Gain insights into advanced deep learning and NLP by building 12 real-world projects using tools like TensorFlow and scikit-learn. Enhance your portfolio with industry-relevant skills.

dockerfile.tar.gz

python3

spa-job

In this course, you'll not only learn advanced deep learning concepts, but you'll also practice building some advanced deep learning and Natural Language Processing (NLP) projects. By the end, you will be able to utilize deep learning algorithms that are used at large in industry.

 

This is a project-based course with 12 projects in total. This will get you used to building real-world applications that are being used in a wide range of industries. You will be exposed to the most common tools used for machine learning projects including: NumPy, Matplotlib, scikit-learn, Tensorflow, and more.

 

It’s recommended that you have a firm grasp in these topic areas: Python basics, Numpy and Pandas, and Artificial Neural Networks.

 

Once you’re finished, you will have the experience to start building your own amazing projects, and some great new additions to your portfolio.

Building Advanced Deep Learning and NLP Projects

We made, shuffled, and preprocessed our dataset in the previous lesson. In this lesson, we will work with the `ResNet50` model.

# Importing the libraries
We will use `TensorFlow's Keras` module to build this project. 

from tensorflow.python.keras.applications.resnet50 import ResNet50
from tensorflow.python.keras.optimizers import Adam
from tensorflow.python.keras.layers import *
from tensorflow.python.keras.models import Model
import numpy as np
print("Imported Successfully!")

# Load the `ResNet50` model
The next step is to load the `ResNet50` model. We will also have a look at the summary of the model to understand the architecture of the `ResNet50` model.

model = ResNet50(include_top = False, weights = 'imagenet', input_shape = (224,224,3))
print(model.summary())

**Explanation:**

* The weights will start to download. It will take a bit of time to complete the download process.
* We passed three parameters in the `ResNet50()`.
  * `include_top`: the default value of this parameter is `True`. It means that we want to load the model with the classifier. Remember the architecture we discussed in the previous lessons. We gave the value, `False`, as we will built our own classifiers on top of the convolutional base of the ResNet50 model.
   * `input_shape`: this has to be specified if we are setting the value of `include_top` to be `False`. The default value is `(224,224,3)`. The third dimension specifies that the image is colored.
   * `weights`: this can have two values: `imagenet` or `None`. We want our model to load with the weights the model learned on the *ImageNet* dataset.

* When you print the summary of the model, you will seethe  `(7 x 7 x 2048)` sized output from the model. This shows that after `flattening`, we would have a large number of parameters. To avoid this, we apply `GlobalAveragePooling` before passing the vector to the `Fully Connected Layer`. Check the output by running the code shown above.

Here, you can see around 23 million parameters are trainable but we will not be training this amount of parameters.

In this lesson, we will be performing the feature extractor strategy to build our classifier.

Welcome to the Course

Project: Build a COVID-19 Detection System Using X-Rays

Project: Building a Pokemon Classifier Using Transfer Learning

Project: Text Generation Using Markov Chains

Word Embedding: Two Mini Projects

Project: IMDB Reviews Sentiment Analysis

Project: Deciphering Text Using Character-Level RNNs

Project: Emoji Predictor Using Transfer Learning in NLP

Final Exam

Where to Go Next?

Project Creation: Part Two

Importing the libraries

Load the `ResNet50` model

Project Creation: Part Two

Importing the libraries

Load the ResNet50 model

Load the `ResNet50` model