{"id":16420207,"url":"https://github.com/geekquad/deep-dream","last_synced_at":"2025-06-17T02:32:46.393Z","repository":{"id":110635439,"uuid":"267619061","full_name":"geekquad/Deep-Dream","owner":"geekquad","description":"A computer vision program which uses a convolutional neural network to find and enhance patterns in images, thus creating a dream-like hallucinogenic appearance in the deliberately over-processed images.","archived":false,"fork":false,"pushed_at":"2020-06-01T05:07:20.000Z","size":9791,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-08T03:01:43.962Z","etag":null,"topics":["cnn","computer-vision","convolutional-neural-networks","deep-learning","pytorch","style-transfer","textures","vgg-19"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/geekquad.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":"2020-05-28T14:57:03.000Z","updated_at":"2021-04-22T18:53:57.000Z","dependencies_parsed_at":"2023-06-03T09:00:51.293Z","dependency_job_id":null,"html_url":"https://github.com/geekquad/Deep-Dream","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/geekquad/Deep-Dream","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/geekquad%2FDeep-Dream","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/geekquad%2FDeep-Dream/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/geekquad%2FDeep-Dream/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/geekquad%2FDeep-Dream/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/geekquad","download_url":"https://codeload.github.com/geekquad/Deep-Dream/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/geekquad%2FDeep-Dream/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260277421,"owners_count":22985097,"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":["cnn","computer-vision","convolutional-neural-networks","deep-learning","pytorch","style-transfer","textures","vgg-19"],"created_at":"2024-10-11T07:27:14.230Z","updated_at":"2025-06-17T02:32:46.384Z","avatar_url":"https://github.com/geekquad.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep-Dream:\nIt is a computer vision program which uses a convolutional neural network to find and enhance patterns in images, thus creating a dream-like hallucinogenic appearance in the deliberately over-processed images. \n\u003cp\u003e It adapts the input images to match the network weights with gradient ascent which results in visualizing network filters on the input images giving them psychodelic look. \u003c/p\u003e\n\u003cp\u003e This notebook recreates a style transfer method that is outlined in the paper\n  \u003ca href=\"https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Gatys_Image_Style_Transfer_CVPR_2016_paper.pdf\"\u003e Image Style Transfer Using Convolutional Neural Networks, by Gatys \u003c/a\u003e in PyTorch.\n  \u003cp\u003e \u003ch2\u003e Style Transfer: \u003c/h2\u003e \u003c/p\u003e\n  \u003cp\u003e Style transfer relies on separating the content and style of an image. Given one content image and one style image, we aim to create a new, target image which should contain our desired content and style components:\n\u003cul\u003e\n\u003cli\u003e objects and their arrangement are similar to that of the content image \u003c/li\u003e\n\u003cli\u003e style, colors, and textures are similar to that of the style image \u003c/li\u003e \u003c/ul\u003e\n\n\u003cp\u003e \u003ch4\u003e Example: \u003c/h4\u003e \u003c/p\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/geekquad/deep-learning-v2-pytorch/master/style-transfer/notebook_ims/style_tx_cat.png\"\u003e\n\u003cp\u003e An example is shown, where the content image is of a cat, and the style image is of Hokusai's Great Wave. The generated target image still contains the cat but is stylized with the waves, blue and beige colors, and block print textures of the style image. \u003c/p\u003e\n\u003ch2\u003e VGG-19: \u003c/h2\u003e\n\u003c/p\u003e\n\u003cp\u003e Using VGG-19 as a feature extractor and \nusing backpropogation to minimize a defined loss function between our target and content images.\nNot training it to produce a specific output. \u003c/p\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/geekquad/deep-learning-v2-pytorch/master/style-transfer/notebook_ims/vgg19_convlayers.png\"\u003e\n\u003cp\u003e The above image shows the various layers of the model VGG-19. \u003c/p\u003e\n\u003cp\u003e \u003ch2\u003e Some of the Images that I played with: \u003c/h2\u003e \u003c/p\u003e\n\u003cimg src=\"https://drive.google.com/uc?id=16p1AvIuFERLoGoaDAN3YOctL_03vVoTL\"\u003e\n\u003cimg src=\"https://drive.google.com/uc?id=1agLnlaOIKpAg3YG9hMnqEn6cMdDnfrLA\"\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgeekquad%2Fdeep-dream","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgeekquad%2Fdeep-dream","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgeekquad%2Fdeep-dream/lists"}