{"id":13427154,"url":"https://github.com/hse-aml/intro-to-dl","last_synced_at":"2025-05-16T10:08:35.434Z","repository":{"id":62221859,"uuid":"107039749","full_name":"hse-aml/intro-to-dl","owner":"hse-aml","description":"Resources for \"Introduction to Deep Learning\" course.","archived":false,"fork":false,"pushed_at":"2020-09-09T18:00:36.000Z","size":6359,"stargazers_count":759,"open_issues_count":14,"forks_count":715,"subscribers_count":56,"default_branch":"master","last_synced_at":"2025-04-09T05:03:17.215Z","etag":null,"topics":["deep-learning"],"latest_commit_sha":null,"homepage":"https://www.coursera.org/learn/intro-to-deep-learning","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hse-aml.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-10-15T18:53:05.000Z","updated_at":"2025-03-16T17:50:14.000Z","dependencies_parsed_at":"2022-10-28T18:00:43.761Z","dependency_job_id":null,"html_url":"https://github.com/hse-aml/intro-to-dl","commit_stats":null,"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hse-aml%2Fintro-to-dl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hse-aml%2Fintro-to-dl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hse-aml%2Fintro-to-dl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hse-aml%2Fintro-to-dl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hse-aml","download_url":"https://codeload.github.com/hse-aml/intro-to-dl/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254509477,"owners_count":22082892,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning"],"created_at":"2024-07-31T00:01:55.145Z","updated_at":"2025-05-16T10:08:30.418Z","avatar_url":"https://github.com/hse-aml.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# Introduction to Deep Learning course resources\nhttps://www.coursera.org/learn/intro-to-deep-learning\n\n## Running on Google Colab (tested for all weeks)\nGoogle has released its own flavour of Jupyter called Colab, which has free GPUs!\n\nHere's how you can use it:\n1. Open https://colab.research.google.com, click **Sign in** in the upper right corner, use your Google credentials to sign in.\n2. Click **GITHUB** tab, paste https://github.com/hse-aml/intro-to-dl and press Enter\n3. Choose the notebook you want to open, e.g. week2/v2/mnist_with_keras.ipynb\n4. Click **File -\u003e Save a copy in Drive...** to save your progress in Google Drive\n5. Click **Runtime -\u003e Change runtime type** and select **GPU** in Hardware accelerator box\n6. **Execute** the following code in the first cell that downloads dependencies (change for your week number):\n```python\n! shred -u setup_google_colab.py\n! wget https://raw.githubusercontent.com/hse-aml/intro-to-dl/master/setup_google_colab.py -O setup_google_colab.py\nimport setup_google_colab\n# please, uncomment the week you're working on\n# setup_google_colab.setup_week1()\n# setup_google_colab.setup_week2()\n# setup_google_colab.setup_week2_honor()\n# setup_google_colab.setup_week3()\n# setup_google_colab.setup_week4()\n# setup_google_colab.setup_week5()\n# setup_google_colab.setup_week6()\n```\n7. If you run many notebooks on Colab, they can continue to eat up memory,\nyou can kill them with `! pkill -9 python3` and check with `! nvidia-smi` that GPU memory is freed.\n\n**Known issues:**\n* Blinking animation with `IPython.display.clear_output()`.\nIt's usable, but still looking for a workaround.\n\n## Offline instructions\nCoursera Jupyter Environment can be slow if many learners use it heavily. \nOur tasks are compute-heavy and we recommend to run them on your hardware for optimal performance.\n\nYou will need a computer with at least 4GB of RAM.\n\nThere're two options to setup the Jupyter Notebooks locally: Docker container and Anaconda.\n\n### Docker container option (best for Mac/Linux)\n\nFollow the instructions on https://hub.docker.com/r/zimovnov/coursera-aml-docker/ to install Docker container with all necessary software installed.\n\nAfter that you should see a Jupyter page in your browser.\n\n### Anaconda option (best for Windows)\nWe highly recommend to install docker environment, but if it's not an option, \nyou can try to install the necessary python modules with Anaconda.\n\nFirst, install Anaconda with **Python 3.5+** from [here](https://www.anaconda.com/download).\n\nDownload `conda_requirements.txt` from [here](https://github.com/ZEMUSHKA/coursera-aml-docker/blob/master/conda_requirements.txt).\n\nOpen terminal on Mac/Linux or \"Anaconda Prompt\" in Start Menu on Windows and run:\n```\nconda config --append channels conda-forge\nconda config --append channels menpo\nconda install --yes --file conda_requirements.txt\n```\n\nTo start Jupyter Notebooks run `jupyter notebook` on Mac/Linux or \"Jupyter Notebook\" in Start Menu on Windows.\n\nAfter that you should see a Jupyter page in your browser.\n\n### Prepare resources inside Jupyter Notebooks (for local setups only)\n\nClick **New -\u003e Terminal** and execute: `git clone https://github.com/hse-aml/intro-to-dl.git`\nOn Windows you might want to install [Git](https://git-scm.com/download/win). \nYou can also download all the resources as zip archive from GitHub page.\n\nClose the terminal and refresh Jupyter page, you will see **intro-to-dl** folder, go there, \nall the necessary notebooks are waiting for you.\n\nFirst you need to download necessary resources, to do that open `download_resources.ipynb` \nand run cells for Keras and your week.\n\nNow you can open a notebook for the corresponding week and work there just like in Coursera Jupyter Environment.\n\n### Using GPU for offline setup (for advanced users)\n- If you have a **Linux host** you can try these instructions for Docker: \nhttps://github.com/ZEMUSHKA/coursera-aml-docker#using-gpu-in-your-container-linux-hosts-only\n- The easiest way is to go with Anaconda setup, \nthat doesn't need virtualization and \nthus works with a GPU on all platforms (including Windows and Mac). \nYou will still have to install NVIDIA GPU driver, CUDA toolkit and CuDNN \n(requires registration with NVIDIA) \non your host machine in order for TensorFlow to work with your GPU: \nhttps://www.tensorflow.org/versions/r1.2/install/install_linux#nvidia_requirements_to_run_tensorflow_with_gpu_support\nIt can be hard to follow, so you might choose to stick to a CPU version, \nwhich is also fine for the purpose of this course.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhse-aml%2Fintro-to-dl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhse-aml%2Fintro-to-dl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhse-aml%2Fintro-to-dl/lists"}