Skip to content

sigmunjr/TEK5030_deep_learning

Repository files navigation

TEK5030_deep_learning

This week we have 3 exercises. They each have a python notebook, which is a set of instructions and code you can run. They are ment to be run in colab. There you have access to a powerfull GPU, and you don't need any additional setup. You do need Google account to run the notebooks in colab.

(not recommended) Alternatively you could use https://www.kaggle.com/notebooks to run the notebooks, or you can install and run jupyter notebook on your own machine.

Enable GPU in colab

For the best experience you'll need to enable GPUs for the notebook:

  • Navigate to Edit→Notebook Settings
  • select GPU from the Hardware Accelerator drop-down

I also recommend to click "Copy in drive" to run the code in your own Google Drive

Learn more about Tensorflow

On tensorflow.org/tutorials can you find lots of learning material and good tutorials.

If you find our exercises hard, it could be a good idea to check out one of the tensorflow tutorials, as they are much more in depth.

Exercise 1: Simple Convolutional Neural network (CNN)

Open exercise in colabTEK5030_deep_learning_EX1.ipynb

Read in github (cannot run) TEK5030_deep_learning_EX1.ipynb

Exercise 2: Live training

Open exercise in colabTEK5030_deep_learning_EX2.ipynb

Read in github (cannot run) TEK5030_deep_learning_EX2.ipynb

Exercise 3: Segmentation

Open exercise in colabTEK5030_deep_learning_EX3.ipynb

Read in github (cannot run) TEK5030_deep_learning_EX3.ipynb

Solutions

TEK5030_deep_learning_EX1_solutions.ipynb

TEK5030_deep_learning_EX2_solution.ipynb

TEK5030_deep_learning_EX3_solutions.ipynb

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published