705.643.8VL - Deep Learning Developments with PyTorch

Expanded Course Description

Prerequisites

Fluency in Python programming is required. Prior experience with deep learning and PyTorch will be very helpful but not required.

Course Structure

The course materials are divided into modules which can be accessed by clicking Modules on the course menu. A module will have several sections including the overview, content, readings, discussions, and assignments. You are encouraged to preview all sections of the module before starting. Most modules run for a period of seven (7) days, exceptions are noted in the Course Outline. You should regularly check the Calendar and Announcements for assignment due dates.

Course Topics

• Introduction to PyTorch
• Image Classification
  
• Object Detection
• Semantic Segmentation
• Video Action Recognition
• Vision Transformer and Its Applications
• Introduction to Contrastive Learning
• Introduction to Self-Supervised Learning
• Introduction to Multimodal Learning
• Advanced Topics of Vision Transformers

Course Goals

The goal is to provide students with comprehensive development experience in one of the most popular deep learning libraries PyTorch, in the context of computer vision, natural language processing, and reinforcement learning. The course adopts a hands-on approach to walk students through core steps involved in real-world DL projects and covers several key application areas.

Course Learning Outcomes (CLOs)

• Understand and implement essential components of PyTorch model development pipelines, including but not limited to, Torch tensors, datasets & dataloaders, elementary data augmentation, automatic differentiation, optimizers, loss functions, model saving & loading etc.
• Learn fundamentals of convolutional neural networks and their variants such as R-CNN, Fast R-CNN, Faster R-CNN, Mask R-CNN, autoencoders, and DETR etc. Develop CNN models for image-based classification, object detection, semantic segmentation, and instance segmentation.
• Select proper learning methods based upon problem contexts, including but not limited to, transfer learning, multi-task learning, contrastive learning, and self-supervised learning. Implement visualization and regularization techniques for neural networks, such as class activation maps, batch normalization, and layer normalization.
• Develop solid foundations to Transformer architectures and their implementations. Examine the details of self-/cross-attention mechanisms, patchifying, and other transformer-specific operations. Learn how transformers outperform CNNs in various downstream tasks.
• Consolidate development skills of key components in neural network modeling via a semester long research project. Summarize and present major findings in research papers or technical reports.

Textbooks

Ayyadevara, V. K. & Reddy, Y. (2020). Modern Computer Vision with PyTorch: Explore Deep Learning Concepts and Implement Over 50 Real-World Image Applications. Birmingham, UK: Packt Publishing.

ISBN-10: 1839213477
ISBN-13: 978-1839213472

Textbook information for this course is available online through the appropriate bookstore website: For online courses, search the BNC Virtual Bookstore

Other Materials & Online Resources

Optional

Additionally, any of the following texts or other resources that you may have from previous courses may be useful for this course if you find yourself struggling with specific skills:

• Foundations of Statistical Natural Language Processing. Manning, C. D. & Schutze H. ISBN-10: ‎ 0262133601.
• Deep Learning with PyTorch: Build, train, and tune neural networks using Python tools. Stevens, E., Antiga, L., & Viehmann, T. ISBN-10: 1617295264.
• Deep Learning. Goodfellow I., Bengio Y., & Courville A. ISBN-10: ‎0262035618.
• Official PyTorch Tutorials: https://pytorch.org/tutorials/.

Required Software

PyTorch

You will need access to a recent version of PyTorch, which is fully open-sourced and free for download.

There are several different ways to install PyTorch. We briefly provide two installation methods below. Feel free to use other installation alternatives that you may find via different sources.

• Install PyTorch to Local Machines: Depending on the operating systems of your laptops/desktops. The official PyTorch website provides different installation packages. Specific instructions can be found on https://pytorch.org/ (scroll down to the INSTALL PYTORCH section). Please note that local installation is typically time-consuming and requires lots of configurations. If you are not comfortable with such processes, proceed with other suggested installation methods.
  
  
• Use PyTorch from Google Colab Notebook: PyTorch has been built in the Colab notebook and only needs to be imported before use. This is arguably the most straightforward installation option. However, this option may suffer from limited GPU capacity that prevents users from training neural networks for longer periods. Upgrading your Google accounts may help you over these constraints with monetary prices.
  
  
• Use PyTorch on GPU servers: Some students may have access to GPU servers which natively host pre-built PyTorch images. This is a luxury and addresses all previous concerns. If one has this option, don’t hesitate to proceed with it.

All implementations (i.e., coding) are expected to be completed using Python and Google Colab Notebook (or Jupyter Notebook). For those with access to local machines or remote servers with GPUs, I strongly recommend that students modularize their code and execute via command line. Specifically, students are encouraged to develop intermediate experience with the following topics:

• Python machine learning and data science libraries, including but not limited to, NumPy, Pandas, MatplotLib, Scipy, Scikit-Learn, and others.
• Elementary single/multivariable calculus, including partial derivatives and vector calculus.
• Basic linear algebra, including matrix operations, decompositions, and eigenvectors.
• Fundamental probability and statistics, including common discrete/continuous random variables, statistical distributions, expectation, variance, sampling, estimation.
• Some machine learning basics, including training versus testing, learning taxonomy such as supervised versus unsupervised, classification versus regression, etc. Previous experience with deep learning would be helpful but not required, tensors, datasets/dataloaders, data augmentation, back-propagation, optimizers, loss functions, and fully connected neural networks etc.

Insufficient preparations in some categories may demand extra time commitment from students. If you either took these courses recently or maintained a decent recollection of roughly 70% or above on these concepts, you should be considered well-prepared. A solid Python programming experience is extremely important.

Student Coursework Requirements

It is expected that each module will take approximately 7–10 hours per week to complete. Here is an approximate breakdown: reading the assigned sections of the texts (approximately 3–4 hours per week) as well as some outside reading, listening to the audio annotated slide presentations (approximately 2–3 hours per week), and writing assignments (approximately 2–3 hours per week).

This course will consist of the following basic student requirements:

Class Discussions (10% of Final Grade Calculation)

You are responsible for carefully reading all assigned material and being prepared for discussion. Majority of the readings are from the course text. Additional reading may be assigned to supplement text readings.

Post your initial response to the discussion questions by the evening of day 3 for that module week. Posting a response to the discussion question is part one of your grade for module discussions (i.e., Timeliness).

Part two of your grade for module discussion is your interaction (i.e., responding to classmate postings with thoughtful responses) with at least two classmates (i.e., Critical Thinking). Just posting your response to a discussion question is not sufficient; we want you to interact with your classmates. Be detailed in your postings and in your responses to your classmates' postings. Feel free to agree or disagree with your classmates. Please ensure that your postings are civil and constructive.

I/We will monitor module discussions and will respond to some of the discussions as discussions are posted. In some instances, I/we will summarize the overall discussions and post the summary for the module.

Evaluation of preparation and participation is based on contribution to discussions.

Preparation and participation are evaluated by the following grading elements:

Timeliness (50%)

Critical Thinking (50%)

Preparation and participation are graded as follows:

• 100–90 = A—Timeliness [regularly participates; all required postings; early in discussion; throughout the discussion]; Critical Thinking [rich in content; full of thoughts, insight, and analysis].
• 89–80 = B—Timeliness [frequently participates; all required postings; some not in time for others to read and respond]; Critical Thinking [substantial information; thought, insight, and analysis has taken place].
• 79–70 = C—Timeliness [infrequently participates; all required postings; most at the last minute without allowing for response time]; Critical Thinking [generally competent; information is thin and commonplace].
• <70 = F—Timeliness [rarely participates; some, or all required postings missing]; Critical Thinking [rudimentary and superficial; no analysis or insight is displayed].

Assignments (60% of Final Grade Calculation)

Assignments will include a mix of qualitative assignments (e.g. literature reviews, model summaries), quantitative problem sets, and case study updates. Include a cover sheet with your name and assignment identifier. Also include your name and a page number indicator (i.e., page x of y) on each page of your submissions. Each problem should have the problem statement, assumptions, computations, and conclusions/discussion delineated. All Figures and Tables should be captioned and labeled appropriately.

All assignments are due according to the dates in the Calendar.

Late submissions will be reduced by one letter grade for each week late (no exceptions without prior coordination with the instructors).

If, after submitting a written assignment you are not satisfied with the grade received, you are encouraged to redo the assignment and resubmit it. If the resubmission results in a better grade, that grade will be substituted for the previous grade.

Qualitative assignments are evaluated by the following grading elements:

1. Each part of question is answered (20%)
2. Writing quality and technical accuracy (30%) (Writing is expected to meet or exceed accepted graduate-level English and scholarship standards. That is, all assignments will be graded on grammar and style as well as content.)
3. Rationale for answer is provided (20%)
4. Examples are included to illustrate rationale (15%) (If you do not have direct experience related to a particular question, then you are to provide analogies versus examples.)
5. Outside references are included (15%)

Qualitative assignments are graded as follows:

• 100–90 = A—All parts of question are addressed; Writing Quality/ Rationale/ Examples/ Outside References [rich in content; full of thought, insight, and analysis].
• 89–80 = B—All parts of the question are addressed; Writing Quality/ Rationale/ Examples/ Outside References [substantial information; thought, insight, and analysis has taken place].
• 79–70=C—Majority of parts of the question are addressed; Writing Quality/ Rationale/ Examples/ Outside References [generally competent; information is thin and commonplace].
• <70=F—Some parts of the question are addressed; Writing Quality/ Rationale/ Examples/ Outside References [rudimentary and superficial; no analysis or insight displayed].

Quantitative assignments are evaluated by the following grading elements:

1. Each part of question is answered (20%)
2. Assumptions are clearly stated (20%)
3. Intermediate derivations and calculations are provided (25%)
4. Answer is technically correct and is clearly indicated (25%)
5. Answer precision and units are appropriate (10%)

Quantitative assignments are graded as follows:

• 100–90 = A—All parts of question are addressed; All assumptions are clearly stated; All intermediate derivations and calculations are provided; Answer is technically correct and is clearly indicated; Answer precision and units are appropriate.
• 89–80 = B—All parts of question are addressed; All assumptions are clearly stated; Some intermediate derivations and calculations are provided; Answer is technically correct and is indicated; Answer precision and units are appropriate.
• 79–70=C—Most parts of question are addressed; Assumptions are partially stated; Few intermediate derivations and calculations are provided; Answer is not technically correct but is indicated; Answer precision and units are indicated but inappropriate.
• <70=F—Some parts of the question are addressed; Assumptions are not stated; Intermediate derivations and calculations are not provided; The answer is incorrect or missing; The answer precision and units are inappropriate or missing.

Course Project (30% of Final Grade Calculation)

A course project will be assigned several weeks into the course. The next-to-the-last week will be devoted to the course project.

The course project is evaluated by the following grading elements:

1. Student preparation and participation (as described in Course Project Description) (40%)
2. Student technical understanding of the course project topic (as related to individual role that the student assumes and described in the Course Project Description) (20%)
3. Team preparation and participation (as described in Course Project Description) (20%)
4. Team technical understanding of the course project topic (as related to the Customer Team roles assumed by the students and the Seller Team roles assumed by the students and described in the Course Project Description) (20%)

Course Project is graded as follows:

• 100–90 = A—Student Preparation and Participation/ Team Preparation and Participation [individual/ team roles and responsibilities well defined and understood; individual/ team well versed in use of Adobe Connect; individual/ teamwork product(s) agreed to, well prepared and available to all team members/ instructors]; Student Understanding/ Team Understanding [rich in content; full of thought, insight, and analysis].
• 89–80 = B—Student Preparation and Participation/ Team Preparation and Participation [individual/ team roles and responsibilities well defined and understood; individual/ team well versed in use of Adobe Connect; individual/ teamwork product(s) agreed to and prepared]; Student Understanding/ Team Understanding [substantial information; thought, insight, and analysis has taken place].
• 79–70 = C—Student Preparation and Participation/ Team Preparation and Participation [individual/ team roles and responsibilities agreed to; individual/ team well versed in use of Adobe Connect; individual/ teamwork product(s) prepared]; Student Understanding/ Team Understanding [generally competent; information is thin and commonplace].
• <70 = F—Student Preparation and Participation/ Team Preparation and Participation [individual/ team roles and responsibilities not well understood; individual/ team has difficult with use of Adobe Connect; individual/ teamwork product(s) partially prepared]; Student Understanding/ Team Understanding [rudimentary and superficial; no analysis or insight displayed].

Grading Policy

Assignments are due according to the dates posted on your Canvas course site. You may check these due dates in the Course Calendar or the Assignments in the corresponding modules. I will post grades one or two weeks after assignment due dates.

We generally do not directly grade spelling and grammar. However, egregious violations of the rules of the English language will be noted without comment. Consistently poor performance in either spelling or grammar is taken as an indication of poor written communication ability that may detract from your grade.

A grade of A indicates achievement of consistent excellence and distinction throughout the course—that is, conspicuous excellence in all aspects of assignments and discussion every week.

A grade of B indicates work that meets all course requirements at a level appropriate for graduate academic work. These criteria apply to both undergraduates and graduate students taking the course.

100-90 = A
89-80 = B
79-70 = C
<70 = F

Final grades will be determined by the following weighting. The grade cut-offs provided above are simply guidelines. I reserve the right to curve the final letter grades based upon the actual class performance.

Course Policies

It is assumed that graduate students are adept at writing English and no points will normally be subtracted for English errors; However, points will be deducted in cases of exceptionally poor English. All external sources of information used to support assignments or projects must be appropriately referenced.

Academic Policies

Deadlines for Adding, Dropping and Withdrawing from Courses

Students may add a course up to one week after the start of the term for that particular course. Students may drop courses according to the drop deadlines outlined in the EP academic calendar (https://ep.jhu.edu/student-services/academic-calendar/). Between the 6th week of the class and prior to the final withdrawal deadline, a student may withdraw from a course with a W on their academic record. A record of the course will remain on the academic record with a W appearing in the grade column to indicate that the student registered and withdrew from the course.

Academic Misconduct Policy

All students are required to read, know, and comply with the Johns Hopkins University Krieger School of Arts and Sciences (KSAS) / Whiting School of Engineering (WSE) Procedures for Handling Allegations of Misconduct by Full-Time and Part-Time Graduate Students.

This policy prohibits academic misconduct, including but not limited to the following: cheating or facilitating cheating; plagiarism; reuse of assignments; unauthorized collaboration; alteration of graded assignments; and unfair competition. Course materials (old assignments, texts, or examinations, etc.) should not be shared unless authorized by the course instructor. Any questions related to this policy should be directed to EP’s academic integrity officer at ep-academic-integrity@jhu.edu.

Students with Disabilities - Accommodations and Accessibility

Johns Hopkins University values diversity and inclusion. We are committed to providing welcoming, equitable, and accessible educational experiences for all students. Students with disabilities (including those with psychological conditions, medical conditions and temporary disabilities) can request accommodations for this course by providing an Accommodation Letter issued by Student Disability Services (SDS). Please request accommodations for this course as early as possible to provide time for effective communication and arrangements.

For further information or to start the process of requesting accommodations, please contact Student Disability Services at Engineering for Professionals, ep-disability-svcs@jhu.edu.

Student Conduct Code

The fundamental purpose of the JHU regulation of student conduct is to promote and to protect the health, safety, welfare, property, and rights of all members of the University community as well as to promote the orderly operation of the University and to safeguard its property and facilities. As members of the University community, students accept certain responsibilities which support the educational mission and create an environment in which all students are afforded the same opportunity to succeed academically. 

For a full description of the code please visit the following website: https://studentaffairs.jhu.edu/policies-guidelines/student-code/

Classroom Climate

JHU is committed to creating a classroom environment that values the diversity of experiences and perspectives that all students bring. Everyone has the right to be treated with dignity and respect. Fostering an inclusive climate is important. Research and experience show that students who interact with peers who are different from themselves learn new things and experience tangible educational outcomes. At no time in this learning process should someone be singled out or treated unequally on the basis of any seen or unseen part of their identity. 
 
If you have concerns in this course about harassment, discrimination, or any unequal treatment, or if you seek accommodations or resources, please reach out to the course instructor directly. Reporting will never impact your course grade. You may also share concerns with your program chair, the Assistant Dean for Diversity and Inclusion, or the Office of Institutional Equity. In handling reports, people will protect your privacy as much as possible, but faculty and staff are required to officially report information for some cases (e.g. sexual harassment).

Course Auditing

When a student enrolls in an EP course with “audit” status, the student must reach an understanding with the instructor as to what is required to earn the “audit.” If the student does not meet those expectations, the instructor must notify the EP Registration Team [EP-Registration@exchange.johnshopkins.edu] in order for the student to be retroactively dropped or withdrawn from the course (depending on when the "audit" was requested and in accordance with EP registration deadlines). All lecture content will remain accessible to auditing students, but access to all other course material is left to the discretion of the instructor.