A PROJECT REPORT ON

FACE EMOTION DETECTION

A SHORT-TERM INTERNSHIP Project Report Submitted to Jawaharlal Nehru

Technological University, Kakinada in partial fulfillments of Requirements for the
Award of the Degree of

BACHELOR OF TECHNOLOGY IN

COMPUTER SCIENCE AND ENGINEERING (AI & ML)

Submitted By

SHAIK KULSUM 21KT1A4256

Under the Esteemed Guidance of

Mrs. Ch. Bala Vijaya Durga, M. Tech, (Ph.D.)

Associate Professor
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING (AI &ML)

POTTI SRIRAMULU CHALAVADI MALLIKARJUNA

RAO COLLEGE OF ENGINEERING & TECHNOLOGY
(AUTONOMOUS)
(Approved by AICTE New Delhi, Affiliated to JNTU-Kakinada)
KOTHAPET, VIJAYAWADA- 520001, A.P

2023-2024
 PROGRAM BOOK FOR

SHORT-TERMINTERNSHIP
Onsite/Virtual

Name of the Student: SHAIK KULSUM

Registration Number: 21KT1A4256

Period of internship: 2 months

From: 03-June-2024 To: 27-July-2024

Name & Address of the Intern Organization: SKILL DZIRE -

Realtime Learning Platform, Hyderabad, Telangana 500081

Jawaharlal Nehru Technological University

2023-2024

YEAR
 An Internship Report on
Face Emotion Recognition

Submitted in accordance with the requirement for the degree of

B. TECH

Under the Faculty Guideship of

Mrs. Ch. Bala Vijaya Durga, M. Tech, (Ph. D.)

Department of CSE (AI & ML)

POTTI SRIRAMULU CHALAVADI MALLIKARJUNA

RAO COLLEGE OF ENGINEERING & TECHNOLOGY
(AUTONOMOUS)

Submitted by: SHAIK KULSUM

Reg. No: 21KT1A4256

Department of CSE(AI&ML)

POTTI SRIRAMULU CHALAVADI MALLIKARJUNA

RAO COLLEGE OF ENGINEERING & TECHNOLOGY
(AUTONOMOUS)
 Student’s Declaration

I am SHAIK KULSUM, a student of B. TECH Program, Reg. No:

21KT1A4256 of the Department of CSE(AI&ML) Collegedo hereby
declare that I have completed the mandatory internship from 03-June-
2024 to 27-July-2024 in “SKILL DZIRE - Realtime Learning
Platform” under the Faculty Guide ship of Mrs. Ch. Bala Vijaya
Durga, M.Tech, (Ph.D.), Department of CSE(AI&ML), Potti
Sriramulu Chalavadi Mallikarjuna Rao College of Engineering
& Technology.

(Signature and Date)

 Official Certification

This is to certify that SHAIK KULSUM Reg. No. 21KT1A4256 has completed
his/her internship in “SKILL DZIRE - Realtime Learning Platform” on FACE
EMOTION DETECTION under my supervision as a part of partial fulfillment of
the requirement for the Degree of B. TECH in the Department of CSE(AI&ML),
Potti Sriramulu Chalavadi Mallikarjuna Rao College of Engineering &
Technology.

This is accepted for evaluation.

(Signatory and Seal)

Endorsements

Faculty Guide

Head of the Department

Principal
 Certificate from Intern Organization

This is to certify that SHAIK KULSUM Reg. No.

21KT1A4256 of Potti Sriramulu Chalavadi Mallikarjuna
Rao College of Engineering & Technology underwent
internship in “SKILL DZIRE - Realtime Learning Platform”
from 03-June-2024 to 27-July-2024.

The overall performance of the intern during his/her internship is

found to be __________________ (Satisfactory/Not Satisfactory).

Authorized Signatory with Date and Seal

 Acknowledgements

We owe many thanks to many people who helped and supported and
suggested us in every step. We are glad to have the support of our
principal Dr. AKELLA PATHANJALI SASTRI who inspired us
with his wordsfilled with dedication and discipline toward work. We
express our gratitude towards Mrs. N V MAHA LAKSHMI,
M.Tech, (PhD), Professor & HOD of CSE(AI&ML) for extending
his support through training classes which had been the major source
to carrying out our project. We are very much thankful to Mrs. Ch.
Bala Vijaya Durga, M.Tech, (Ph.D.), Associate Professor for
various documents of ours with attention and care. She has taken pain
to go through the project and make necessary corrections as and when
needed. Finally, we thank one and all who directly and indirectly
helped us to complete our project successfully.

Project Associates
SHAIK KULSUM

21KT1A4256
 Contents

S. No Topic Page. No

1 EXECUTIVE SUMMARY 2

2 OVERVIEW OF THE 3
ORGANIZATION

3 INTERNSHIP PART 4

4 ACTIVITY LOG 5-20

5 OUTCOMES DESCRIPTION 21-32

Page 1
 CHAPTER1: EXECUTIVE SUMMARY

I have successfully completed a Deep Learning internship with “SKILL

DZIRE - Realtime Learning Platform” company. The major focus
of this curriculum was to teach the fundamentals of deep learning, introduce
several DL models and enhance Python programming skills. The internship
program was conducted offline. The fundamentals of Python, deep learning
algorithms, an introduction to DL models, and building optimized DL models
were covered during this internship. Additionally, we successfully completed
a Deep Learning project using Python.

1. Objectives:
 Improve understanding of Deep Learning with Python.
 Gain knowledge of Python libraries like TensorFlow and Keras.
 Learn various concepts related to DL models.
 Gain familiarity with Neural Networks, Convolutional Networks (CNNs),
and other advanced DL techniques.
 Develop skills in Flask and Web Scraping for integrating DL models in
applications.
 Explore applications and algorithms in Deep Learning.

2. Outcomes:
 Acquired in-depth knowledge of Python for deep learning.
 Gained hands-on experience with libraries such as TensorFlow, Keras, and
Numpy.
 Learned and implemented key Deep Learning algorithms and architectures.
 Built interactive visualizations using plotly for data interpretation.
 Successfully implemented CNNs, LSTM, and other DL models for project
applications.

Page 2
 CHAPTER 2: OVERVIEW OF THE ORGANIZATION
SkillDzire is a Hyderabad-based job-oriented training platform designed to
provide real-time learning experiences and internships to help individuals
develop the skills needed to succeed in today's job market. The platform offers a
wide range of courses, internships, and placement services. Its registered office
is in Hydreabad, Telangana, India.
Courses: SkillDzire provides over 65 job-oriented courses and internships in a
variety of fields, including full stack development, data science, human resource
management, digital marketing, electric vehicle technology, UI/UX design, and
product management.
Internships: SkillDzire offers real-time internship programs that allow learners
to apply their skills in practical settings, helping them gain valuable hands-on
experience.
Placement: SkillDzire has a dedicated placement team that works with
companies and recruiters across India to help graduates find jobs that match their
skillsets.
Payment Options: SkillDzire offers flexible payment options, including easy
monthly installments and pay-later plans, to make their courses more accessible
to a wider audience.
Mission: SkillDzire's mission is to drive change in India by equipping individuals
with relevant industry skills. We shall play the parts of software trainees during
the internship time. Our internship program lasts eight weeks. The interns are
trained by a highly skilled technical staff of Skilldzire. This does not imply that
we will be given a guaranteed income, though. Interns are asked to uphold
workplace etiquette during theinternship since it will affect their ability to receive
a project completion certificate. Only if you are active during the duration of the
internship by finishing all assignments and project work assigned to the intern
will a completion letter be awarded. The main activities of the company are
maintenance of websites of other firms/ creation of multimedia presentations for
other firms and provide complete end-to-end outsourcing solutions for various
industries, have a comprehensive set of solutions for the Educational Institutes,
banking, finance, insurance, manufacturing, retail & distribution and contracting
sectors. Skilldzire has marketing presence in all.

Page 3
 CHAPTER 3: INTERNSHIP PART

As an online program, the internship provides participants with direct interaction

with the team through platforms such as Google Meet and a WhatsApp group,
where all assignments and tasks are posted. Our work primarily required the usage
of the Python programming language, and we utilized tools such as Google Colab
and Jupyter Notebook for executing the code. These platforms save our work and
allocate some RAM for program execution. The datasets were obtained from Kaggle,
a public repository. The training lasts six weeks, with weekly assignments, and the
program runs for a total of six to eight weeks. The final project's completion and
video documentation took two weeks. Regular training sessions are held from 6 pm
to 8 pm.

During the first week of training, we covered the basics of the Python language.
Each assignment is given 3-4 days for completion. Every task assigned to us is
assessed, and our progress is consistently tracked and recorded.

As part of the internship requirements, we could choose to complete the project

individually or in pairs, with a two-week deadline after selecting the topic. A video
presentation and documentation of the project were required, which were uploaded
to each intern's LinkedIn profile. Our trainers reviewed the project and conducted
a follow-up discussion, asking questions about the work. Successful completion of
the reviews results in the award of an internship completion certificate.

Through this internship, we gained valuable insights into deep learning algorithms,
What Convolutional Neural Networks (CNNs) function, how to create video
documentation, and how to review projects. Additionally, we developed time
management skills through the structured schedule of the program.

Page 4
 CHAPTER 4: ACTIVITY LOG

ACTIVITY LOG FOR THE FIRST WEEK

Person
Day & Date Brief description of the daily Learning Outcome In-Charge
Signature
activity

Day–1
03-06-2024

Day-2
04-06-2024

Day–3
05-06-2024

Day–4
06-06-2024

Day–5
07-06-2024

c
Day–6
08-06-2024

Page 5
 WEEKLY REPORT WEEK–1

(From 03-06-2024 To 08-06-2024)

Objective of the Activity Done:

Page 6
 ACTIVITY LOG FOR THE SECOND WEEK
Person
Day & Date Brief description of the daily Learning Outcome In-Charge
Signature
activity

Day–1
10-06-2024

Day-2
11-06-2024

Day–3
12-06-2024

Day–4
13-06-2024

Day–5
14-06-2024

Day–6
15-06-2024

Page 7
 WEEKLY REPORT WEEK–2
(From 10-06-2024 To 15-06-2024)

Objective of the Activity Done:

Page 8
 ACTIVITY LOG FOR THE THIRD WEEK
Person
Day & Date Brief description of the daily Learning Outcome In-Charge
Signature
activity

Day–1
17-06-2024

Day-2
18-06-2024

Day–3
19-06-2024

Day–4
20-06-2024

Day–5
21-06-2024

Day–6
22-06-2024

Page 9
 WEEKLY REPORT WEEK–3
(From 17-06-2024 To 22-06-2024)

Objective of the Activity Done:

Page 10
 ACTIVITY LOG FOR THE FOURTH WEEK
Person
Day & Date Brief description of the daily Learning Outcome In-Charge
Signature
activity

Day–1
24-06-2024

Day-2
25-06-2024

Day–3
26-06-2024

Day–4
27-06-2024

Day–5
28-06-2024

Day–6
29-06-2024

Page 11
 WEEKLY REPORT WEEK–4
(From 24-06-2024 To 29-06-2024)

Objective of the Activity Done:

Page 12
 ACTIVITY LOG FOR THE FIFTH WEEK
Person
Day & Date Brief description of the daily Learning Outcome In-Charge
Signature
activity

Day–1
01-07-2024

Day-2
02-07-2024

Day–3
03-07-2024

Day–4
04-07-2024

Day–5
05-07-2024

Day–6
06-07-2024

Page 13
 WEEKLY REPORT WEEK–5

(From 01-07-2024 To 06-07-2024)

Objective of the Activity Done:

Page 14
 ACTIVITY LOG FOR THE SIXTH WEEK
Person
Day & Date Brief description of the daily Learning Outcome In-Charge
Signature
activity

Day–1
08-07-2024

Day-2
09-07-2024

Day–3
10-07-2024

Day–4
11-07-2024

Day–5
12-07-2024

Day–6
13-07-2024

Page 15
 WEEKLY REPORT WEEK–6

(From 08-07-2024 To 13-07-2024)

Objective of the Activity Done:

Page 16
 ACTIVITY LOG FOR THE SEVENTH WEEK
Person
Day & Date Brief description of the daily Learning Outcome In-Charge
Signature
activity

Day–1
15-07-2024

Day-2
16-07-2024

Day–3
17-07-2024

Day–4
18-07-2024

Day–5
19-07-2024

Day–6
20-07-2024

Page 17
 WEEKLY REPORT WEEK–7
(From 15-07-2024 To 20-07-2024)

Objective of the Activity Done:

Page 18
 ACTIVITY LOG FOR THE EIGHTH WEEK
Person
Day & Date Brief description of the daily Learning Outcome In-Charge
Signature
activity

Day–1
22-07-2024

Day-2
23-07-2024

Day–3
24-07-2024

Day–4
25-07-2024

Day–5
26-07-2024

Day–6
27-07-2024

Page 19
 WEEKLY REPORT WEEK–8
(From 22-07-2024 To 27-07-2024)

Objective of the Activity Done:

Page 20
 CHAPTER 5: OUTCOMES DESCRIPTION

Communicated with the trainers in the internship program through Meetings in

the organization. For every topic covered during the meeting, they facilitate
recorded sessions. The program assigns weeklyhomework in order to assess the
development. The deep learning internship focused on implementing and fine-
tuning various advanced neural network architectures, including Convolutional
Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-
Term Memory (LSTM) networks. These models were applied to a range of tasks
such as image classification, natural language processing (NLP), and time-series
prediction. A comprehensive understanding of both machine learning (ML) and
deep learning (DL) concepts was developed, encompassing essential topics like
activation functions, loss functions, optimization algorithms, and performance
evaluation metrics. The hands-on experience spanned several projects, including
fake news detection using RNNs, brain tumor classification through CNNs, and
real-time object detection with the YOLO algorithm. These projects involved
working extensively with large datasets, requiring the application of various
preprocessing techniques such as tokenization, stemming, normalization, and data
augmentation.

Key tools and libraries, including TensorFlow, PyTorch, Keras, OpenCV, and
Numpy, were utilized throughout the data preparation, model training, and
deployment processes. Special attention was given to optimizing model
performance through techniques like hyperparameter tuning, regularization, and
early stopping. This experience not only enhanced technical expertise but also
honed essential soft skills, including problem-solving, logical thinking, and
effective project management. The combination of theoretical knowledge and
practical application provided a well-rounded foundation, equipping for tackling
real-world AI challenges across a variety of domains, such as healthcare, NLP, and
computer vision. This internship fostered both technical growth and the ability to
address complex problems in AI and deep learning.

Page 21
 TECHNOLOGIES
DEEP LEARNING: Deep learning is a method in artificial intelligence (AI) that teaches
computers to process data in a way that is inspired by the human brain. Deep learning
models can recognize complex patterns in pictures, text, sounds, and other data to produce
accurate insights and predictions. Deep Learning (DL) is a subset of Machine Learning (ML)
that focuses on algorithms inspired by the structure and function of the brain, known as
artificial neural networks (ANNs). DL is designed to automatically learn representations
from data, enabling the model to capture intricate patterns and relationships.
Technologies:
1. Deep Learning Frameworks:
o TensorFlow: An open-source library developed by Google, TensorFlow provides a
flexible ecosystem for building and deploying deep learning models. It supports both
high-level APIs like Keras for quick prototyping and lower-level operations for fine-
tuning model performance.
o Keras: A high-level API that runs on top of TensorFlow, Keras simplifies the process
of building and training deep learning models. Its user-friendly interface allows
developers to create complex neural networks with minimal code, making it ideal for
beginners and those looking to prototype quickly.
o PyTorch: Developed by Facebook, PyTorch is popular for its dynamic computation
graph, allowing real-time changes during model training. This feature is particularly
useful in research environments where flexibility is crucial. PyTorch also supports a
wide range of neural network architectures and is increasingly being adopted in
production settings.
o MXNet: A scalable deep learning framework that supports a variety of programming
languages, including Python, R, and Julia. It is designed for efficiency in both training
and inference, making it suitable for applications involving large datasets.
o Caffe: A deep learning framework focused on speed and modularity, Caffe is well-
suited for image classification tasks and convolutional neural networks (CNNs).
2. Neural Network Architectures:
o Convolutional Neural Networks (CNNs): CNNs are specifically designed for
processing structured grid data, such as images. They use convolutional layers to extract
features from input images, enabling the model to recognize patterns and perform tasks
like image classification and object detection.
o Recurrent Neural Networks (RNNs): RNNs are designed for sequential data, such as
time series or text. They maintain a memory of previous inputs, allowing them to capture
temporal dependencies.
o Transformers: Transformers are powerful models used primarily in NLP tasks. They
utilize self-attention mechanisms to process input data in parallel, making them highly
effective for tasks such as language translation, text summarization, and sentiment
analysis.

Page 22
 PROJECT DESCRIPTION

Face emotion recognition has become a critical area of research in human-

computer interaction, security, and entertainment industries. This project
focuses on developing a deep learning-based system for identifying human
emotions from facial expressions. Leveraging Convolutional Neural Networks
(CNNs), the system is trained on a labeled dataset of facial images representing
different emotional states such as happiness, sadness, anger, surprise, and
neutral expressions.

The proposed model processes input images to extract facial features and maps
them to corresponding emotions. By employing techniques such as data
augmentation, transfer learning, and hyperparameter tuning, the system
enhances recognition accuracy and robustness across diverse facial
characteristics and lighting conditions.

The system is designed to work in real-time, making it ideal for applications in

areas such as customer service, security surveillance, and entertainment. By
integrating deep learning with emotion recognition, this project paves the way
for enhancing human-machine interaction, enabling systems to respond more
naturally to users' emotional states. Future improvements could involve
expanding the dataset to include more complex emotions or integrating the
system into real-world environments like video conferencing tools, social
robots, or virtual reality platforms.

The effectiveness of the model is evaluated using standard benchmarks,

achieving promising results in real-time emotion detection. The system's
applications span areas like sentiment analysis, social robotics, and
psychological analysis, offering a step toward more intuitive and adaptive
human-machine interactions.

Page 23
OUTCOMES

Page 24
Page 25
Page 26
 HARDWARE REQUIREMENTS
1. For the project, you will need system software that can handle data analysis and
Machine Learning tasks. Graphics Processing Units (GPUs): Training deep
learning models is computationally intensive, and GPUs significantly accelerate the
process due to their parallel processing capabilities. NVIDIA GPUs are widely used
in the deep learning community, and frameworks like TensorFlow and PyTorch are
optimized to take advantage of GPU architectures through CUDA.

2. Central Processing Units (CPUs): While GPUs are essential for training, CPUs are
still necessary for data preprocessing, loading, and other tasks. A multi-core CPU
can handle these operations more efficiently, ensuring that the training process is
not bottlenecked by data input.

3. RAM: Sufficient RAM is critical for deep learning tasks, especially when handling
large datasets. A minimum of 16GB is recommended, while 32GB or more is ideal
for complex model training.

4. Storage: Fast storage solutions, such as Solid-State Drives (SSDs), are crucial for
quick data access and model training. At least 500GB of SSD storage is advisable
to accommodate datasets and intermediate output.

PROGRAMMING LANGUAGES:

 Python
 R
 Julia
 JavaScript (TensorFlow.js)
 C++
 Java
 MATLAB
 Scala

Page 27
 SOFTWARE REQUIREMENTS

Operating System: A modern OS, such as Windows, Linux, or macOS, is necessary to run
deep learning frameworks and tools. Linux is particularly favored for its robustness and
support for various open-source libraries.

1. Integrated Development Environment (IDE): An IDE is crucial for writing and

debugging code. Popular options for Python development include:
o PyCharm: A feature-rich IDE that supports Python and offers strong integration with
data science libraries.
o Jupyter Notebook: An interactive environment ideal for experimentation and
documentation, allowing users to combine code, visualizations, and narrative text.
o Visual Studio Code: A versatile code editor with support for Python and Jupyter
integration.

2. Deep Learning Libraries: Libraries necessary for implementing deep learning models
include:
o TensorFlow and Keras: For building and training deep learning models with high-
level abstractions.
o PyTorch: For its dynamic computation graph and ease of use in research and
production.
o Scikit-learn: While primarily for classical machine learning, it is useful for
preprocessing data and evaluating models.

3. Database Management System: A robust DBMS is required for managing and storing
datasets efficiently. Popular choices include:
o MySQL: A widely used relational database management system.
o PostgreSQL: Known for its robustness and support for advanced data types.
o MongoDB: A NoSQL database ideal for handling unstructured data and large datasets.

4. Version Control: Utilizing version control systems like Git is essential for managing
code changes, facilitating collaboration, and maintaining a history of project
modifications.

Page 28
 Managerial Skills Acquired

In this Onsite internship, we have learned skills including

⮚ Teamwork
⮚ Behavior
⮚ Efficient time management
⮚ Weekly competency growth
⮚ Goal-setting
⮚ Decision-making
⮚ Performance analysis, etc.

As a team member working on a project, we discovered what responsibilities

should be played and how to use timeefficiently.

Project management teams that work together are more effective and
productive. Everyone is showcasing their talents, being honest with themselves,
and being willing to accept assistance because they value one another. There
will be less conflict and more positive attitudes everywhere.

Man becomes expert in a subject by learning new stuff. As a result,

performance has improved. From week one to week six, we learned a lot of new
things, such as how to use statistics to solve problems in the real world.

Page 29
 Communication Skills

Only when knowledge is transferred between two or more people can

communication occur. When one of the persons engaged is not listening
effectively, communicationis limited, hence good listening helps to improve
communication abilities. You can better understand the conversation and
increase your ability to communicate back by paying attentively.

Since this is a Onsite internship, there is face-to-face interaction.

However, contact takes place through regular attendance at meetings and
WhatsApp groups. To dispelany remaining questions about the subject,
some seminars are held in this manner. In any conversation, make an effort
to strike a balance between talking and listening. It should be mandatory to
add courtesy when speaking to oneanother.

While some form of contact is taking place, the information is being

conveyed. The confidence level must be high when speaking with the guide in
offline meetings. We are able to speak clearly thanks to our confidence. When
I spoke with the mentor, I felt a little more confident, so the task at hand was
successfully completed. We must send eachother thank-you notes and smiles
when communication is about to end to ensure a smooth exchange.

Page 30
 Collaborative Skills
Discussions can help make better understand a subject or topic area, explore
ideas and exchange information, expand and clarifying knowledge, improve your
ability to think critically, improve my language skills, and boost the speaking
confidence. Discussions can also change our attitudes and ideas, help a group
come to a decision, and giving the chance to hear what others are thinking and
feeling. Communication canonly take place when knowledge is shared between
two or more individuals.

Paying attention will help you grasp the discourse more clearly and
improve your capacity to respond. To dispel any remaining questions about the
subject, certain seminars are held in this way. In any interaction, try to establish
a balance between talking and listening. Contact, however, takes place through
regular attendance at meetings and WhatsApp groups. When conversing to one
another, civility should be required. The information is being transmitted while
there is some sort of contact. When chatting with the guide in offline meetings,
the confidence level must be high. Wecommunicate with clarity because we are
confident.

After speaking with the mentor,I felt a little more confident, therefore the
task at hand was effectively completed. The project, which is a group effort, and
it was also a collaborative effort, we were able to turn in our project on time. To
finish the project, a video documentation is created. Pre-processed the data for
our project, built the model, and evaluated the model components in our ML
algorithm. In this internship, we finally predicted whether there will be rain
tomorrow or not based on today and some other parameters.

Page 31
 Technological Developments

No-Code and Low-Code Deep Learning Development are rapidly growing trends,
enabling businesses to leverage deep learning without extensive coding knowledge.
These platforms offer pre-built models, automated functions, and intuitive interfaces,
allowing users to train and deploy models easily. Throughout this internship, I have
learned about cutting-edge deep learning tools like TensorFlow and Pytorch, along
with essential libraries such as Numpy, Pandas, and Matplotlib.
 TensorFlow: TensorFlow is one of the most popular open-source libraries for deep
learning and machine learning. It supports various deep learning models, including
Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and
more. TensorFlow allows users to build and train models with both low and high
levels of abstraction, offering flexibility for simple and complex deep learning tasks.
 PyTorch: PyTorch is another powerful deep learning library with strong support for
dynamic computational graphs, which makes model training more intuitive. It is
widely used in academic research and industry for deep learning applications,
especially in computer vision and natural language processing
 Numpy in Deep Learning; Numpy plays a critical role in deep learning as it allows
for efficient handling of multi-dimensional arrays and matrices, which are the
foundation of neural network computations. Functions like min(), max(), mean(), and
std() help in basic data analysis and preparation for model training. Numpy’s fast
array operations make it invaluable for pre-processing data.
 Pandas in Deep Learning: Pandas is widely used for data manipulation and analysis
in deep learning projects. In deep learning workflows, Pandas helps in cleaning,
transforming, and organizing data into formats that can be easily used by neural
networks. Whether working with one-dimensional Series, two-dimensional
DataFrames, or more complex data structures, Pandas simplifies the process of
preparing data for deep learning.
 Matplotlib in Deep Learning: Matplotlib is a fundamental plotting library in Python
and is crucial in deep learning for visualizing data, model performance, and results.
It's frequently used for plotting learning curves, visualizing loss, accuracy, and
analyzing features from CNNs and other deep learning architectures.

Page 32
 Student Self Evaluation of the Short-Term Internship
Student Name: SHAIK KULSUM Registration No: 21KT1A4256
Term of Internship: 2 Months From:03-June-2024 To:27-July-2024
Date of Evaluation:

Organization Name & Address: SKILL DZIRE - Realtime Learning Platform, 04th Floor,
Bizness Square, opp: Hitex Junction, HITEC City, Hyderabad, Telangana 500081

Please rate your performance in the following areas:

Rating Scale: Letter grade of CGPA calculation to be provided

1 Oral communication 1 2 3 4 5
2 Written communication 1 2 3 4 5
3 Proactiveness 1 2 3 4 5
4 Interaction ability with community 1 2 3 4 5
5 Positive Attitude 1 2 3 4 5
6 Self-confidence 1 2 3 4 5
7 Ability to learn 1 2 3 4 5
8 Work Plan and organization 1 2 3 4 5
9 Professionalism 1 2 3 4 5
10 Creativity 1 2 3 4 5
11 Quality of work done 1 2 3 4 5
12 Time Management 1 2 3 4 5
13 Understanding the Community 1 2 3 4 5
14 Achievement of Desired Outcomes 1 2 3 4 5
15 OVERALL PERFORMANCE 1 2 3 4 5

Date: Signature of the Student

 Evaluation by the Supervisor of the Intern Organization
Student Name: SHAIK KULSUM Registration No: 21KT1A4256

Term of Internship: 2 Months From:03-June-2024 To:27-July-2024

Date of Evaluation:

Organization Name & Address: SKILL DZIRE - Realtime Learning Platform, 04th Floor,
Bizness Square, opp: Hitex Junction, HITEC City, Hyderabad, Telangana 500081

Name & Address of the Supervisor with Mobile Number:

Please rate the student’s performance in the following areas:

Please note that your evaluation shall be done independent of the student’s self-evaluation
Rating Scale: 1 is lowest and 5 is highest rank
1 Oral communication 1 2 3 4 5

2 Written communication 1 2 3 4 5

3 Proactiveness 1 2 3 4 5

4 Interaction ability with community 1 2 3 4 5

5 Positive Attitude 1 2 3 4 5

6 Self-confidence 1 2 3 4 5

7 Ability to learn 1 2 3 4 5

8 Work Plan and organization 1 2 3 4 5

9 Professionalism 1 2 3 4 5

10 Creativity 1 2 3 4 5

11 Quality of work done 1 2 3 4 5

12 Time Management 1 2 3 4 5

13 Understanding the Community 1 2 3 4 5

14 Achievement of Desired Outcomes 1 2 3 4 5

15 OVERALL PERFORMANCE 1 2 3 4 5

Date: Signature of the Supervisor

 PHOTOS & VIDEO LINKS

PROJECT SOURCE CODE:

https://github.com/kul32/face-emotion-recognition

DATASET LINK:

https://www.kaggle.com/datasets/aadityasinghal/facial-
expression-dataset

SOFTWARE USED: Free Download | Anaconda

OFFER LETTER
COMPLETION CERTIFICATE