [4], [1], [1], [2], [2], [3], [2], [4], [1], [5], [1], [3], [4], [5], [2], [1], [5], [1], [4], [3], [4], [2], [2], [3], [3], [1], [2], [4], [5], [3], [4], [2], [5], [1], [5], [1], [5], [3], [2], [1], [2], [1], [1], [5], [1], [3], [3], [2], [5], [4], [2], [1], [2], [5], [2], [2], [2], [3], [2], [3], [5], [5], [2], [1], [2], [3], [2], [4], [5], [2], [1], [1], [5], [2], [2], [3], [4], [5], [4], [3], [2], [1], [3], [2], [5], [4], [5], [4], [3], [1], [5], [2], [3], [2], [2], [3], [1], [4], [2], [2], [5], [5], [4], [1], [2], [5], [4], [4], [5], [5], [5], [3], [1], [3], [4], [2], [5], [3], [2], [5], [3], [3], [1], [1], [2], [3], [5], [2], [1], [2], [2], [1], [2], [3], [3], [3], [1], [4], [4], [2], [4], [1], [5], [2], [3], [2], [5], [2], [3], [5], [3], [2], [4], [2], [1], [1], [2], [1], [1], [5], [1], [1], [1], [4], [2], [2], [2], [3], [1], [1], [2], [4], [2], [3], [1], [3], [4], [2], [1], [5], [2], [3], [4], [2], [1], [2], [3], [2], [2], [1], [5], [4], [3], [4], [2], [1], [2], [5], [4], [4], [2], [1], [1], [5], [3], [3], [3], [1], [3], [4], [4], [5], [3], [4], [5], [2], [1], [1], [4], [2], [1], [1], [3], [1], [1], [2], [1], [5], [4], [3], [1], [3], [4], [2], [2], [2], [4], [2], [2], [1], [1], [1], [1], [2], [4], [5], [1], [1], [4], [2], [4], [5], [3], [1], [2], [3], [2], [4], [4], [3], [4], [2], [1], [2], [5], [1], [3], [5], [1], [1], [3], [4], [5], [4], [1], [3], [2], [5], [3], [2], [5], [1], [1], [4], [3], [5], [3], [5], [3], [4], [3], [5], [1], [2], [1], [5], [1], [5], [4], [2], [1], [3], [5], [3], [5], [5], [5], [3], [5], [4], [3], [4], [4], [1], [1], [4], [4], [1], [5], [5], [1], [4], [5], [1], [1], [4], [2], [3], [4], [2], [1], [5], [1], [5], [3], [4], [5], [5], [2], [5], [5], [1], [4], [4], [3], [1], [4], [1], [3], [3], [5], [4], [2], [4], [4], [4], [2], [3], [3], [1], [4], [2], [2], [5], [5], [1], [4], [2], [4], [5], [1], [4], [3], [4], [3], [2], [3], [3], [2], [1], [4], [1], [4], [3], [5], [4], [1], [5], [4], [1], [3], [5], [1], [4], [1], [1], [3], [5], [2], [3], [5], [2], [2], [4], [2], [5], [4], [1], [4], [3], [4], [3], [2], [3], [5], [1], [2], [2], [2], [5], [1], [2], [5], [5], [1], [5], [3], [3], [3], [1], [1], [1], [4], [3], [1], [3], [3], [4], [3], [1], [2], [5], [1], [2], [2], [4], [2], [5], [5], [5], [2], [5], [5], [3], [4], [2], [1], [4], [1], [1], [3], [2], [1], [4], [2], [1], [4], [1], [1], [5], [1], [2], [1], [2], [4], [3], [4], [2], [1], [1], [2], [2], [2], [2], [3], [1], [2], [4], [2], [1], [3], [2], [4], [2], [1], [2], [3], [5], [1], [2], [3], [2], [5], [2], [2], [2], [1], [3], [5], [1], [3], [1], [3], [3], [2], [2], [1], [4], [5], [1], [5], [2], [2], [2], [4], [1], [4], [3], [4], [4], [4], [1], [4], [4], [5], [5], [4], [1], [5], [4], [1], [1], [2], [5], [4], [2], [1], [2], [3], [2], [5], [4], [2], [3], [2], [4], [1], [2], [5], [2], [3], [1], [5], [3], [1], [2], [1], [3], [3], [1], [5], [5], [2], [2], [1], [4], [4], [1], [5], [4], [4], [2], [1], [5], [4], [1], [1], [2], [5], [2], [2], [2], [5], [1], [5], [4], [4], [4], [3], [4], [4], [5], [5], [1], [1], [3], [2], [5], [1], [3], [5], [4], [3], [4], [4], [2], [5], [3], [4], [3], [3], [1], [3], [3], [5], [4], [1], [3], [1], [5], [3], [2], [2], [3], [1], [1], [1], [5], [4], [4], [2], [5], [1], [3], [4], [3], [5], [4], [4], [2], [2], [1], [2], [2], [4], [3], [5], [2], [2], [2], [2], [2], [4], [1], [3], [4], [4], [2], [2], [5], [3], [5], [1], [4], [1], [5], [1], [4], [1], [2], [1], [3], [3], [5], [2], [1], [3], [3], [1], [5], [3], [2], [4], [1], [2], [2], [2], [5], [5], [4], [4], [2], [2], [5], [1], [2], [5], [4], [4], [2], [2], [1], [1], [1], [3], [3], [1], [3], [1], [2], [5], [1], [4], [5], [1], [1], [2], [2], [4], [4], [1], [5], [1], [5], [1], [5], [3], [5], [5], [4], [5], [2], [2], [3], [1], [3], [4], [2], [3], [1], [3], [1], [5], [1], [3], [1], [1], [4], [5], [1], [3], [1], [1], [2], [4], [5], [3], [4], [5], [3], [5], [3], [5], [5], [4], [5], [3], [5], [5], [4], [4], [1], [1], [5], [5], [4], [5], [3], [4], [5], [2], [4], [1], [2], [5], [5], [4], [5], [4], [2], [5], [1], [5], [2], [1], [2], [1], [3], [4], [5], [3], [2], [5], [5], [3], [2], [5], [1], [3], [1], [2], [2], [2], [2], [2], [5], [4], [1], [5], [5], [2], [1], [4], [4], [5], [1], [2], [3], [2], [3], [2], [2], [5], [3], [2], [2], [4], [3], [1], [4], [5], [3], [2], [2], [1], [5], [3], [4], [2], [2], [3], [2], [1], [5], [1], [5], [4], [3], [2], [2], [4], [2], [2], [1], [2], [4], [5], [3], [2], [3], [2], [1], [4], [2], [3], [5], [4], [2], [5], [1], [3], [3], [1], [3], [2], [4], [5], [1], [1], [4], [2], [1], [5], [4], [1], [3], [1], [2], [2], [2], [3], [5], [1], [3], [4], [2], [2], [4], [5], [5], [4], [4], [1], [1], [5], [4], [5], [1], [3], [4], [2], [1], [5], [2], [2], [5], [1], [2], [1], [4], [3], [3], [4], [5], [3], [5], [2], [2], [3], [1], [4], [1], [1], [1], [3], [2], [1], [2], [4], [1], [2], [2], [1], [3], [4], [1], [2], [4], [1], [1], [2], [2], [2], [2], [3], [5], [4], [2], [2], [1], [2], [5], [2], [5], [1], [3], [2], [2], [4], [5], [2], [2], [2], [3], [2], [3], [4], [5], [3], [5], [1], [4], [3], [2], [4], [1], [2], [2], [5], [4], [2], [2], [1], [1], [5], [1], [3], [1], [2], [1], [2], [3], [3], [2], [3], [4], [5], [1], [2], [5], [1], [3], [3], [4], [5], [2], [3], [3], [1], [4], [2], [1], [5], [1], [5], [1], [2], [1], [3], [5], [4], [2], [1], [3], [4], [1], [5], [2], [1], [5], [1], [4], [1], [4], [3], [1], [2], [5], [4], [4], [3], [4], [5], [4], [1], [2], [4], [2], [5], [1], [4], [3], [3], [3], [3], [5], [5], [5], [2], [3], [3], [1], [1], [4], [1], [3], [2], [2], [4], [1], [4], [2], [4], [3], [3], [1], [2], [3], [1], [2], [4], [2], [2], [5], [5], [1], [2], [4], [4], [3], [2], [3], [1], [5], [5], [3], [3], [2], [2], [4], [4], [1], [1], [3], [4], [1], [4], [2], [1], [2], [3], [1], [5], [2], [4], [3], [5], [4], [2], [1], [5], [4], [4], [5], [3], [4], [5], [1], [5], [1], [1], [1], [3], [4], [1], [2], [1], [1], [2], [4], [1], [2], [5], [3], [4], [1], [3], [4], [5], [3], [1], [3], [4], [2], [5], [1], [3], [2], [4], [4], [4], [3], [2], [1], [3], [5], [4], [5], [1], [4], [2], [3], [5], [4], [3], [1], [1], [2], [5], [2], [2], [3], [2], [2], [3], [4], [5], [3], [5], [5], [2], [3], [1], [3], [5], [1], [5], [3], [5], [5], [5], [2], [1], [3], [1], [5], [4], [4], [2], [3], [5], [2], [1], [2], [3], [3], [2], [1], [4], [4], [4], [2], [3], [3], [2], [1], [1], [5], [2], [1], [1], [3], [3], [3], [5], [3], [2], [4], [2], [3], [5], [5], [2], [1], [3], [5], [1], [5], [3], [3], [2], [3], [1], [5], [5], [4], [4], [4], [4], [3], [4], [2], [4], [1], [1], [5], [2], [4], [5], [2], [4], [1], [4], [5], [5], [3], [3], [1], [2], [2], [4], [5], [1], [3], [2], [4], [5], [3], [1], [5], [3], [3], [4], [1], [3], [2], [3], [5], [4], [1], [3], [5], [5], [2], [1], [4], [4], [1], [5], [4], [3], [4], [1], [3], [3], [1], [5], [1], [3], [1], [4], [5], [1], [5], [2], [2], [5], [5], [5], [4], [1], [2], [2], [3], [3], [2], [3], [5], [1], [1], [4], [3], [1], [2], [1], [2], [4], [1], [1], [2], [5], [1], [1], [4], [1], [2], [3], [2], [5], [4], [5], [3], [2], [5], [3], [5], [3], [3], [2], [1], [1], [1], [4], [4], [1], [3], [5], [4], [1], [5], [2], [5], [3], [2], [1], [4], [2], [1], [3], [2], [5], [5], [5], [3], [5], [3], [5], [1], [5], [1], [3], [3], [2], [3], [4], [1], [4], [1], [2], [3], [4], [5], [5], [3], [5], [3], [1], [1], [3], [2], [4], [1], [3], [3], [5], [1], [3], [3], [2], [4], [4], [2], [4], [1], [1], [2], [3], [2], [4], [1], [4], [3], [5], [1], [2], [1], [5], [4], [4], [1], [3], [1], [2], [1], [2], [1], [1], [5], [5], [2], [4], [4], [2], [4], [2], [2], [1], [1], [3], [1], [4], [1], [4], [1], [1], [2], [2], [4], [1], [2], [4], [4], [3], [1], [2], [5], [5], [4], [3], [1], [1], [4], [2], [4], [5], [5], [3], [3], [2], [5], [1], [5], [5], [2], [1], [3], [4], [2], [1], [5], [4], [3], [3], [1], [1], [2], [2], [2], [2], [2], [5], [2], [3], [3], [4], [4], [5], [3], [5], [2], [3], [1], [1], [2], [4], [2], [4], [1], [2], [2], [3], [1], [1], [3], [3], [5], [5], [3], [2], [3], [3], [2], [4], [3], [3], [3], [3], [3], [5], [5], [4], [3], [1], [3], [1], [4], [1], [1], [1], [5], [4], [5], [4], [1], [4], [1], [1], [5], [5], [2], [5], [5], [3], [2], [1], [4], [4], [3], [2], [1], [2], [5], [1], [3], [5], [1], [1], [2], [3], [4], [4], [2], [2], [1], [3], [5], [1], [1], [3], [5], [4], [1], [5], [2], [3], [1], [3], [4], [5], [1], [3], [2], [5], [3], [5], [3], [1], [3], [2], [2], [3], [2], [4], [1], [2], [5], [2], [1], [1], [5], [4], [3], [4], [3], [3], [1], [1], [1], [2], [4], [5], [2], [1], [2], [1], [2], [4], [2], [2], [2], [2], [1], [1], [1], [2], [2], [5], [2], [2], [2], [1], [1], [1], [4], [2], [1], [1], [1], [2], [5], [4], [4], [4], [3], [2], [2], [4], [2], [4], [1], [1], [3], [3], [3], [1], [1], [3], [3], [4], [2], [1], [1], [1], [1], [2], [1], [2], [2], [2], [2], [1], [3], [1], [4], [4], [1], [4], [2], [5], [2], [1], [2], [4], [4], [3], [5], [2], [5], [2], [4], [3], [5], [3], [5], [5], [4], [2], [4], [4], [2], [3], [1], [5], [2], [3], [5], [2], [4], [1], [4], [3], [1], [3], [2], [3], [3], [2], [2], [2], [4], [3], [2], [3], [2], [5], [3], [1], [3], [3], [1], [5], [4], [4], [2], [4], [1], [2], [2], [3], [1], [4], [4], [4], [1], [5], [1], [3], [2], [3], [3], [5], [4], [2], [4], [1], [5], [5], [1], [2], [5], [4], [4], [1], [5], [2], [3], [3], [3], [4], [4], [2], [3], [2], [3], [3], [5], [1], [4], [2], [4], [5], [4], [4], [1], [3], [1], [1], [3], [5], [5], [2], [3], [3], [1], [2], [2], [4], [2], [4], [4], [1], [2], [3], [1], [2], [2], [1], [4], [1], [4], [5], [1], [1], [5], [2], [4], [1], [1], [3], [4], [2], [3], [1], [1], [3], [5], [4], [4], [4], [2], [1], [5], [5], [4], [2], [3], [4], [1], [1], [4], [4], [3], [2], [1], [5], [5], [1], [5], [4], [4], [2], [2], [2], [1], [1], [4], [1], [2], [4], [2], [2], [1], [2], [3], [2], [2], [4], [2], [4], [3], [4], [5], [3], [4], [5], [1], [3], [5], [2], [4], [2], [4], [5], [4], [1], [2], [2], [3], [5], [3], [1]]\n",
127 | "# {'sport': 1, 'business': 2, 'politics': 3, 'tech': 4, 'entertainment': 5}"
128 | ],
129 | "execution_count": 0,
130 | "outputs": []
131 | }
132 | ]
133 | }
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 1/Week 1 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/3 - Natural Langu age Processing in TensorFlow/Week 1/Week 1 Quiz.pdf
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 1/Week 1 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/3 - Natural Langu age Processing in TensorFlow/Week 1/Week 1 Quiz.png
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 2/Course 3 Week 2.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "Course 3 - Week 2 - Exercise - Answer.ipynb",
7 | "provenance": [],
8 | "collapsed_sections": []
9 | },
10 | "kernelspec": {
11 | "name": "python3",
12 | "display_name": "Python 3"
13 | },
14 | "accelerator": "GPU"
15 | },
16 | "cells": [
17 | {
18 | "cell_type": "code",
19 | "metadata": {
20 | "id": "gnwiOnGyW5JK",
21 | "colab_type": "code",
22 | "colab": {}
23 | },
24 | "source": [
25 | "import csv\n",
26 | "import tensorflow as tf\n",
27 | "import numpy as np\n",
28 | "from tensorflow.keras.preprocessing.text import Tokenizer\n",
29 | "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
30 | "\n",
31 | "!wget --no-check-certificate \\\n",
32 | " https://storage.googleapis.com/laurencemoroney-blog.appspot.com/bbc-text.csv \\\n",
33 | " -O /tmp/bbc-text.csv"
34 | ],
35 | "execution_count": 0,
36 | "outputs": []
37 | },
38 | {
39 | "cell_type": "code",
40 | "metadata": {
41 | "id": "EYo6A4v5ZABQ",
42 | "colab_type": "code",
43 | "colab": {}
44 | },
45 | "source": [
46 | "vocab_size = 1000\n",
47 | "embedding_dim = 16\n",
48 | "max_length = 120\n",
49 | "trunc_type='post'\n",
50 | "padding_type='post'\n",
51 | "oov_tok = \"\"\n",
52 | "training_portion = .8"
53 | ],
54 | "execution_count": 0,
55 | "outputs": []
56 | },
57 | {
58 | "cell_type": "code",
59 | "metadata": {
60 | "id": "iU1qq3_SZBx_",
61 | "colab_type": "code",
62 | "colab": {}
63 | },
64 | "source": [
65 | "sentences = []\n",
66 | "labels = []\n",
67 | "stopwords = [ \"a\", \"about\", \"above\", \"after\", \"again\", \"against\", \"all\", \"am\", \"an\", \"and\", \"any\", \"are\", \"as\", \"at\", \"be\", \"because\", \"been\", \"before\", \"being\", \"below\", \"between\", \"both\", \"but\", \"by\", \"could\", \"did\", \"do\", \"does\", \"doing\", \"down\", \"during\", \"each\", \"few\", \"for\", \"from\", \"further\", \"had\", \"has\", \"have\", \"having\", \"he\", \"he'd\", \"he'll\", \"he's\", \"her\", \"here\", \"here's\", \"hers\", \"herself\", \"him\", \"himself\", \"his\", \"how\", \"how's\", \"i\", \"i'd\", \"i'll\", \"i'm\", \"i've\", \"if\", \"in\", \"into\", \"is\", \"it\", \"it's\", \"its\", \"itself\", \"let's\", \"me\", \"more\", \"most\", \"my\", \"myself\", \"nor\", \"of\", \"on\", \"once\", \"only\", \"or\", \"other\", \"ought\", \"our\", \"ours\", \"ourselves\", \"out\", \"over\", \"own\", \"same\", \"she\", \"she'd\", \"she'll\", \"she's\", \"should\", \"so\", \"some\", \"such\", \"than\", \"that\", \"that's\", \"the\", \"their\", \"theirs\", \"them\", \"themselves\", \"then\", \"there\", \"there's\", \"these\", \"they\", \"they'd\", \"they'll\", \"they're\", \"they've\", \"this\", \"those\", \"through\", \"to\", \"too\", \"under\", \"until\", \"up\", \"very\", \"was\", \"we\", \"we'd\", \"we'll\", \"we're\", \"we've\", \"were\", \"what\", \"what's\", \"when\", \"when's\", \"where\", \"where's\", \"which\", \"while\", \"who\", \"who's\", \"whom\", \"why\", \"why's\", \"with\", \"would\", \"you\", \"you'd\", \"you'll\", \"you're\", \"you've\", \"your\", \"yours\", \"yourself\", \"yourselves\" ]\n",
68 | "print(len(stopwords))\n",
69 | "# Expected Output\n",
70 | "# 153"
71 | ],
72 | "execution_count": 0,
73 | "outputs": []
74 | },
75 | {
76 | "cell_type": "code",
77 | "metadata": {
78 | "id": "eutB2xMiZD0e",
79 | "colab_type": "code",
80 | "colab": {}
81 | },
82 | "source": [
83 | "with open(\"/tmp/bbc-text.csv\", 'r') as csvfile:\n",
84 | " reader = csv.reader(csvfile, delimiter=',')\n",
85 | " next(reader)\n",
86 | " for row in reader:\n",
87 | " labels.append(row[0])\n",
88 | " sentence = row[1]\n",
89 | " for word in stopwords:\n",
90 | " token = \" \" + word + \" \"\n",
91 | " sentence = sentence.replace(token, \" \")\n",
92 | " sentences.append(sentence)\n",
93 | "\n",
94 | "print(len(labels))\n",
95 | "print(len(sentences))\n",
96 | "print(sentences[0])\n",
97 | "# Expected Output\n",
98 | "# 2225\n",
99 | "# 2225\n",
100 | "# tv future hands viewers home theatre systems plasma high-definition tvs digital video recorders moving living room way people watch tv will radically different five years time. according expert panel gathered annual consumer electronics show las vegas discuss new technologies will impact one favourite pastimes. us leading trend programmes content will delivered viewers via home networks cable satellite telecoms companies broadband service providers front rooms portable devices. one talked-about technologies ces digital personal video recorders (dvr pvr). set-top boxes like us s tivo uk s sky+ system allow people record store play pause forward wind tv programmes want. essentially technology allows much personalised tv. also built-in high-definition tv sets big business japan us slower take off europe lack high-definition programming. not can people forward wind adverts can also forget abiding network channel schedules putting together a-la-carte entertainment. us networks cable satellite companies worried means terms advertising revenues well brand identity viewer loyalty channels. although us leads technology moment also concern raised europe particularly growing uptake services like sky+. happens today will see nine months years time uk adam hume bbc broadcast s futurologist told bbc news website. likes bbc no issues lost advertising revenue yet. pressing issue moment commercial uk broadcasters brand loyalty important everyone. will talking content brands rather network brands said tim hanlon brand communications firm starcom mediavest. reality broadband connections anybody can producer content. added: challenge now hard promote programme much choice. means said stacey jolna senior vice president tv guide tv group way people find content want watch simplified tv viewers. means networks us terms channels take leaf google s book search engine future instead scheduler help people find want watch. kind channel model might work younger ipod generation used taking control gadgets play them. might not suit everyone panel recognised. older generations comfortable familiar schedules channel brands know getting. perhaps not want much choice put hands mr hanlon suggested. end kids just diapers pushing buttons already - everything possible available said mr hanlon. ultimately consumer will tell market want. 50 000 new gadgets technologies showcased ces many enhancing tv-watching experience. high-definition tv sets everywhere many new models lcd (liquid crystal display) tvs launched dvr capability built instead external boxes. one example launched show humax s 26-inch lcd tv 80-hour tivo dvr dvd recorder. one us s biggest satellite tv companies directtv even launched branded dvr show 100-hours recording capability instant replay search function. set can pause rewind tv 90 hours. microsoft chief bill gates announced pre-show keynote speech partnership tivo called tivotogo means people can play recorded programmes windows pcs mobile devices. reflect increasing trend freeing multimedia people can watch want want."
101 | ],
102 | "execution_count": 0,
103 | "outputs": []
104 | },
105 | {
106 | "cell_type": "code",
107 | "metadata": {
108 | "id": "XfdaWh06ZGe3",
109 | "colab_type": "code",
110 | "colab": {}
111 | },
112 | "source": [
113 | "train_size = int(len(sentences) * training_portion)\n",
114 | "\n",
115 | "train_sentences = sentences[:train_size]\n",
116 | "train_labels = labels[:train_size]\n",
117 | "\n",
118 | "validation_sentences = sentences[train_size:]\n",
119 | "validation_labels = labels[train_size:]\n",
120 | "\n",
121 | "print(train_size)\n",
122 | "print(len(train_sentences))\n",
123 | "print(len(train_labels))\n",
124 | "print(len(validation_sentences))\n",
125 | "print(len(validation_labels))\n",
126 | "\n",
127 | "# Expected output (if training_portion=.8)\n",
128 | "# 1780\n",
129 | "# 1780\n",
130 | "# 1780\n",
131 | "# 445\n",
132 | "# 445"
133 | ],
134 | "execution_count": 0,
135 | "outputs": []
136 | },
137 | {
138 | "cell_type": "code",
139 | "metadata": {
140 | "id": "ULzA8xhwZI22",
141 | "colab_type": "code",
142 | "colab": {}
143 | },
144 | "source": [
145 | "tokenizer = Tokenizer(num_words = vocab_size, oov_token=oov_tok)\n",
146 | "tokenizer.fit_on_texts(train_sentences)\n",
147 | "word_index = tokenizer.word_index\n",
148 | "\n",
149 | "train_sequences = tokenizer.texts_to_sequences(train_sentences)\n",
150 | "train_padded = pad_sequences(train_sequences, padding=padding_type, maxlen=max_length)\n",
151 | "\n",
152 | "print(len(train_sequences[0]))\n",
153 | "print(len(train_padded[0]))\n",
154 | "\n",
155 | "print(len(train_sequences[1]))\n",
156 | "print(len(train_padded[1]))\n",
157 | "\n",
158 | "print(len(train_sequences[10]))\n",
159 | "print(len(train_padded[10]))\n",
160 | "\n",
161 | "# Expected Ouput\n",
162 | "# 449\n",
163 | "# 120\n",
164 | "# 200\n",
165 | "# 120\n",
166 | "# 192\n",
167 | "# 120"
168 | ],
169 | "execution_count": 0,
170 | "outputs": []
171 | },
172 | {
173 | "cell_type": "code",
174 | "metadata": {
175 | "id": "c8PeFWzPZLW_",
176 | "colab_type": "code",
177 | "colab": {}
178 | },
179 | "source": [
180 | "validation_sequences = tokenizer.texts_to_sequences(validation_sentences)\n",
181 | "validation_padded = pad_sequences(validation_sequences, padding=padding_type, maxlen=max_length)\n",
182 | "\n",
183 | "print(len(validation_sequences))\n",
184 | "print(validation_padded.shape)\n",
185 | "\n",
186 | "# Expected output\n",
187 | "# 445\n",
188 | "# (445, 120)"
189 | ],
190 | "execution_count": 0,
191 | "outputs": []
192 | },
193 | {
194 | "cell_type": "code",
195 | "metadata": {
196 | "id": "XkWiQ_FKZNp2",
197 | "colab_type": "code",
198 | "colab": {}
199 | },
200 | "source": [
201 | "label_tokenizer = Tokenizer()\n",
202 | "label_tokenizer.fit_on_texts(labels)\n",
203 | "\n",
204 | "training_label_seq = np.array(label_tokenizer.texts_to_sequences(train_labels))\n",
205 | "validation_label_seq = np.array(label_tokenizer.texts_to_sequences(validation_labels))\n",
206 | "\n",
207 | "print(training_label_seq[0])\n",
208 | "print(training_label_seq[1])\n",
209 | "print(training_label_seq[2])\n",
210 | "print(training_label_seq.shape)\n",
211 | "\n",
212 | "print(validation_label_seq[0])\n",
213 | "print(validation_label_seq[1])\n",
214 | "print(validation_label_seq[2])\n",
215 | "print(validation_label_seq.shape)\n",
216 | "\n",
217 | "# Expected output\n",
218 | "# [4]\n",
219 | "# [2]\n",
220 | "# [1]\n",
221 | "# (1780, 1)\n",
222 | "# [5]\n",
223 | "# [4]\n",
224 | "# [3]\n",
225 | "# (445, 1)"
226 | ],
227 | "execution_count": 0,
228 | "outputs": []
229 | },
230 | {
231 | "cell_type": "code",
232 | "metadata": {
233 | "id": "HZ5um4MWZP-W",
234 | "colab_type": "code",
235 | "colab": {}
236 | },
237 | "source": [
238 | "model = tf.keras.Sequential([\n",
239 | " tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),\n",
240 | " tf.keras.layers.GlobalAveragePooling1D(),\n",
241 | " tf.keras.layers.Dense(24, activation='relu'),\n",
242 | " tf.keras.layers.Dense(6, activation='softmax')\n",
243 | "])\n",
244 | "model.compile(loss='sparse_categorical_crossentropy',optimizer='adam',metrics=['accuracy'])\n",
245 | "model.summary()\n",
246 | "\n",
247 | "# Expected Output\n",
248 | "# Layer (type) Output Shape Param # \n",
249 | "# =================================================================\n",
250 | "# embedding (Embedding) (None, 120, 16) 16000 \n",
251 | "# _________________________________________________________________\n",
252 | "# global_average_pooling1d (Gl (None, 16) 0 \n",
253 | "# _________________________________________________________________\n",
254 | "# dense (Dense) (None, 24) 408 \n",
255 | "# _________________________________________________________________\n",
256 | "# dense_1 (Dense) (None, 6) 150 \n",
257 | "# =================================================================\n",
258 | "# Total params: 16,558\n",
259 | "# Trainable params: 16,558\n",
260 | "# Non-trainable params: 0"
261 | ],
262 | "execution_count": 0,
263 | "outputs": []
264 | },
265 | {
266 | "cell_type": "code",
267 | "metadata": {
268 | "id": "XsfdxySKZSXu",
269 | "colab_type": "code",
270 | "colab": {}
271 | },
272 | "source": [
273 | "num_epochs = 30\n",
274 | "history = model.fit(train_padded, training_label_seq, epochs=num_epochs, validation_data=(validation_padded, validation_label_seq), verbose=2)"
275 | ],
276 | "execution_count": 0,
277 | "outputs": []
278 | },
279 | {
280 | "cell_type": "code",
281 | "metadata": {
282 | "id": "dQ0BX2apXS9u",
283 | "colab_type": "code",
284 | "colab": {}
285 | },
286 | "source": [
287 | "import matplotlib.pyplot as plt\n",
288 | "\n",
289 | "\n",
290 | "def plot_graphs(history, string):\n",
291 | " plt.plot(history.history[string])\n",
292 | " plt.plot(history.history['val_'+string])\n",
293 | " plt.xlabel(\"Epochs\")\n",
294 | " plt.ylabel(string)\n",
295 | " plt.legend([string, 'val_'+string])\n",
296 | " plt.show()\n",
297 | " \n",
298 | "plot_graphs(history, \"acc\")\n",
299 | "plot_graphs(history, \"loss\")"
300 | ],
301 | "execution_count": 0,
302 | "outputs": []
303 | },
304 | {
305 | "cell_type": "code",
306 | "metadata": {
307 | "id": "w7Xc-uWxXhML",
308 | "colab_type": "code",
309 | "colab": {}
310 | },
311 | "source": [
312 | "\n",
313 | "\n",
314 | "reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])\n",
315 | "\n",
316 | "def decode_sentence(text):\n",
317 | " return ' '.join([reverse_word_index.get(i, '?') for i in text])\n"
318 | ],
319 | "execution_count": 0,
320 | "outputs": []
321 | },
322 | {
323 | "cell_type": "code",
324 | "metadata": {
325 | "id": "OhnFA_TDXrih",
326 | "colab_type": "code",
327 | "colab": {}
328 | },
329 | "source": [
330 | "e = model.layers[0]\n",
331 | "weights = e.get_weights()[0]\n",
332 | "print(weights.shape) # shape: (vocab_size, embedding_dim)\n",
333 | "\n",
334 | "# Expected output\n",
335 | "# (1000, 16)"
336 | ],
337 | "execution_count": 0,
338 | "outputs": []
339 | },
340 | {
341 | "cell_type": "code",
342 | "metadata": {
343 | "id": "_POzcWWAXudL",
344 | "colab_type": "code",
345 | "colab": {}
346 | },
347 | "source": [
348 | "import io\n",
349 | "\n",
350 | "out_v = io.open('vecs.tsv', 'w', encoding='utf-8')\n",
351 | "out_m = io.open('meta.tsv', 'w', encoding='utf-8')\n",
352 | "for word_num in range(1, vocab_size):\n",
353 | " word = reverse_word_index[word_num]\n",
354 | " embeddings = weights[word_num]\n",
355 | " out_m.write(word + \"\\n\")\n",
356 | " out_v.write('\\t'.join([str(x) for x in embeddings]) + \"\\n\")\n",
357 | "out_v.close()\n",
358 | "out_m.close()"
359 | ],
360 | "execution_count": 0,
361 | "outputs": []
362 | },
363 | {
364 | "cell_type": "code",
365 | "metadata": {
366 | "id": "VmqpQMZ_XyOa",
367 | "colab_type": "code",
368 | "colab": {}
369 | },
370 | "source": [
371 | "try:\n",
372 | " from google.colab import files\n",
373 | "except ImportError:\n",
374 | " pass\n",
375 | "else:\n",
376 | " files.download('vecs.tsv')\n",
377 | " files.download('meta.tsv')"
378 | ],
379 | "execution_count": 0,
380 | "outputs": []
381 | }
382 | ]
383 | }
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 2/Week 2 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/3 - Natural Langu age Processing in TensorFlow/Week 2/Week 2 Quiz.pdf
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 2/Week 2 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/3 - Natural Langu age Processing in TensorFlow/Week 2/Week 2 Quiz.png
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 3/Course 3 Week 3.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "NLP Course - Week 3 Exercise Answer.ipynb",
7 | "provenance": []
8 | },
9 | "kernelspec": {
10 | "name": "python3",
11 | "display_name": "Python 3"
12 | },
13 | "accelerator": "GPU"
14 | },
15 | "cells": [
16 | {
17 | "cell_type": "code",
18 | "metadata": {
19 | "id": "hmA6EzkQJ5jt",
20 | "colab_type": "code",
21 | "colab": {}
22 | },
23 | "source": [
24 | "import json\n",
25 | "import tensorflow as tf\n",
26 | "import csv\n",
27 | "import random\n",
28 | "import numpy as np\n",
29 | "\n",
30 | "from tensorflow.keras.preprocessing.text import Tokenizer\n",
31 | "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
32 | "from tensorflow.keras.utils import to_categorical\n",
33 | "from tensorflow.keras import regularizers\n",
34 | "\n",
35 | "\n",
36 | "embedding_dim = 100\n",
37 | "max_length = 16\n",
38 | "trunc_type='post'\n",
39 | "padding_type='post'\n",
40 | "oov_tok = \"\"\n",
41 | "training_size=160000\n",
42 | "test_portion=.1\n",
43 | "\n",
44 | "corpus = []\n"
45 | ],
46 | "execution_count": 0,
47 | "outputs": []
48 | },
49 | {
50 | "cell_type": "code",
51 | "metadata": {
52 | "id": "bM0l_dORKqE0",
53 | "colab_type": "code",
54 | "outputId": "491ba86b-f780-4355-a4be-765565a29c8c",
55 | "colab": {
56 | "base_uri": "https://localhost:8080/",
57 | "height": 204
58 | }
59 | },
60 | "source": [
61 | "\n",
62 | "# Note that I cleaned the Stanford dataset to remove LATIN1 encoding to make it easier for Python CSV reader\n",
63 | "# You can do that yourself with:\n",
64 | "# iconv -f LATIN1 -t UTF8 training.1600000.processed.noemoticon.csv -o training_cleaned.csv\n",
65 | "# I then hosted it on my site to make it easier to use in this notebook\n",
66 | "\n",
67 | "!wget --no-check-certificate \\\n",
68 | " https://storage.googleapis.com/laurencemoroney-blog.appspot.com/training_cleaned.csv \\\n",
69 | " -O /tmp/training_cleaned.csv\n",
70 | "\n",
71 | "num_sentences = 0\n",
72 | "\n",
73 | "with open(\"/tmp/training_cleaned.csv\") as csvfile:\n",
74 | " reader = csv.reader(csvfile, delimiter=',')\n",
75 | " for row in reader:\n",
76 | " list_item=[]\n",
77 | " list_item.append(row[5])\n",
78 | " this_label=row[0]\n",
79 | " if this_label=='0':\n",
80 | " list_item.append(0)\n",
81 | " else:\n",
82 | " list_item.append(1)\n",
83 | " num_sentences = num_sentences + 1\n",
84 | " corpus.append(list_item)\n",
85 | "\n",
86 | "\n"
87 | ],
88 | "execution_count": 0,
89 | "outputs": [
90 | {
91 | "output_type": "stream",
92 | "text": [
93 | "--2019-06-07 17:53:35-- https://storage.googleapis.com/laurencemoroney-blog.appspot.com/training_cleaned.csv\n",
94 | "Resolving storage.googleapis.com (storage.googleapis.com)... 173.194.192.128, 2607:f8b0:4001:c1d::80\n",
95 | "Connecting to storage.googleapis.com (storage.googleapis.com)|173.194.192.128|:443... connected.\n",
96 | "HTTP request sent, awaiting response... 200 OK\n",
97 | "Length: 238942690 (228M) [application/octet-stream]\n",
98 | "Saving to: ‘/tmp/training_cleaned.csv’\n",
99 | "\n",
100 | "/tmp/training_clean 100%[===================>] 227.87M 221MB/s in 1.0s \n",
101 | "\n",
102 | "2019-06-07 17:53:36 (221 MB/s) - ‘/tmp/training_cleaned.csv’ saved [238942690/238942690]\n",
103 | "\n"
104 | ],
105 | "name": "stdout"
106 | }
107 | ]
108 | },
109 | {
110 | "cell_type": "code",
111 | "metadata": {
112 | "id": "3kxblBUjEUX-",
113 | "colab_type": "code",
114 | "outputId": "3c0227a2-e74b-4d9b-cabb-f9ee150571b1",
115 | "colab": {
116 | "base_uri": "https://localhost:8080/",
117 | "height": 68
118 | }
119 | },
120 | "source": [
121 | "print(num_sentences)\n",
122 | "print(len(corpus))\n",
123 | "print(corpus[1])\n",
124 | "\n",
125 | "# Expected Output:\n",
126 | "# 1600000\n",
127 | "# 1600000\n",
128 | "# [\"is upset that he can't update his Facebook by texting it... and might cry as a result School today also. Blah!\", 0]"
129 | ],
130 | "execution_count": 0,
131 | "outputs": [
132 | {
133 | "output_type": "stream",
134 | "text": [
135 | "1600000\n",
136 | "1600000\n",
137 | "[\"is upset that he can't update his Facebook by texting it... and might cry as a result School today also. Blah!\", 0]\n"
138 | ],
139 | "name": "stdout"
140 | }
141 | ]
142 | },
143 | {
144 | "cell_type": "code",
145 | "metadata": {
146 | "id": "ohOGz24lsNAD",
147 | "colab_type": "code",
148 | "colab": {}
149 | },
150 | "source": [
151 | "sentences=[]\n",
152 | "labels=[]\n",
153 | "random.shuffle(corpus)\n",
154 | "for x in range(training_size):\n",
155 | " sentences.append(corpus[x][0])\n",
156 | " labels.append(corpus[x][1])\n",
157 | "\n",
158 | "\n",
159 | "tokenizer = Tokenizer()\n",
160 | "tokenizer.fit_on_texts(sentences)\n",
161 | "\n",
162 | "word_index = tokenizer.word_index\n",
163 | "vocab_size=len(word_index)\n",
164 | "\n",
165 | "sequences = tokenizer.texts_to_sequences(sentences)\n",
166 | "padded = pad_sequences(sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)\n",
167 | "\n",
168 | "split = int(test_portion * training_size)\n",
169 | "\n",
170 | "test_sequences = padded[0:split]\n",
171 | "training_sequences = padded[split:training_size]\n",
172 | "test_labels = labels[0:split]\n",
173 | "training_labels = labels[split:training_size]"
174 | ],
175 | "execution_count": 0,
176 | "outputs": []
177 | },
178 | {
179 | "cell_type": "code",
180 | "metadata": {
181 | "id": "gIrtRem1En3N",
182 | "colab_type": "code",
183 | "outputId": "4ad8401c-8dba-420d-8aee-38dac0b0839a",
184 | "colab": {
185 | "base_uri": "https://localhost:8080/",
186 | "height": 51
187 | }
188 | },
189 | "source": [
190 | "print(vocab_size)\n",
191 | "print(word_index['i'])\n",
192 | "# Expected Output\n",
193 | "# 138858\n",
194 | "# 1"
195 | ],
196 | "execution_count": 0,
197 | "outputs": [
198 | {
199 | "output_type": "stream",
200 | "text": [
201 | "138858\n",
202 | "1\n"
203 | ],
204 | "name": "stdout"
205 | }
206 | ]
207 | },
208 | {
209 | "cell_type": "code",
210 | "metadata": {
211 | "id": "C1zdgJkusRh0",
212 | "colab_type": "code",
213 | "outputId": "b6edd322-8191-45e7-cb12-08921685a72f",
214 | "colab": {
215 | "base_uri": "https://localhost:8080/",
216 | "height": 204
217 | }
218 | },
219 | "source": [
220 | "# Note this is the 100 dimension version of GloVe from Stanford\n",
221 | "# I unzipped and hosted it on my site to make this notebook easier\n",
222 | "!wget --no-check-certificate \\\n",
223 | " https://storage.googleapis.com/laurencemoroney-blog.appspot.com/glove.6B.100d.txt \\\n",
224 | " -O /tmp/glove.6B.100d.txt\n",
225 | "embeddings_index = {};\n",
226 | "with open('/tmp/glove.6B.100d.txt') as f:\n",
227 | " for line in f:\n",
228 | " values = line.split();\n",
229 | " word = values[0];\n",
230 | " coefs = np.asarray(values[1:], dtype='float32');\n",
231 | " embeddings_index[word] = coefs;\n",
232 | "\n",
233 | "embeddings_matrix = np.zeros((vocab_size+1, embedding_dim));\n",
234 | "for word, i in word_index.items():\n",
235 | " embedding_vector = embeddings_index.get(word);\n",
236 | " if embedding_vector is not None:\n",
237 | " embeddings_matrix[i] = embedding_vector;"
238 | ],
239 | "execution_count": 0,
240 | "outputs": [
241 | {
242 | "output_type": "stream",
243 | "text": [
244 | "--2019-06-07 17:55:30-- https://storage.googleapis.com/laurencemoroney-blog.appspot.com/glove.6B.100d.txt\n",
245 | "Resolving storage.googleapis.com (storage.googleapis.com)... 64.233.183.128, 2607:f8b0:4001:c12::80\n",
246 | "Connecting to storage.googleapis.com (storage.googleapis.com)|64.233.183.128|:443... connected.\n",
247 | "HTTP request sent, awaiting response... 200 OK\n",
248 | "Length: 347116733 (331M) [text/plain]\n",
249 | "Saving to: ‘/tmp/glove.6B.100d.txt’\n",
250 | "\n",
251 | "/tmp/glove.6B.100d. 100%[===================>] 331.04M 160MB/s in 2.1s \n",
252 | "\n",
253 | "2019-06-07 17:55:33 (160 MB/s) - ‘/tmp/glove.6B.100d.txt’ saved [347116733/347116733]\n",
254 | "\n"
255 | ],
256 | "name": "stdout"
257 | }
258 | ]
259 | },
260 | {
261 | "cell_type": "code",
262 | "metadata": {
263 | "id": "71NLk_lpFLNt",
264 | "colab_type": "code",
265 | "outputId": "97cb88db-754f-4375-fdc3-876cd6b4fdce",
266 | "colab": {
267 | "base_uri": "https://localhost:8080/",
268 | "height": 34
269 | }
270 | },
271 | "source": [
272 | "print(len(embeddings_matrix))\n",
273 | "# Expected Output\n",
274 | "# 138859"
275 | ],
276 | "execution_count": 0,
277 | "outputs": [
278 | {
279 | "output_type": "stream",
280 | "text": [
281 | "138859\n"
282 | ],
283 | "name": "stdout"
284 | }
285 | ]
286 | },
287 | {
288 | "cell_type": "code",
289 | "metadata": {
290 | "colab_type": "code",
291 | "id": "iKKvbuEBOGFz",
292 | "colab": {}
293 | },
294 | "source": [
295 | "model = tf.keras.Sequential([\n",
296 | " tf.keras.layers.Embedding(vocab_size+1, embedding_dim, input_length=max_length, weights=[embeddings_matrix], trainable=False),\n",
297 | " tf.keras.layers.Dropout(0.2),\n",
298 | " tf.keras.layers.Conv1D(64, 5, activation='relu'),\n",
299 | " tf.keras.layers.MaxPooling1D(pool_size=4),\n",
300 | " tf.keras.layers.LSTM(64),\n",
301 | " tf.keras.layers.Dense(1, activation='sigmoid')\n",
302 | "])\n",
303 | "model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])\n",
304 | "model.summary()\n",
305 | "\n",
306 | "num_epochs = 50\n",
307 | "history = model.fit(training_sequences, training_labels, epochs=num_epochs, validation_data=(test_sequences, test_labels), verbose=2)\n",
308 | "\n",
309 | "print(\"Training Complete\")\n"
310 | ],
311 | "execution_count": 0,
312 | "outputs": []
313 | },
314 | {
315 | "cell_type": "code",
316 | "metadata": {
317 | "id": "qxju4ItJKO8F",
318 | "colab_type": "code",
319 | "colab": {}
320 | },
321 | "source": [
322 | "import matplotlib.image as mpimg\n",
323 | "import matplotlib.pyplot as plt\n",
324 | "\n",
325 | "#-----------------------------------------------------------\n",
326 | "# Retrieve a list of list results on training and test data\n",
327 | "# sets for each training epoch\n",
328 | "#-----------------------------------------------------------\n",
329 | "acc=history.history['acc']\n",
330 | "val_acc=history.history['val_acc']\n",
331 | "loss=history.history['loss']\n",
332 | "val_loss=history.history['val_loss']\n",
333 | "\n",
334 | "epochs=range(len(acc)) # Get number of epochs\n",
335 | "\n",
336 | "#------------------------------------------------\n",
337 | "# Plot training and validation accuracy per epoch\n",
338 | "#------------------------------------------------\n",
339 | "plt.plot(epochs, acc, 'r')\n",
340 | "plt.plot(epochs, val_acc, 'b')\n",
341 | "plt.title('Training and validation accuracy')\n",
342 | "plt.xlabel(\"Epochs\")\n",
343 | "plt.ylabel(\"Accuracy\")\n",
344 | "plt.legend([\"Accuracy\", \"Validation Accuracy\"])\n",
345 | "\n",
346 | "plt.figure()\n",
347 | "\n",
348 | "#------------------------------------------------\n",
349 | "# Plot training and validation loss per epoch\n",
350 | "#------------------------------------------------\n",
351 | "plt.plot(epochs, loss, 'r')\n",
352 | "plt.plot(epochs, val_loss, 'b')\n",
353 | "plt.title('Training and validation loss')\n",
354 | "plt.xlabel(\"Epochs\")\n",
355 | "plt.ylabel(\"Loss\")\n",
356 | "plt.legend([\"Loss\", \"Validation Loss\"])\n",
357 | "\n",
358 | "plt.figure()\n",
359 | "\n",
360 | "\n",
361 | "# Expected Output\n",
362 | "# A chart where the validation loss does not increase sharply!"
363 | ],
364 | "execution_count": 0,
365 | "outputs": []
366 | }
367 | ]
368 | }
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 3/Week 3 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/3 - Natural Langu age Processing in TensorFlow/Week 3/Week 3 Quiz.pdf
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 3/Week 3 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/3 - Natural Langu age Processing in TensorFlow/Week 3/Week 3 Quiz.png
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 4/Course 3 Week 4.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "NLP_Week4_Exercise_Shakespeare_Answer.ipynb",
7 | "provenance": []
8 | },
9 | "kernelspec": {
10 | "name": "python3",
11 | "display_name": "Python 3"
12 | },
13 | "accelerator": "GPU"
14 | },
15 | "cells": [
16 | {
17 | "cell_type": "code",
18 | "metadata": {
19 | "id": "BOwsuGQQY9OL",
20 | "colab_type": "code",
21 | "colab": {}
22 | },
23 | "source": [
24 | "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
25 | "from tensorflow.keras.layers import Embedding, LSTM, Dense, Dropout, Bidirectional\n",
26 | "from tensorflow.keras.preprocessing.text import Tokenizer\n",
27 | "from tensorflow.keras.models import Sequential\n",
28 | "from tensorflow.keras.optimizers import Adam\n",
29 | "from tensorflow.keras import regularizers\n",
30 | "import tensorflow.keras.utils as ku \n",
31 | "import numpy as np "
32 | ],
33 | "execution_count": 0,
34 | "outputs": []
35 | },
36 | {
37 | "cell_type": "code",
38 | "metadata": {
39 | "colab_type": "code",
40 | "id": "PRnDnCW-Z7qv",
41 | "colab": {}
42 | },
43 | "source": [
44 | "tokenizer = Tokenizer()\n",
45 | "!wget --no-check-certificate \\\n",
46 | " https://storage.googleapis.com/laurencemoroney-blog.appspot.com/sonnets.txt \\\n",
47 | " -O /tmp/sonnets.txt\n",
48 | "data = open('/tmp/sonnets.txt').read()\n",
49 | "\n",
50 | "corpus = data.lower().split(\"\\n\")\n",
51 | "\n",
52 | "\n",
53 | "tokenizer.fit_on_texts(corpus)\n",
54 | "total_words = len(tokenizer.word_index) + 1\n",
55 | "\n",
56 | "# create input sequences using list of tokens\n",
57 | "input_sequences = []\n",
58 | "for line in corpus:\n",
59 | "\ttoken_list = tokenizer.texts_to_sequences([line])[0]\n",
60 | "\tfor i in range(1, len(token_list)):\n",
61 | "\t\tn_gram_sequence = token_list[:i+1]\n",
62 | "\t\tinput_sequences.append(n_gram_sequence)\n",
63 | "\n",
64 | "\n",
65 | "# pad sequences \n",
66 | "max_sequence_len = max([len(x) for x in input_sequences])\n",
67 | "input_sequences = np.array(pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre'))\n",
68 | "\n",
69 | "# create predictors and label\n",
70 | "predictors, label = input_sequences[:,:-1],input_sequences[:,-1]\n",
71 | "\n",
72 | "label = ku.to_categorical(label, num_classes=total_words)"
73 | ],
74 | "execution_count": 0,
75 | "outputs": []
76 | },
77 | {
78 | "cell_type": "code",
79 | "metadata": {
80 | "id": "w9vH8Y59ajYL",
81 | "colab_type": "code",
82 | "colab": {}
83 | },
84 | "source": [
85 | "model = Sequential()\n",
86 | "model.add(Embedding(total_words, 100, input_length=max_sequence_len-1))\n",
87 | "model.add(Bidirectional(LSTM(150, return_sequences = True)))\n",
88 | "model.add(Dropout(0.2))\n",
89 | "model.add(LSTM(100))\n",
90 | "model.add(Dense(total_words/2, activation='relu', kernel_regularizer=regularizers.l2(0.01)))\n",
91 | "model.add(Dense(total_words, activation='softmax'))\n",
92 | "model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n",
93 | "print(model.summary())\n"
94 | ],
95 | "execution_count": 0,
96 | "outputs": []
97 | },
98 | {
99 | "cell_type": "code",
100 | "metadata": {
101 | "id": "AIg2f1HBxqof",
102 | "colab_type": "code",
103 | "colab": {}
104 | },
105 | "source": [
106 | " history = model.fit(predictors, label, epochs=100, verbose=1)"
107 | ],
108 | "execution_count": 0,
109 | "outputs": []
110 | },
111 | {
112 | "cell_type": "code",
113 | "metadata": {
114 | "id": "1fXTEO3GJ282",
115 | "colab_type": "code",
116 | "colab": {}
117 | },
118 | "source": [
119 | "import matplotlib.pyplot as plt\n",
120 | "acc = history.history['acc']\n",
121 | "loss = history.history['loss']\n",
122 | "\n",
123 | "epochs = range(len(acc))\n",
124 | "\n",
125 | "plt.plot(epochs, acc, 'b', label='Training accuracy')\n",
126 | "plt.title('Training accuracy')\n",
127 | "\n",
128 | "plt.figure()\n",
129 | "\n",
130 | "plt.plot(epochs, loss, 'b', label='Training Loss')\n",
131 | "plt.title('Training loss')\n",
132 | "plt.legend()\n",
133 | "\n",
134 | "plt.show()"
135 | ],
136 | "execution_count": 0,
137 | "outputs": []
138 | },
139 | {
140 | "cell_type": "code",
141 | "metadata": {
142 | "id": "6Vc6PHgxa6Hm",
143 | "colab_type": "code",
144 | "colab": {}
145 | },
146 | "source": [
147 | "seed_text = \"Help me Obi Wan Kenobi, you're my only hope\"\n",
148 | "next_words = 100\n",
149 | " \n",
150 | "for _ in range(next_words):\n",
151 | "\ttoken_list = tokenizer.texts_to_sequences([seed_text])[0]\n",
152 | "\ttoken_list = pad_sequences([token_list], maxlen=max_sequence_len-1, padding='pre')\n",
153 | "\tpredicted = model.predict_classes(token_list, verbose=0)\n",
154 | "\toutput_word = \"\"\n",
155 | "\tfor word, index in tokenizer.word_index.items():\n",
156 | "\t\tif index == predicted:\n",
157 | "\t\t\toutput_word = word\n",
158 | "\t\t\tbreak\n",
159 | "\tseed_text += \" \" + output_word\n",
160 | "print(seed_text)"
161 | ],
162 | "execution_count": 0,
163 | "outputs": []
164 | }
165 | ]
166 | }
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 4/Week 4 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/3 - Natural Langu age Processing in TensorFlow/Week 4/Week 4 Quiz.pdf
--------------------------------------------------------------------------------
/3 - Natural Langu age Processing in TensorFlow/Week 4/Week 4 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/3 - Natural Langu age Processing in TensorFlow/Week 4/Week 4 Quiz.png
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Sequ ences, Time Series and Prediction Certificate.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/4 - Sequences, Time Series and Prediction/Sequ ences, Time Series and Prediction Certificate.pdf
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 1/Course 4 Week 1.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "Week 1 Exercise Answer.ipynb",
7 | "provenance": [],
8 | "collapsed_sections": []
9 | },
10 | "kernelspec": {
11 | "name": "python3",
12 | "display_name": "Python 3"
13 | },
14 | "accelerator": "GPU"
15 | },
16 | "cells": [
17 | {
18 | "cell_type": "code",
19 | "metadata": {
20 | "id": "y7QztBIVR1tb",
21 | "colab_type": "code",
22 | "colab": {}
23 | },
24 | "source": [
25 | "!pip install tensorflow==2.0.0b1\n"
26 | ],
27 | "execution_count": 0,
28 | "outputs": []
29 | },
30 | {
31 | "cell_type": "code",
32 | "metadata": {
33 | "id": "t9HrvPfrSlzS",
34 | "colab_type": "code",
35 | "colab": {}
36 | },
37 | "source": [
38 | "import tensorflow as tf\n",
39 | "print(tf.__version__)\n"
40 | ],
41 | "execution_count": 0,
42 | "outputs": []
43 | },
44 | {
45 | "cell_type": "code",
46 | "metadata": {
47 | "id": "gqWabzlJ63nL",
48 | "colab_type": "code",
49 | "colab": {}
50 | },
51 | "source": [
52 | "import numpy as np\n",
53 | "import matplotlib.pyplot as plt\n",
54 | "import tensorflow as tf\n",
55 | "from tensorflow import keras\n",
56 | "\n",
57 | "def plot_series(time, series, format=\"-\", start=0, end=None):\n",
58 | " plt.plot(time[start:end], series[start:end], format)\n",
59 | " plt.xlabel(\"Time\")\n",
60 | " plt.ylabel(\"Value\")\n",
61 | " plt.grid(True)\n",
62 | "\n",
63 | "def trend(time, slope=0):\n",
64 | " return slope * time\n",
65 | "\n",
66 | "def seasonal_pattern(season_time):\n",
67 | " \"\"\"Just an arbitrary pattern, you can change it if you wish\"\"\"\n",
68 | " return np.where(season_time < 0.1,\n",
69 | " np.cos(season_time * 7 * np.pi),\n",
70 | " 1 / np.exp(5 * season_time))\n",
71 | "\n",
72 | "def seasonality(time, period, amplitude=1, phase=0):\n",
73 | " \"\"\"Repeats the same pattern at each period\"\"\"\n",
74 | " season_time = ((time + phase) % period) / period\n",
75 | " return amplitude * seasonal_pattern(season_time)\n",
76 | "\n",
77 | "def noise(time, noise_level=1, seed=None):\n",
78 | " rnd = np.random.RandomState(seed)\n",
79 | " return rnd.randn(len(time)) * noise_level\n",
80 | "\n",
81 | "time = np.arange(4 * 365 + 1, dtype=\"float32\")\n",
82 | "baseline = 10\n",
83 | "series = trend(time, 0.1) \n",
84 | "baseline = 10\n",
85 | "amplitude = 40\n",
86 | "slope = 0.01\n",
87 | "noise_level = 2\n",
88 | "\n",
89 | "# Create the series\n",
90 | "series = baseline + trend(time, slope) + seasonality(time, period=365, amplitude=amplitude)\n",
91 | "# Update with noise\n",
92 | "series += noise(time, noise_level, seed=42)\n",
93 | "\n",
94 | "plt.figure(figsize=(10, 6))\n",
95 | "plot_series(time, series)\n",
96 | "plt.show()"
97 | ],
98 | "execution_count": 0,
99 | "outputs": []
100 | },
101 | {
102 | "cell_type": "markdown",
103 | "metadata": {
104 | "id": "UfdyqJJ1VZVu",
105 | "colab_type": "text"
106 | },
107 | "source": [
108 | "Now that we have the time series, let's split it so we can start forecasting"
109 | ]
110 | },
111 | {
112 | "cell_type": "code",
113 | "metadata": {
114 | "id": "_w0eKap5uFNP",
115 | "colab_type": "code",
116 | "colab": {}
117 | },
118 | "source": [
119 | "split_time = 1100\n",
120 | "time_train = time[:split_time]\n",
121 | "x_train = series[:split_time]\n",
122 | "time_valid = time[split_time:]\n",
123 | "x_valid = series[split_time:]\n",
124 | "plt.figure(figsize=(10, 6))\n",
125 | "plot_series(time_train, x_train)\n",
126 | "plt.show()\n",
127 | "\n",
128 | "plt.figure(figsize=(10, 6))\n",
129 | "plot_series(time_valid, x_valid)\n",
130 | "plt.show()"
131 | ],
132 | "execution_count": 0,
133 | "outputs": []
134 | },
135 | {
136 | "cell_type": "markdown",
137 | "metadata": {
138 | "id": "bjD8ncEZbjEW",
139 | "colab_type": "text"
140 | },
141 | "source": [
142 | "# Naive Forecast"
143 | ]
144 | },
145 | {
146 | "cell_type": "code",
147 | "metadata": {
148 | "id": "Pj_-uCeYxcAb",
149 | "colab_type": "code",
150 | "colab": {}
151 | },
152 | "source": [
153 | "naive_forecast = series[split_time - 1:-1]"
154 | ],
155 | "execution_count": 0,
156 | "outputs": []
157 | },
158 | {
159 | "cell_type": "code",
160 | "metadata": {
161 | "id": "JtxwHj9Ig0jT",
162 | "colab_type": "code",
163 | "colab": {}
164 | },
165 | "source": [
166 | "plt.figure(figsize=(10, 6))\n",
167 | "plot_series(time_valid, x_valid)\n",
168 | "plot_series(time_valid, naive_forecast)"
169 | ],
170 | "execution_count": 0,
171 | "outputs": []
172 | },
173 | {
174 | "cell_type": "markdown",
175 | "metadata": {
176 | "id": "fw1SP5WeuixH",
177 | "colab_type": "text"
178 | },
179 | "source": [
180 | "Let's zoom in on the start of the validation period:"
181 | ]
182 | },
183 | {
184 | "cell_type": "code",
185 | "metadata": {
186 | "id": "D0MKg7FNug9V",
187 | "colab_type": "code",
188 | "colab": {}
189 | },
190 | "source": [
191 | "plt.figure(figsize=(10, 6))\n",
192 | "plot_series(time_valid, x_valid, start=0, end=150)\n",
193 | "plot_series(time_valid, naive_forecast, start=1, end=151)"
194 | ],
195 | "execution_count": 0,
196 | "outputs": []
197 | },
198 | {
199 | "cell_type": "markdown",
200 | "metadata": {
201 | "id": "35gIlQLfu0TT",
202 | "colab_type": "text"
203 | },
204 | "source": [
205 | "You can see that the naive forecast lags 1 step behind the time series."
206 | ]
207 | },
208 | {
209 | "cell_type": "markdown",
210 | "metadata": {
211 | "id": "Uh_7244Gsxfx",
212 | "colab_type": "text"
213 | },
214 | "source": [
215 | "Now let's compute the mean squared error and the mean absolute error between the forecasts and the predictions in the validation period:"
216 | ]
217 | },
218 | {
219 | "cell_type": "code",
220 | "metadata": {
221 | "id": "byNnC7IbsnMZ",
222 | "colab_type": "code",
223 | "colab": {}
224 | },
225 | "source": [
226 | "print(keras.metrics.mean_squared_error(x_valid, naive_forecast).numpy())\n",
227 | "print(keras.metrics.mean_absolute_error(x_valid, naive_forecast).numpy())"
228 | ],
229 | "execution_count": 0,
230 | "outputs": []
231 | },
232 | {
233 | "cell_type": "markdown",
234 | "metadata": {
235 | "id": "WGPBC9QttI1u",
236 | "colab_type": "text"
237 | },
238 | "source": [
239 | "That's our baseline, now let's try a moving average:"
240 | ]
241 | },
242 | {
243 | "cell_type": "code",
244 | "metadata": {
245 | "id": "YGz5UsUdf2tV",
246 | "colab_type": "code",
247 | "colab": {}
248 | },
249 | "source": [
250 | "def moving_average_forecast(series, window_size):\n",
251 | " \"\"\"Forecasts the mean of the last few values.\n",
252 | " If window_size=1, then this is equivalent to naive forecast\"\"\"\n",
253 | " forecast = []\n",
254 | " for time in range(len(series) - window_size):\n",
255 | " forecast.append(series[time:time + window_size].mean())\n",
256 | " return np.array(forecast)"
257 | ],
258 | "execution_count": 0,
259 | "outputs": []
260 | },
261 | {
262 | "cell_type": "code",
263 | "metadata": {
264 | "id": "HHFhGXQji7_r",
265 | "colab_type": "code",
266 | "colab": {}
267 | },
268 | "source": [
269 | "moving_avg = moving_average_forecast(series, 30)[split_time - 30:]\n",
270 | "\n",
271 | "plt.figure(figsize=(10, 6))\n",
272 | "plot_series(time_valid, x_valid)\n",
273 | "plot_series(time_valid, moving_avg)"
274 | ],
275 | "execution_count": 0,
276 | "outputs": []
277 | },
278 | {
279 | "cell_type": "code",
280 | "metadata": {
281 | "id": "wG7pTAd7z0e8",
282 | "colab_type": "code",
283 | "colab": {}
284 | },
285 | "source": [
286 | "print(keras.metrics.mean_squared_error(x_valid, moving_avg).numpy())\n",
287 | "print(keras.metrics.mean_absolute_error(x_valid, moving_avg).numpy())"
288 | ],
289 | "execution_count": 0,
290 | "outputs": []
291 | },
292 | {
293 | "cell_type": "markdown",
294 | "metadata": {
295 | "id": "JMYPnJqwz8nS",
296 | "colab_type": "text"
297 | },
298 | "source": [
299 | "That's worse than naive forecast! The moving average does not anticipate trend or seasonality, so let's try to remove them by using differencing. Since the seasonality period is 365 days, we will subtract the value at time *t* – 365 from the value at time *t*."
300 | ]
301 | },
302 | {
303 | "cell_type": "code",
304 | "metadata": {
305 | "id": "5pqySF7-rJR4",
306 | "colab_type": "code",
307 | "colab": {}
308 | },
309 | "source": [
310 | "diff_series = (series[365:] - series[:-365])\n",
311 | "diff_time = time[365:]\n",
312 | "\n",
313 | "plt.figure(figsize=(10, 6))\n",
314 | "plot_series(diff_time, diff_series)\n",
315 | "plt.show()"
316 | ],
317 | "execution_count": 0,
318 | "outputs": []
319 | },
320 | {
321 | "cell_type": "markdown",
322 | "metadata": {
323 | "id": "xPlPlS7DskWg",
324 | "colab_type": "text"
325 | },
326 | "source": [
327 | "Great, the trend and seasonality seem to be gone, so now we can use the moving average:"
328 | ]
329 | },
330 | {
331 | "cell_type": "code",
332 | "metadata": {
333 | "id": "QmZpz7arsjbb",
334 | "colab_type": "code",
335 | "colab": {}
336 | },
337 | "source": [
338 | "diff_moving_avg = moving_average_forecast(diff_series, 50)[split_time - 365 - 50:]\n",
339 | "\n",
340 | "plt.figure(figsize=(10, 6))\n",
341 | "plot_series(time_valid, diff_series[split_time - 365:])\n",
342 | "plot_series(time_valid, diff_moving_avg)\n",
343 | "plt.show()"
344 | ],
345 | "execution_count": 0,
346 | "outputs": []
347 | },
348 | {
349 | "cell_type": "markdown",
350 | "metadata": {
351 | "id": "Gno9S2lyecnc",
352 | "colab_type": "text"
353 | },
354 | "source": [
355 | "Now let's bring back the trend and seasonality by adding the past values from t – 365:"
356 | ]
357 | },
358 | {
359 | "cell_type": "code",
360 | "metadata": {
361 | "id": "Dv6RWFq7TFGB",
362 | "colab_type": "code",
363 | "colab": {}
364 | },
365 | "source": [
366 | "diff_moving_avg_plus_past = series[split_time - 365:-365] + diff_moving_avg\n",
367 | "\n",
368 | "plt.figure(figsize=(10, 6))\n",
369 | "plot_series(time_valid, x_valid)\n",
370 | "plot_series(time_valid, diff_moving_avg_plus_past)\n",
371 | "plt.show()"
372 | ],
373 | "execution_count": 0,
374 | "outputs": []
375 | },
376 | {
377 | "cell_type": "code",
378 | "metadata": {
379 | "id": "59jmBrwcTFCx",
380 | "colab_type": "code",
381 | "colab": {}
382 | },
383 | "source": [
384 | "\n",
385 | "print(keras.metrics.mean_squared_error(x_valid, diff_moving_avg_plus_past).numpy())\n",
386 | "print(keras.metrics.mean_absolute_error(x_valid, diff_moving_avg_plus_past).numpy())"
387 | ],
388 | "execution_count": 0,
389 | "outputs": []
390 | },
391 | {
392 | "cell_type": "markdown",
393 | "metadata": {
394 | "id": "vx9Et1Hkeusl",
395 | "colab_type": "text"
396 | },
397 | "source": [
398 | "Better than naive forecast, good. However the forecasts look a bit too random, because we're just adding past values, which were noisy. Let's use a moving averaging on past values to remove some of the noise:"
399 | ]
400 | },
401 | {
402 | "cell_type": "code",
403 | "metadata": {
404 | "id": "K81dtROoTE_r",
405 | "colab_type": "code",
406 | "colab": {}
407 | },
408 | "source": [
409 | "diff_moving_avg_plus_smooth_past = moving_average_forecast(series[split_time - 370:-360], 10) + diff_moving_avg\n",
410 | "\n",
411 | "plt.figure(figsize=(10, 6))\n",
412 | "plot_series(time_valid, x_valid)\n",
413 | "plot_series(time_valid, diff_moving_avg_plus_smooth_past)\n",
414 | "plt.show()"
415 | ],
416 | "execution_count": 0,
417 | "outputs": []
418 | },
419 | {
420 | "cell_type": "code",
421 | "metadata": {
422 | "id": "iN2MsBxWTE3m",
423 | "colab_type": "code",
424 | "colab": {}
425 | },
426 | "source": [
427 | "print(keras.metrics.mean_squared_error(x_valid, diff_moving_avg_plus_smooth_past).numpy())\n",
428 | "print(keras.metrics.mean_absolute_error(x_valid, diff_moving_avg_plus_smooth_past).numpy())"
429 | ],
430 | "execution_count": 0,
431 | "outputs": []
432 | }
433 | ]
434 | }
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 1/Week 1 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/4 - Sequences, Time Series and Prediction/Week 1/Week 1 Quiz.pdf
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 1/Week 1 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/4 - Sequences, Time Series and Prediction/Week 1/Week 1 Quiz.png
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 2/Course 4 Week 2.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "S+P Week 2 Exercise Answer.ipynb",
7 | "provenance": []
8 | },
9 | "kernelspec": {
10 | "name": "python3",
11 | "display_name": "Python 3"
12 | },
13 | "accelerator": "GPU"
14 | },
15 | "cells": [
16 | {
17 | "cell_type": "code",
18 | "metadata": {
19 | "id": "D1J15Vh_1Jih",
20 | "colab_type": "code",
21 | "cellView": "both",
22 | "colab": {}
23 | },
24 | "source": [
25 | "!pip install tf-nightly-2.0-preview\n"
26 | ],
27 | "execution_count": 0,
28 | "outputs": []
29 | },
30 | {
31 | "cell_type": "code",
32 | "metadata": {
33 | "id": "BOjujz601HcS",
34 | "colab_type": "code",
35 | "colab": {}
36 | },
37 | "source": [
38 | "import tensorflow as tf\n",
39 | "import numpy as np\n",
40 | "import matplotlib.pyplot as plt\n",
41 | "print(tf.__version__)"
42 | ],
43 | "execution_count": 0,
44 | "outputs": []
45 | },
46 | {
47 | "cell_type": "code",
48 | "metadata": {
49 | "colab_type": "code",
50 | "id": "Zswl7jRtGzkk",
51 | "colab": {}
52 | },
53 | "source": [
54 | "def plot_series(time, series, format=\"-\", start=0, end=None):\n",
55 | " plt.plot(time[start:end], series[start:end], format)\n",
56 | " plt.xlabel(\"Time\")\n",
57 | " plt.ylabel(\"Value\")\n",
58 | " plt.grid(False)\n",
59 | "\n",
60 | "def trend(time, slope=0):\n",
61 | " return slope * time\n",
62 | "\n",
63 | "def seasonal_pattern(season_time):\n",
64 | " \"\"\"Just an arbitrary pattern, you can change it if you wish\"\"\"\n",
65 | " return np.where(season_time < 0.1,\n",
66 | " np.cos(season_time * 6 * np.pi),\n",
67 | " 2 / np.exp(9 * season_time))\n",
68 | "\n",
69 | "def seasonality(time, period, amplitude=1, phase=0):\n",
70 | " \"\"\"Repeats the same pattern at each period\"\"\"\n",
71 | " season_time = ((time + phase) % period) / period\n",
72 | " return amplitude * seasonal_pattern(season_time)\n",
73 | "\n",
74 | "def noise(time, noise_level=1, seed=None):\n",
75 | " rnd = np.random.RandomState(seed)\n",
76 | " return rnd.randn(len(time)) * noise_level\n",
77 | "\n",
78 | "time = np.arange(10 * 365 + 1, dtype=\"float32\")\n",
79 | "baseline = 10\n",
80 | "series = trend(time, 0.1) \n",
81 | "baseline = 10\n",
82 | "amplitude = 40\n",
83 | "slope = 0.005\n",
84 | "noise_level = 3\n",
85 | "\n",
86 | "# Create the series\n",
87 | "series = baseline + trend(time, slope) + seasonality(time, period=365, amplitude=amplitude)\n",
88 | "# Update with noise\n",
89 | "series += noise(time, noise_level, seed=51)\n",
90 | "\n",
91 | "split_time = 3000\n",
92 | "time_train = time[:split_time]\n",
93 | "x_train = series[:split_time]\n",
94 | "time_valid = time[split_time:]\n",
95 | "x_valid = series[split_time:]\n",
96 | "\n",
97 | "window_size = 20\n",
98 | "batch_size = 32\n",
99 | "shuffle_buffer_size = 1000\n",
100 | "\n",
101 | "plot_series(time, series)"
102 | ],
103 | "execution_count": 0,
104 | "outputs": []
105 | },
106 | {
107 | "cell_type": "code",
108 | "metadata": {
109 | "id": "4sTTIOCbyShY",
110 | "colab_type": "code",
111 | "colab": {}
112 | },
113 | "source": [
114 | "def windowed_dataset(series, window_size, batch_size, shuffle_buffer):\n",
115 | " dataset = tf.data.Dataset.from_tensor_slices(series)\n",
116 | " dataset = dataset.window(window_size + 1, shift=1, drop_remainder=True)\n",
117 | " dataset = dataset.flat_map(lambda window: window.batch(window_size + 1))\n",
118 | " dataset = dataset.shuffle(shuffle_buffer).map(lambda window: (window[:-1], window[-1]))\n",
119 | " dataset = dataset.batch(batch_size).prefetch(1)\n",
120 | " return dataset"
121 | ],
122 | "execution_count": 0,
123 | "outputs": []
124 | },
125 | {
126 | "cell_type": "code",
127 | "metadata": {
128 | "id": "TW-vT7eLYAdb",
129 | "colab_type": "code",
130 | "colab": {}
131 | },
132 | "source": [
133 | "dataset = windowed_dataset(x_train, window_size, batch_size, shuffle_buffer_size)\n",
134 | "\n",
135 | "\n",
136 | "model = tf.keras.models.Sequential([\n",
137 | " tf.keras.layers.Dense(100, input_shape=[window_size], activation=\"relu\"), \n",
138 | " tf.keras.layers.Dense(10, activation=\"relu\"), \n",
139 | " tf.keras.layers.Dense(1)\n",
140 | "])\n",
141 | "\n",
142 | "model.compile(loss=\"mse\", optimizer=tf.keras.optimizers.SGD(lr=1e-6, momentum=0.9))\n",
143 | "model.fit(dataset,epochs=100,verbose=0)\n",
144 | "\n"
145 | ],
146 | "execution_count": 0,
147 | "outputs": []
148 | },
149 | {
150 | "cell_type": "code",
151 | "metadata": {
152 | "id": "efhco2rYyIFF",
153 | "colab_type": "code",
154 | "colab": {}
155 | },
156 | "source": [
157 | "forecast = []\n",
158 | "for time in range(len(series) - window_size):\n",
159 | " forecast.append(model.predict(series[time:time + window_size][np.newaxis]))\n",
160 | "\n",
161 | "forecast = forecast[split_time-window_size:]\n",
162 | "results = np.array(forecast)[:, 0, 0]\n",
163 | "\n",
164 | "\n",
165 | "plt.figure(figsize=(10, 6))\n",
166 | "\n",
167 | "plot_series(time_valid, x_valid)\n",
168 | "plot_series(time_valid, results)"
169 | ],
170 | "execution_count": 0,
171 | "outputs": []
172 | },
173 | {
174 | "cell_type": "code",
175 | "metadata": {
176 | "id": "-kT6j186YO6K",
177 | "colab_type": "code",
178 | "colab": {}
179 | },
180 | "source": [
181 | "tf.keras.metrics.mean_absolute_error(x_valid, results).numpy()"
182 | ],
183 | "execution_count": 0,
184 | "outputs": []
185 | }
186 | ]
187 | }
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 2/Week 2 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/4 - Sequences, Time Series and Prediction/Week 2/Week 2 Quiz.pdf
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 2/Week 2 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/4 - Sequences, Time Series and Prediction/Week 2/Week 2 Quiz.png
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 3/Course 4 Week 3.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "name": "S+P Week 3 Exercise Answer.ipynb",
7 | "provenance": [],
8 | "collapsed_sections": []
9 | },
10 | "kernelspec": {
11 | "name": "python3",
12 | "display_name": "Python 3"
13 | },
14 | "accelerator": "GPU"
15 | },
16 | "cells": [
17 | {
18 | "cell_type": "code",
19 | "metadata": {
20 | "id": "D1J15Vh_1Jih",
21 | "colab_type": "code",
22 | "colab": {}
23 | },
24 | "source": [
25 | "!pip install tf-nightly-2.0-preview\n"
26 | ],
27 | "execution_count": 0,
28 | "outputs": []
29 | },
30 | {
31 | "cell_type": "code",
32 | "metadata": {
33 | "id": "BOjujz601HcS",
34 | "colab_type": "code",
35 | "colab": {}
36 | },
37 | "source": [
38 | "import tensorflow as tf\n",
39 | "import numpy as np\n",
40 | "import matplotlib.pyplot as plt\n",
41 | "print(tf.__version__)"
42 | ],
43 | "execution_count": 0,
44 | "outputs": []
45 | },
46 | {
47 | "cell_type": "code",
48 | "metadata": {
49 | "colab_type": "code",
50 | "id": "Zswl7jRtGzkk",
51 | "colab": {}
52 | },
53 | "source": [
54 | "def plot_series(time, series, format=\"-\", start=0, end=None):\n",
55 | " plt.plot(time[start:end], series[start:end], format)\n",
56 | " plt.xlabel(\"Time\")\n",
57 | " plt.ylabel(\"Value\")\n",
58 | " plt.grid(False)\n",
59 | "\n",
60 | "def trend(time, slope=0):\n",
61 | " return slope * time\n",
62 | "\n",
63 | "def seasonal_pattern(season_time):\n",
64 | " \"\"\"Just an arbitrary pattern, you can change it if you wish\"\"\"\n",
65 | " return np.where(season_time < 0.1,\n",
66 | " np.cos(season_time * 6 * np.pi),\n",
67 | " 2 / np.exp(9 * season_time))\n",
68 | "\n",
69 | "def seasonality(time, period, amplitude=1, phase=0):\n",
70 | " \"\"\"Repeats the same pattern at each period\"\"\"\n",
71 | " season_time = ((time + phase) % period) / period\n",
72 | " return amplitude * seasonal_pattern(season_time)\n",
73 | "\n",
74 | "def noise(time, noise_level=1, seed=None):\n",
75 | " rnd = np.random.RandomState(seed)\n",
76 | " return rnd.randn(len(time)) * noise_level\n",
77 | "\n",
78 | "time = np.arange(10 * 365 + 1, dtype=\"float32\")\n",
79 | "baseline = 10\n",
80 | "series = trend(time, 0.1) \n",
81 | "baseline = 10\n",
82 | "amplitude = 40\n",
83 | "slope = 0.005\n",
84 | "noise_level = 3\n",
85 | "\n",
86 | "# Create the series\n",
87 | "series = baseline + trend(time, slope) + seasonality(time, period=365, amplitude=amplitude)\n",
88 | "# Update with noise\n",
89 | "series += noise(time, noise_level, seed=51)\n",
90 | "\n",
91 | "split_time = 3000\n",
92 | "time_train = time[:split_time]\n",
93 | "x_train = series[:split_time]\n",
94 | "time_valid = time[split_time:]\n",
95 | "x_valid = series[split_time:]\n",
96 | "\n",
97 | "window_size = 20\n",
98 | "batch_size = 32\n",
99 | "shuffle_buffer_size = 1000\n",
100 | "\n",
101 | "plot_series(time, series)"
102 | ],
103 | "execution_count": 0,
104 | "outputs": []
105 | },
106 | {
107 | "cell_type": "code",
108 | "metadata": {
109 | "id": "4sTTIOCbyShY",
110 | "colab_type": "code",
111 | "colab": {}
112 | },
113 | "source": [
114 | "def windowed_dataset(series, window_size, batch_size, shuffle_buffer):\n",
115 | " dataset = tf.data.Dataset.from_tensor_slices(series)\n",
116 | " dataset = dataset.window(window_size + 1, shift=1, drop_remainder=True)\n",
117 | " dataset = dataset.flat_map(lambda window: window.batch(window_size + 1))\n",
118 | " dataset = dataset.shuffle(shuffle_buffer).map(lambda window: (window[:-1], window[-1]))\n",
119 | " dataset = dataset.batch(batch_size).prefetch(1)\n",
120 | " return dataset"
121 | ],
122 | "execution_count": 0,
123 | "outputs": []
124 | },
125 | {
126 | "cell_type": "code",
127 | "metadata": {
128 | "id": "A1Hl39rklkLm",
129 | "colab_type": "code",
130 | "colab": {}
131 | },
132 | "source": [
133 | "tf.keras.backend.clear_session()\n",
134 | "tf.random.set_seed(51)\n",
135 | "np.random.seed(51)\n",
136 | "\n",
137 | "tf.keras.backend.clear_session()\n",
138 | "dataset = windowed_dataset(x_train, window_size, batch_size, shuffle_buffer_size)\n",
139 | "\n",
140 | "model = tf.keras.models.Sequential([\n",
141 | " tf.keras.layers.Lambda(lambda x: tf.expand_dims(x, axis=-1),\n",
142 | " input_shape=[None]),\n",
143 | " tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32, return_sequences=True)),\n",
144 | " tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),\n",
145 | " tf.keras.layers.Dense(1),\n",
146 | " tf.keras.layers.Lambda(lambda x: x * 10.0)\n",
147 | "])\n",
148 | "\n",
149 | "lr_schedule = tf.keras.callbacks.LearningRateScheduler(\n",
150 | " lambda epoch: 1e-8 * 10**(epoch / 20))\n",
151 | "optimizer = tf.keras.optimizers.SGD(lr=1e-8, momentum=0.9)\n",
152 | "model.compile(loss=tf.keras.losses.Huber(),\n",
153 | " optimizer=optimizer,\n",
154 | " metrics=[\"mae\"])\n",
155 | "history = model.fit(dataset, epochs=100, callbacks=[lr_schedule])"
156 | ],
157 | "execution_count": 0,
158 | "outputs": []
159 | },
160 | {
161 | "cell_type": "code",
162 | "metadata": {
163 | "id": "AkBsrsXMzoWR",
164 | "colab_type": "code",
165 | "colab": {}
166 | },
167 | "source": [
168 | "plt.semilogx(history.history[\"lr\"], history.history[\"loss\"])\n",
169 | "plt.axis([1e-8, 1e-4, 0, 30])"
170 | ],
171 | "execution_count": 0,
172 | "outputs": []
173 | },
174 | {
175 | "cell_type": "code",
176 | "metadata": {
177 | "id": "4uh-97bpLZCA",
178 | "colab_type": "code",
179 | "colab": {}
180 | },
181 | "source": [
182 | "tf.keras.backend.clear_session()\n",
183 | "tf.random.set_seed(51)\n",
184 | "np.random.seed(51)\n",
185 | "\n",
186 | "tf.keras.backend.clear_session()\n",
187 | "dataset = windowed_dataset(x_train, window_size, batch_size, shuffle_buffer_size)\n",
188 | "\n",
189 | "model = tf.keras.models.Sequential([\n",
190 | " tf.keras.layers.Lambda(lambda x: tf.expand_dims(x, axis=-1),\n",
191 | " input_shape=[None]),\n",
192 | " tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32, return_sequences=True)),\n",
193 | " tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),\n",
194 | " tf.keras.layers.Dense(1),\n",
195 | " tf.keras.layers.Lambda(lambda x: x * 100.0)\n",
196 | "])\n",
197 | "\n",
198 | "\n",
199 | "model.compile(loss=\"mse\", optimizer=tf.keras.optimizers.SGD(lr=1e-5, momentum=0.9),metrics=[\"mae\"])\n",
200 | "history = model.fit(dataset,epochs=500,verbose=1)"
201 | ],
202 | "execution_count": 0,
203 | "outputs": []
204 | },
205 | {
206 | "cell_type": "code",
207 | "metadata": {
208 | "id": "icGDaND7z0ne",
209 | "colab_type": "code",
210 | "colab": {}
211 | },
212 | "source": [
213 | "forecast = []\n",
214 | "results = []\n",
215 | "for time in range(len(series) - window_size):\n",
216 | " forecast.append(model.predict(series[time:time + window_size][np.newaxis]))\n",
217 | "\n",
218 | "forecast = forecast[split_time-window_size:]\n",
219 | "results = np.array(forecast)[:, 0, 0]\n",
220 | "\n",
221 | "\n",
222 | "plt.figure(figsize=(10, 6))\n",
223 | "\n",
224 | "plot_series(time_valid, x_valid)\n",
225 | "plot_series(time_valid, results)"
226 | ],
227 | "execution_count": 0,
228 | "outputs": []
229 | },
230 | {
231 | "cell_type": "code",
232 | "metadata": {
233 | "id": "KfPeqI7rz4LD",
234 | "colab_type": "code",
235 | "colab": {}
236 | },
237 | "source": [
238 | "tf.keras.metrics.mean_absolute_error(x_valid, results).numpy()"
239 | ],
240 | "execution_count": 0,
241 | "outputs": []
242 | },
243 | {
244 | "cell_type": "code",
245 | "metadata": {
246 | "id": "JUsdZB_tzDLe",
247 | "colab_type": "code",
248 | "colab": {}
249 | },
250 | "source": [
251 | "import matplotlib.image as mpimg\n",
252 | "import matplotlib.pyplot as plt\n",
253 | "\n",
254 | "#-----------------------------------------------------------\n",
255 | "# Retrieve a list of list results on training and test data\n",
256 | "# sets for each training epoch\n",
257 | "#-----------------------------------------------------------\n",
258 | "mae=history.history['mae']\n",
259 | "loss=history.history['loss']\n",
260 | "\n",
261 | "epochs=range(len(loss)) # Get number of epochs\n",
262 | "\n",
263 | "#------------------------------------------------\n",
264 | "# Plot MAE and Loss\n",
265 | "#------------------------------------------------\n",
266 | "plt.plot(epochs, mae, 'r')\n",
267 | "plt.plot(epochs, loss, 'b')\n",
268 | "plt.title('MAE and Loss')\n",
269 | "plt.xlabel(\"Epochs\")\n",
270 | "plt.ylabel(\"Accuracy\")\n",
271 | "plt.legend([\"MAE\", \"Loss\"])\n",
272 | "\n",
273 | "plt.figure()\n",
274 | "\n",
275 | "epochs_zoom = epochs[200:]\n",
276 | "mae_zoom = mae[200:]\n",
277 | "loss_zoom = loss[200:]\n",
278 | "\n",
279 | "#------------------------------------------------\n",
280 | "# Plot Zoomed MAE and Loss\n",
281 | "#------------------------------------------------\n",
282 | "plt.plot(epochs_zoom, mae_zoom, 'r')\n",
283 | "plt.plot(epochs_zoom, loss_zoom, 'b')\n",
284 | "plt.title('MAE and Loss')\n",
285 | "plt.xlabel(\"Epochs\")\n",
286 | "plt.ylabel(\"Accuracy\")\n",
287 | "plt.legend([\"MAE\", \"Loss\"])\n",
288 | "\n",
289 | "plt.figure()"
290 | ],
291 | "execution_count": 0,
292 | "outputs": []
293 | }
294 | ]
295 | }
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 3/Week 3 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/4 - Sequences, Time Series and Prediction/Week 3/Week 3 Quiz.pdf
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 3/Week 3 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/4 - Sequences, Time Series and Prediction/Week 3/Week 3 Quiz.png
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 4/Week 4 Quiz.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/4 - Sequences, Time Series and Prediction/Week 4/Week 4 Quiz.pdf
--------------------------------------------------------------------------------
/4 - Sequences, Time Series and Prediction/Week 4/Week 4 Quiz.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/4 - Sequences, Time Series and Prediction/Week 4/Week 4 Quiz.png
--------------------------------------------------------------------------------
/CODE_OF_CONDUCT.md:
--------------------------------------------------------------------------------
1 | # Contributor Covenant Code of Conduct
2 |
3 | ## Our Pledge
4 |
5 | In the interest of fostering an open and welcoming environment, we as
6 | contributors and maintainers pledge to making participation in our project and
7 | our community a harassment-free experience for everyone, regardless of age, body
8 | size, disability, ethnicity, sex characteristics, gender identity and expression,
9 | level of experience, education, socio-economic status, nationality, personal
10 | appearance, race, religion, or sexual identity and orientation.
11 |
12 | ## Our Standards
13 |
14 | Examples of behavior that contributes to creating a positive environment
15 | include:
16 |
17 | * Using welcoming and inclusive language
18 | * Being respectful of differing viewpoints and experiences
19 | * Gracefully accepting constructive criticism
20 | * Focusing on what is best for the community
21 | * Showing empathy towards other community members
22 |
23 | Examples of unacceptable behavior by participants include:
24 |
25 | * The use of sexualized language or imagery and unwelcome sexual attention or
26 | advances
27 | * Trolling, insulting/derogatory comments, and personal or political attacks
28 | * Public or private harassment
29 | * Publishing others' private information, such as a physical or electronic
30 | address, without explicit permission
31 | * Other conduct which could reasonably be considered inappropriate in a
32 | professional setting
33 |
34 | ## Our Responsibilities
35 |
36 | Project maintainers are responsible for clarifying the standards of acceptable
37 | behavior and are expected to take appropriate and fair corrective action in
38 | response to any instances of unacceptable behavior.
39 |
40 | Project maintainers have the right and responsibility to remove, edit, or
41 | reject comments, commits, code, wiki edits, issues, and other contributions
42 | that are not aligned to this Code of Conduct, or to ban temporarily or
43 | permanently any contributor for other behaviors that they deem inappropriate,
44 | threatening, offensive, or harmful.
45 |
46 | ## Scope
47 |
48 | This Code of Conduct applies both within project spaces and in public spaces
49 | when an individual is representing the project or its community. Examples of
50 | representing a project or community include using an official project e-mail
51 | address, posting via an official social media account, or acting as an appointed
52 | representative at an online or offline event. Representation of a project may be
53 | further defined and clarified by project maintainers.
54 |
55 | ## Enforcement
56 |
57 | Instances of abusive, harassing, or otherwise unacceptable behavior may be
58 | reported by contacting the project team at mahesh.b.pec@gmail.com. All
59 | complaints will be reviewed and investigated and will result in a response that
60 | is deemed necessary and appropriate to the circumstances. The project team is
61 | obligated to maintain confidentiality with regard to the reporter of an incident.
62 | Further details of specific enforcement policies may be posted separately.
63 |
64 | Project maintainers who do not follow or enforce the Code of Conduct in good
65 | faith may face temporary or permanent repercussions as determined by other
66 | members of the project's leadership.
67 |
68 | ## Attribution
69 |
70 | This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
71 | available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
72 |
73 | [homepage]: https://www.contributor-covenant.org
74 |
75 | For answers to common questions about this code of conduct, see
76 | https://www.contributor-covenant.org/faq
77 |
--------------------------------------------------------------------------------
/CONTRIBUTING.md:
--------------------------------------------------------------------------------
1 | Share your doubts and suggesions about the course.
2 |
--------------------------------------------------------------------------------
/DeepLearning.AI
TensorFlow Developer Professional Certificate.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/DeepLearning.AI
TensorFlow Developer Professional Certificate.pdf
--------------------------------------------------------------------------------
/DeepLearning.AI TensorFlow Developer Course Certificate.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/3aadc85579898c9fd815eb05012e02a5946d2015/DeepLearning.AI TensorFlow Developer Course Certificate.png
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "[]"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright [yyyy] [name of copyright owner]
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # DeepLearning.AI-TensorFlow-Developer-Course
2 |
3 |
4 |
5 |
6 |
7 | **[DeepLearning.AI TensorFlow Developer Professional Certificate](https://www.coursera.org/specializations/tensorflow-in-practice)**
8 |
9 |
10 | **Instructor**: `Laurence Moroney`
11 |
12 |
13 | All course Notebooks can be found [here](https://github.com/lmoroney/dlaicourse).
14 |
15 |
16 |
17 | ## Star History
18 |
19 |
20 |
21 |
22 |
23 |
24 |
25 |
26 |
27 | ## Stargazers
28 |
29 | [](https://github.com/MaheshBabu11/DeepLearning.AI-TensorFlow-Developer-Course/stargazers)
30 |
--------------------------------------------------------------------------------