{"id":17267179,"url":"https://github.com/agamiko/100-days-of-code","last_synced_at":"2026-01-05T19:42:20.512Z","repository":{"id":101298589,"uuid":"258176584","full_name":"AgaMiko/100-days-of-code","owner":"AgaMiko","description":"My 100 days journey with coding to improve my Machine Learning, Deep Learning, Data Science skills","archived":false,"fork":false,"pushed_at":"2020-05-04T11:35:37.000Z","size":813,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-01-31T12:22:30.078Z","etag":null,"topics":["acoustics","computer-vision","data-science","deep-learning","image-processing","machine-learning","natural-language-processing","neural-networks"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AgaMiko.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-04-23T11:05:45.000Z","updated_at":"2024-04-30T06:12:31.000Z","dependencies_parsed_at":null,"dependency_job_id":"9d211156-e405-4028-bcfd-96a5caa02ead","html_url":"https://github.com/AgaMiko/100-days-of-code","commit_stats":{"total_commits":9,"total_committers":3,"mean_commits":3.0,"dds":0.4444444444444444,"last_synced_commit":"116b32cd0c0979f26ab008dfe7abebaf5886c215"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgaMiko%2F100-days-of-code","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgaMiko%2F100-days-of-code/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgaMiko%2F100-days-of-code/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgaMiko%2F100-days-of-code/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AgaMiko","download_url":"https://codeload.github.com/AgaMiko/100-days-of-code/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245641437,"owners_count":20648644,"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":["acoustics","computer-vision","data-science","deep-learning","image-processing","machine-learning","natural-language-processing","neural-networks"],"created_at":"2024-10-15T08:09:47.492Z","updated_at":"2026-01-05T19:42:20.467Z","avatar_url":"https://github.com/AgaMiko.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# 100-days-of-code\nMy 100 days journey with coding to improve my Machine Learning, Deep Learning, Data Science skills. Posting current updates on twitter: https://twitter.com/AgnMikolajczyk\n\n## Day 1\nI continued with wav2wav #autoencoder for audio style transfer. Loss decreased gradually during the training, so I've started writing audio generation script Nuty Also, I've added json configuration files with parameters of e.g. melspectrogram.\n\n![](images/wav2wav.PNG)\n\n* Wav2wav autoencoder: https://arxiv.org/pdf/1904.08983.pdf\n\n## Day 2\nHad a little fun with casual convolutions in wav-to-wav autoencoder in #pytorch. Reimplemented\u0026tried to understand it better. Later, experimented a bit with different architectures.\n\n* Casual convolutions: https://medium.com/the-artificial-impostor/notes-understanding-tensorflow-part-3-7f6633fcc7c7\n\n## Day 3\nI came up with an idea for a fun project  after working hours. I always wanted to train GANs but popular datasets seemed boring -\u003e I started scraping data with Selenium! It's my first time trying it out and first successfully clicked button felt awesome\n\n* Selenium: https://www.selenium.dev/\n* Selenium for data scraping: https://medium.com/the-andela-way/introduction-to-web-scraping-using-selenium-7ec377a8cf72\n* BeautifulSoup: https://www.crummy.com/software/BeautifulSoup/bs4/doc/\n\n## Day 4\nStarted generating random RPG-like pixel characters with LPC spritesheet: http://tinyurl.com/yb6yg7kw. I'm creating my own dataset for my experiment with Generative Adversarial Networks. Soon I'll start implementing it in #pytorch \n\n* LPC spritesheet: http://tinyurl.com/yb6yg7kw.\n* Pytorch: https://pytorch.org/\n\nMy notebooks:\n* [Download random spritesheet with Selenium](https://github.com/AgaMiko/pixel_character_generator/blob/master/notebooks/1_download_random_spritesheet.ipynb)\n* [Extract character from spritesheet](https://github.com/AgaMiko/pixel_character_generator/blob/master/notebooks/2_extract_character.ipynb)\n\n ![](images/58.png)  ![](images/58_2.png)  ![](images/58_3.png)  ![](images/58_4.png)\n ![](images/212.png)  ![](images/212_2.png)  ![](images/212_3.png)  ![](images/212_4.png)\n ![](images/584.png)  ![](images/584_2.png)  ![](images/584_3.png)  ![](images/584_4.png)\n\n## Day 5\nImplemented DCGAN from pytorch tutorial.\n  * Experimented with latent size (input for Generator) and feature map sizes \n  * Added soft and noisy labels\n  * Added Wasserstein loss which is a good solution for mode collapse\n    * Wasserstein loss - https://developers.google.com/machine-learning/gan/loss\n    * mode collapse - https://machinelearningmastery.com/practical-guide-to-gan-failure-modes/\n  * Added dropout in both generator and discriminator\n\n* [DCGAN Tutorial](https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html)\n\n### Dataset\n![](images/random_chars.png)\n\n* [Download dataset here](https://github.com/AgaMiko/pixel_character_generator)\n\n\n### Results\n* [My final code with modified DCGAN](https://github.com/AgaMiko/pixel_character_generator/blob/master/notebooks/3_DCGAN.ipynb)\n\n ![](images/real_fake.png)\n \n## Day 6\nToday practiced a bit with custom data loaders in pytorch: https://pytorch.org/tutorials/beginner/data_loading_tutorial.html\nStarted writing generator code for my wav-to-wav autoencoder.\n\n## Day 7\nFirst week finished! Today, I've experimented with a XLA for TPU with multiprocessing, the notebook shared on Kaggle for Flower classification challenge.  https://kaggle.com/dhananjay3/fast-pytorch-xla-for-tpu-with-multiprocessing\nhttps://www.kaggle.com/c/flower-classification-with-tpus/notebooks?sortBy=relevance\u0026group=everyone\u0026search=pytorch\u0026page=1\u0026pageSize=20\u0026competitionId=18278\n\n## Day 8\nContinued having fun with #GenerativeAdversarialNetwork - this time Conditional GANs on retro pixel game dataset - http://github.com/AgaMiko/pixel_character_generator\nI've managed to modify code and run the training, can't wait to see the results\n\n## Day 9\nToday finished Conditional DCGAN experiments! GAN generates a pixel character seen from selected angle.\n\n* different learning rate for discriminator and generator\n* soft labels\n* added classification loss to the discriminator. Discriminator have to guess fake/real but also the character angle\n* generator is conditioned with embedding from trainable look-up table that gives the info about the character view angle\n\n![](https://github.com/AgaMiko/pixel_character_generator/blob/master/images/CGAN.PNG)\n\n* [notebook with modified Conditional DCGAN](https://github.com/AgaMiko/pixel_character_generator/blob/master/notebooks/4_Conditional_DCGAN.ipynb)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagamiko%2F100-days-of-code","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fagamiko%2F100-days-of-code","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagamiko%2F100-days-of-code/lists"}