{"id":23103896,"url":"https://github.com/moatifbutt/cs867-assignment3","last_synced_at":"2025-04-03T21:44:44.599Z","repository":{"id":247245772,"uuid":"327625291","full_name":"moatifbutt/CS867-Assignment3","owner":"moatifbutt","description":null,"archived":false,"fork":false,"pushed_at":"2021-01-07T17:45:57.000Z","size":1540,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-09T09:44:00.015Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/moatifbutt.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-01-07T13:48:56.000Z","updated_at":"2021-01-07T17:45:59.000Z","dependencies_parsed_at":"2024-07-07T16:28:45.621Z","dependency_job_id":"e6a1b78b-f962-44a5-b8d4-12e5ecd6ff67","html_url":"https://github.com/moatifbutt/CS867-Assignment3","commit_stats":null,"previous_names":["moatifbutt/cs867-assignment3"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/moatifbutt%2FCS867-Assignment3","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/moatifbutt%2FCS867-Assignment3/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/moatifbutt%2FCS867-Assignment3/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/moatifbutt%2FCS867-Assignment3/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/moatifbutt","download_url":"https://codeload.github.com/moatifbutt/CS867-Assignment3/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247085993,"owners_count":20881158,"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":[],"created_at":"2024-12-17T00:29:40.977Z","updated_at":"2025-04-03T21:44:44.579Z","avatar_url":"https://github.com/moatifbutt.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## CS867-Assignment 3: Image Classification Using Convolutional Neural Network\n\n## Pre-Requisites\n1. Anaconda (https://www.anaconda.com/products/individual)\n2. Pytorch (https://pytorch.org/get-started/locally/)\n3. Natural Scene Classification Dataset (https://www.kaggle.com/puneet6060/intel-image-classification/version/2)\n\n## Data Augmentation\n\nTo add more diversity in dataset, I have performed four types of data augmentations including,\n\n- Gaussian Blur\n- Horizontal Flip\n- Contrast\n- Saturation\n\nYou can use the **Augmentation.ipynb** in **Train_Notebooks** to perform augmentation on the provided dataset.\n\n## Training\n\nTo this end, three state-of-the-art CNNs i.e. **Alexnet** , **Resnet-152**, and **VGG** are employed to perform classification. It is important to mention here that, pre-trained CNNs are downloaded, and trained through transfer learning to achieve effective results. All the networks are available in above-folder named **Trained Notebooks**. All the trained models are available in above-folder **models**.\n\n## Results\nThe experiments are performed on both i.e. the base and augmented datasets to analyse the difference through adaptive and static learning rate. The experiments showed that Resnet-152 achieved better accuracy on augmented dataset with adaptive learning rate.\n\n#### Alexnet\n- With Adaptive Learning Rate on Augmented Dataset\n\n![alt text](https://github.com/aatiibutt/CS867-Assignment3/blob/main/graphs/Alex_Aug_AL.PNG?raw=true)\n\n- With Constant Learning Rate on Augmented Dataset\n\n![alt text](https://github.com/aatiibutt/CS867-Assignment3/blob/main/graphs/Alex_Aug_CLR.PNG?raw=true)\n\n- With Adaptive Learning Rate on Base Dataset\n\n![alt text](https://github.com/aatiibutt/CS867-Assignment3/blob/main/graphs/Alex_Base_AL.PNG?raw=true)\n\n- With Constant Learning Rate on Base Dataset\n\n![alt text](https://github.com/aatiibutt/CS867-Assignment3/blob/main/graphs/Alex_Base_CLR.PNG?raw=true)\n\n#### Resnet\n\n- With Adaptive Learning Rate on Augmented Dataset\n\n![alt text](https://github.com/aatiibutt/CS867-Assignment3/blob/main/graphs/Res_Aug_AL.PNG?raw=true)\n\n- With Constant Learning Rate on Augmented Dataset\n\n![alt text](https://github.com/aatiibutt/CS867-Assignment3/blob/main/graphs/Res_Aug_AL.PNG?raw=true)\n\n#### VGG\n\n- With Adaptive Learning Rate on Augmented Dataset\n\n![alt text](https://github.com/aatiibutt/CS867-Assignment3/blob/main/graphs/VGG_Aug_AL.PNG?raw=true)\n\n- With Constant Learning Rate on Augmented Dataset\n\n![alt text](https://github.com/aatiibutt/CS867-Assignment3/blob/main/graphs/Res_Aug_AL.PNG?raw=true)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmoatifbutt%2Fcs867-assignment3","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmoatifbutt%2Fcs867-assignment3","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmoatifbutt%2Fcs867-assignment3/lists"}