You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This repository contains all of the code and software labs for [MIT 6.S191: Introduction to Deep Learning](http://introtodeeplearning.com)! All lecture slides and videos are available on the course website.
3
+
This repository contains all of the code and software labs for [MIT Introduction to Deep Learning](http://introtodeeplearning.com)! All lecture slides and videos are available on the program website.
4
4
5
5
# Instructions
6
-
6.S191 software labs are designed to be completed at your own pace. At the end of each of the labs, there will be instructions on how you can submit your notebook for grade. Additionally, if you would like to submit your lab as part of the 6.S191 lab competitions, instructions regarding what information must be submitted is also provided at the end of each lab.
6
+
MIT Introduction to Deep Learning software labs are designed to be completed at your own pace. At the end of each of the labs, there will be instructions on how you can submit your materials as part of the lab competitions. These instructions include what information must be submitted and in what format.
7
7
8
8
## Opening the labs in Google Colaboratory:
9
9
10
-
The 2022 6.S191 labs will be run in Google's Colaboratory, a Jupyter notebook environment that runs entirely in the cloud, you don't need to download anything. To run these labs, you must have a Google account.
10
+
The 2023 Introduction to Deep Learning labs will be run in Google's Colaboratory, a Jupyter notebook environment that runs entirely in the cloud, so you don't need to download anything. To run these labs, you must have a Google account.
11
11
12
12
On this Github repo, navigate to the lab folder you want to run (`lab1`, `lab2`, `lab3`) and open the appropriate python notebook (\*.ipynb). Click the "Run in Colab" link on the top of the lab. That's it!
13
13
@@ -30,17 +30,17 @@ We do this for you in each of the labs, but the package is also open source unde
All lecture videos are available publicly online and linked above! Use and/or modification of lecture slides outside of 6.S191 must reference:
33
+
All lecture videos are available publicly online and linked above! Use and/or modification of lecture slides outside of MIT Introduction to Deep Learning must reference:
All code in this repository is copyright 2022[MIT 6.S191 Introduction to Deep Learning](http://introtodeeplearning.com). All Rights Reserved.
40
+
All code in this repository is copyright 2023[MIT Introduction to Deep Learning](http://introtodeeplearning.com). All Rights Reserved.
41
41
42
-
Licensed under the MIT License. You may not use this file except in compliance with the License. Use and/or modification of this code outside of 6.S191 must reference:
42
+
Licensed under the MIT License. You may not use this file except in compliance with the License. Use and/or modification of this code outside of MIT Introduction to Deep Learning must reference:
"TensorFlow is a software library extensively used in machine learning. Here we'll learn how computations are represented and how to define a simple neural network in TensorFlow. For all the labs in 6.S191 2022, we'll be using the latest version of TensorFlow, TensorFlow 2, which affords great flexibility and the ability to imperatively execute operations, just like in Python. You'll notice that TensorFlow 2 is quite similar to Python in its syntax and imperative execution. Let's install TensorFlow and a couple of dependencies.\n"
73
+
"TensorFlow is a software library extensively used in machine learning. Here we'll learn how computations are represented and how to define a simple neural network in TensorFlow. For all the labs in Introduction to Deep Learning 2023, we'll be using the latest version of TensorFlow, TensorFlow 2, which affords great flexibility and the ability to imperatively execute operations, just like in Python. You'll notice that TensorFlow 2 is quite similar to Python in its syntax and imperative execution. Let's install TensorFlow and a couple of dependencies.\n"
74
74
]
75
75
},
76
76
{
@@ -82,7 +82,7 @@
82
82
"%tensorflow_version 2.x\n",
83
83
"import tensorflow as tf\n",
84
84
"\n",
85
-
"# Download and import the MIT 6.S191 package\n",
85
+
"# Download and import the MIT Introduction to Deep Learning package\n",
"# Download and import the MIT Introduction to Deep Learning package\n",
91
91
"!pip install mitdeeplearning\n",
92
92
"import mitdeeplearning as mdl\n",
93
93
"\n",
@@ -932,13 +932,15 @@
932
932
"* What if you alter or augment the dataset? \n",
933
933
"* Does the choice of start string significantly affect the result? \n",
934
934
"\n",
935
-
"Try to optimize your model and submit your best song! **MIT students and affiliates will be eligible for prizes during the IAP offering**. To enter the competition, MIT students and affiliates should upload the following to the course Canvas:\n",
935
+
"Try to optimize your model and submit your best song! **Participants will be eligible for prizes during the January 2023 offering. To enter the competition, you must upload the following to [this submission link](https://www.dropbox.com/request/Xj9iI1JXLsDy5FWgug7s):**\n",
936
936
"\n",
937
937
"* a recording of your song;\n",
938
938
"* iPython notebook with the code you used to generate the song;\n",
939
939
"* a description and/or diagram of the architecture and hyperparameters you used -- if there are any additional or interesting modifications you made to the template code, please include these in your description.\n",
940
940
"\n",
941
-
"You can also tweet us at [@MITDeepLearning](https://twitter.com/MITDeepLearning) a copy of the song! See this example song generated by a previous 6.S191 student (credit Ana Heart): <a href=\"https://twitter.com/AnaWhatever16/status/1263092914680410112?s=20\">song from May 20, 2020.</a>\n",
941
+
"**Name your file in the following format: ``[FirstName]_[LastName]_RNNMusic``, followed by the file format (.zip, .mp4, .ipynb, .pdf, etc). ZIP files of all three components are preferred over individual files. If you submit individual files, you must name the individual files according to the above nomenclature.**\n",
942
+
"\n",
943
+
"You can also tweet us at [@MITDeepLearning](https://twitter.com/MITDeepLearning) a copy of the song (but this will not enter you into the competition)! See this example song generated by a previous student (credit Ana Heart): <a href=\"https://twitter.com/AnaWhatever16/status/1263092914680410112?s=20\">song from May 20, 2020.</a>\n",
"TensorFlow is a software library extensively used in machine learning. Here we'll learn how computations are represented and how to define a simple neural network in TensorFlow. For all the labs in 6.S191 2022, we'll be using the latest version of TensorFlow, TensorFlow 2, which affords great flexibility and the ability to imperatively execute operations, just like in Python. You'll notice that TensorFlow 2 is quite similar to Python in its syntax and imperative execution. Let's install TensorFlow and a couple of dependencies.\n"
72
+
"TensorFlow is a software library extensively used in machine learning. Here we'll learn how computations are represented and how to define a simple neural network in TensorFlow. For all the labs in Introduction to Deep Learning 2023, we'll be using the latest version of TensorFlow, TensorFlow 2, which affords great flexibility and the ability to imperatively execute operations, just like in Python. You'll notice that TensorFlow 2 is quite similar to Python in its syntax and imperative execution. Let's install TensorFlow and a couple of dependencies.\n"
73
73
]
74
74
},
75
75
{
@@ -81,7 +81,7 @@
81
81
"%tensorflow_version 2.x\n",
82
82
"import tensorflow as tf\n",
83
83
"\n",
84
-
"# Download and import the MIT 6.S191 package\n",
84
+
"# Download and import the MIT Introduction to Deep Learning package\n",
0 commit comments