Skip to content

Commit 3bf222c

Browse files
committed
Set up repo for intro to cv series
1 parent 1f1b2da commit 3bf222c

File tree

6 files changed

+388
-0
lines changed

6 files changed

+388
-0
lines changed
Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
title: "Intro to CV Workshop Series"
2+
description: "This workshop series will teach you the fundamentals of machine leraning and computer vision. We will cover neural networks, CNNs, and more."
28.4 KB
Loading
26.6 KB
Loading
Lines changed: 132 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,132 @@
1+
<!--
2+
If you have any questions about this template, feel free to ask
3+
your Director for help!
4+
-->
5+
6+
7+
<!--
8+
SECTION: Header
9+
---------
10+
Request new headers from you Director to fit your workshop!
11+
-->
12+
13+
![Alt Text (Intro to CV Workshop Series)](./Default_Main_Header_Light.png#gh-light-mode-only)
14+
![Alt Text (Intro to CV Workshop Series)](./Default_Main_Header_Dark.png#gh-dark-mode-only)
15+
16+
The official ACM AI **Intro to Computer Vision Workshop Series** repository.
17+
18+
<!--
19+
SECTION: Table of Contents
20+
---------
21+
Mandatory Sections:
22+
- File Directory Structure
23+
- Getting Started
24+
- Give an interesting description of your workshop!
25+
- E.g. you can use the marketing descriptiong (w/o the emojis
26+
and make the nouns general ('you' becomes 'the reader'))
27+
- Resources
28+
- Images, papers, etc
29+
Other Possible Sections:
30+
- Datasets
31+
- Separate from 'Resources' to distinguish between inspiration and
32+
things like datasets used in a notebook
33+
- Anything else you'd like, but try not to be redundant!
34+
-->
35+
36+
<!--
37+
SECTION: File Directory Structure
38+
---------
39+
Write out your File Directory Structure below (make sure it's up-to-date)
40+
-->
41+
42+
# 1. File Directory Structure
43+
44+
```bash
45+
intro-cv-series
46+
| -- workshop-1
47+
| -- [Workshop 1 Resources]
48+
| -- ...
49+
| -- Default_Main_Header_Dark.png
50+
| -- Default_Main_Header_Light.png
51+
| -- ...
52+
| -- README.md
53+
```
54+
55+
<!--
56+
SECTION: Getting Started
57+
---------
58+
Brief description of your workshop here
59+
-->
60+
61+
# 2. Getting Started
62+
63+
## 2.1 Workshop 1 - Intro to CV: Pytorch and Neural Networks
64+
65+
<!--
66+
You can write something up for each worksop or use their marketing descriptions.
67+
-->
68+
69+
An introduction to Pytorch, basic machine learning formulations, and neural networks. This workshop will lead students through developing a multi layer neural network to classify handwritten digits from the MNIST dataset, and provide the foundation and intuitions for students to begin tackling basic computer vision problems on their own, and empower their own learning.
70+
71+
Slides:
72+
<!--
73+
SECTION: Resources
74+
---------
75+
Make sure to cite everything you use, whether directly or for inspiration!
76+
-->
77+
78+
## 2.2 Workshop 2 - Intro to CV: Convolutional Neural Networks
79+
80+
<!--
81+
You can write something up for each worksop or use their marketing descriptions.
82+
-->
83+
84+
N/A
85+
86+
Slides:
87+
<!--
88+
SECTION: Resources
89+
---------
90+
Make sure to cite everything you use, whether directly or for inspiration!
91+
-->
92+
93+
## 2.3 Workshop 3 - Intro to CV
94+
95+
<!--
96+
You can write something up for each worksop or use their marketing descriptions.
97+
-->
98+
99+
N/A
100+
101+
Slides:
102+
103+
<!--
104+
SECTION: Resources
105+
---------
106+
Make sure to cite everything you use, whether directly or for inspiration!
107+
-->
108+
109+
# 3. Resources
110+
111+
## 3.1 Workshop 1 - Intro to CV: Pytorch and Neural Networks
112+
113+
-
114+
115+
## 3.2 Workshop 2 - Intro to CV: Convolutional Neural Networks
116+
117+
## 3.3 Workshop 3 - Intro to CV
118+
119+
120+
<!--
121+
SECTION: Author Info
122+
---------
123+
Make sure to give yourself credit for your work by listing yourself and
124+
your partners below! Add your LinkedIn and GitHub!
125+
-->
126+
127+
# 4. Author Info
128+
129+
- Alan Li: [LinkedIn](https://www.linkedin.com/in/alan-li-2001/) | [GitHub](https://github.com/yuyeon)
130+
- Stefanie Dao: [LinkedIn](https://www.linkedin.com/in/stefanie-dao/) | [GitHub](https://github.com/StefanieDao)
131+
- Weiji
132+
- Arth Shukla: [Site](https://arth.website/) | [LinkedIn](https://www.linkedin.com/in/arth-shukla/) | [GitHub](https://github.com/arth-shukla)
Lines changed: 144 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,144 @@
1+
{
2+
"nbformat": 4,
3+
"nbformat_minor": 0,
4+
"metadata": {
5+
"colab": {
6+
"provenance": []
7+
},
8+
"kernelspec": {
9+
"name": "python3",
10+
"display_name": "Python 3"
11+
},
12+
"language_info": {
13+
"name": "python"
14+
}
15+
},
16+
"cells": [
17+
{
18+
"cell_type": "markdown",
19+
"source": [
20+
"# Intro to CV Workshop 1: Getting Started with Computer Vision"
21+
],
22+
"metadata": {
23+
"id": "lrPpS1rpCK-h"
24+
}
25+
},
26+
{
27+
"cell_type": "markdown",
28+
"source": [
29+
"## Section 1 - Overview of Computer Vision\n"
30+
],
31+
"metadata": {
32+
"id": "X_yXZfg-9Fa-"
33+
}
34+
},
35+
{
36+
"cell_type": "markdown",
37+
"source": [
38+
"### 1.1 Introduction of Computer Vision\n"
39+
],
40+
"metadata": {
41+
"id": "t-rte0n6Jrn5"
42+
}
43+
},
44+
{
45+
"cell_type": "markdown",
46+
"source": [
47+
" ### 1.2 The MNIST Dataset"
48+
],
49+
"metadata": {
50+
"id": "LAy-avyOKTPw"
51+
}
52+
},
53+
{
54+
"cell_type": "markdown",
55+
"source": [
56+
"## Section 2 - Basics of basics"
57+
],
58+
"metadata": {
59+
"id": "TknP7gWmCJvB"
60+
}
61+
},
62+
{
63+
"cell_type": "markdown",
64+
"source": [
65+
"### 2.1 Pytorch Basics"
66+
],
67+
"metadata": {
68+
"id": "xClsDXlOJNZM"
69+
}
70+
},
71+
{
72+
"cell_type": "markdown",
73+
"source": [
74+
"### 2.2 Model Training and Evaluation"
75+
],
76+
"metadata": {
77+
"id": "vKDff4XKJgx_"
78+
}
79+
},
80+
{
81+
"cell_type": "markdown",
82+
"source": [
83+
"## Section 3 - Formulating a Machine Learning problem "
84+
],
85+
"metadata": {
86+
"id": "pcibKmYR_OTW"
87+
}
88+
},
89+
{
90+
"cell_type": "markdown",
91+
"source": [
92+
"(feel free to edit the outline)"
93+
],
94+
"metadata": {
95+
"id": "tIpm_ep-K3lQ"
96+
}
97+
},
98+
{
99+
"cell_type": "markdown",
100+
"source": [
101+
"### 3.1 Set up MLP Architecture (NN layers, activation function)\n"
102+
],
103+
"metadata": {
104+
"id": "hanQrmfxCH5C"
105+
}
106+
},
107+
{
108+
"cell_type": "markdown",
109+
"source": [
110+
"### 3.2 Loss function and Regularization (L1/L2/Dropout)"
111+
],
112+
"metadata": {
113+
"id": "k2zSw1jLKvM9"
114+
}
115+
},
116+
{
117+
"cell_type": "markdown",
118+
"source": [
119+
"### 3.3 Learning and Evaluation (Gradient Descent, SGD)\n"
120+
],
121+
"metadata": {
122+
"id": "ZAqFgipcKx6S"
123+
}
124+
},
125+
{
126+
"cell_type": "markdown",
127+
"source": [
128+
"## Section 4 - Making a MLP piece-by-piece"
129+
],
130+
"metadata": {
131+
"id": "7gJNzxuBLDyv"
132+
}
133+
},
134+
{
135+
"cell_type": "markdown",
136+
"source": [
137+
"## Section 5 - Putting it together for CV (Can change this later)"
138+
],
139+
"metadata": {
140+
"id": "tbIiaUguLUoU"
141+
}
142+
}
143+
]
144+
}
Lines changed: 110 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,110 @@
1+
<!--
2+
If you have any questions about this template, feel free to ask
3+
your Director for help!
4+
-->
5+
6+
7+
<!--
8+
SECTION: Header
9+
---------
10+
Request new headers from you Director to fit your workshop!
11+
-->
12+
13+
![Intro to CV: Search Algorithms](./figures/W1_Header_Light.png#gh-light-mode-only)
14+
![Intro to CV: Search Algorithms](./figures/W1_Header_Dark.png#gh-dark-mode-only)
15+
16+
The official ACM AI **Intro to CV: Pytorch and Neural Networks** repository. Here you can find the slides and notebook for the workshop. Feel free to go through it yourself to learn how to train a neural network for classifying handwritten digits!
17+
18+
<!--
19+
SECTION: Table of Contents
20+
---------
21+
Mandatory Sections:
22+
- File Directory Structure
23+
- Workshop Recording
24+
- if you recorded your workshop, please make it available here
25+
- Getting Started
26+
- Give an interesting description of your workshop!
27+
- E.g. you can use the marketing descriptiong (w/o the emojis
28+
and make the nouns general ('you' becomes 'the reader'))
29+
- Resources
30+
- Images, papers, etc
31+
Do NOT Include:
32+
- Author Info
33+
- This should only be in the main README for your series
34+
Other Possible Sections:
35+
- Anything else you'd like, but try not to be redundant!
36+
- Make sure it's not already in the main series README or
37+
another section
38+
-->
39+
40+
<!--
41+
SECTION: Workshop Video
42+
---------
43+
Most, if not all, workshops should have recordings. Once the recording
44+
is posted to the ACMUCSD YT channel (https://www.youtube.com/channel/UCyjPATFqc3FwOiuqJ2UG1Eg), replace the text with an <img> element.
45+
-->
46+
47+
# 1. Getting Started
48+
49+
<!--
50+
You can write something up or use the marketing description.
51+
-->
52+
53+
## 1.1 Environment Setup
54+
55+
```
56+
conda env create -f environment.yaml
57+
conda activate ai
58+
```
59+
60+
Workshop "Intro to CV: Neural Networks" consists of 2 components:
61+
- [Notebook](<!-- Local Path to Notebook -->) with completed code and explanations.
62+
- [Slide Deck](<!-- Local Path to Slide Deck -->) for the presentation slides
63+
64+
<!--
65+
Note: The above list will depend on your specific workshop.
66+
-->
67+
68+
69+
# 2. Workshop Video
70+
71+
*Will be added as soon as uploaded to YouTube*
72+
73+
<!--
74+
<div align="center">
75+
<a href="YT Video Link">
76+
<img
77+
src="YT Max Res Thumbnail Link"
78+
alt="Screen reader-compatible alt text"
79+
width="500px"
80+
/>
81+
</a>
82+
</div>
83+
-->
84+
85+
<!--
86+
SECTION: File Directory Structure
87+
---------
88+
Write out your File Directory Structure below (make sure it's up-to-date)
89+
-->
90+
91+
# 3. File Directory Structure
92+
93+
```bash
94+
intro-ai-series
95+
| -- figures
96+
| -- DefaultW1_Header_Dark.png
97+
| -- DefaultW1_Header_Light.png
98+
| -- src
99+
| -- videos # where the videos of our agent traversing the FrozenLake grid are stored
100+
| -- main.py # calls the core search algorithms
101+
| -- search.py # where we define the core search algorithms for our AI agent
102+
| -- test.py # for testing determinstic trajectories in FrozenLake enviroment
103+
| -- README.md
104+
```
105+
106+
<!--
107+
SECTION: Getting Started
108+
---------
109+
Brief description of your workshop here
110+
-->

0 commit comments

Comments
 (0)