{"id":18244296,"url":"https://github.com/manikantasanjay/transferlearning_with_pytorch","last_synced_at":"2026-04-30T10:08:55.964Z","repository":{"id":48828032,"uuid":"288947599","full_name":"ManikantaSanjay/TransferLearning_with_pytorch","owner":"ManikantaSanjay","description":"Understanding the importance of Transfer Learning with by performing model training with the help of a Pre-Trained Model(Resnet-50).","archived":false,"fork":false,"pushed_at":"2021-07-09T16:54:51.000Z","size":765,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-08T18:51:41.616Z","etag":null,"topics":["computer-vision","deep-learning","image-classification","neural-networks","pytorch","resnet","transfer-learning"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ManikantaSanjay.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}},"created_at":"2020-08-20T08:17:39.000Z","updated_at":"2024-04-25T05:25:23.000Z","dependencies_parsed_at":"2022-09-23T22:30:20.042Z","dependency_job_id":null,"html_url":"https://github.com/ManikantaSanjay/TransferLearning_with_pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ManikantaSanjay/TransferLearning_with_pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManikantaSanjay%2FTransferLearning_with_pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManikantaSanjay%2FTransferLearning_with_pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManikantaSanjay%2FTransferLearning_with_pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManikantaSanjay%2FTransferLearning_with_pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ManikantaSanjay","download_url":"https://codeload.github.com/ManikantaSanjay/TransferLearning_with_pytorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ManikantaSanjay%2FTransferLearning_with_pytorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32460940,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-29T22:27:22.272Z","status":"online","status_checked_at":"2026-04-30T02:00:05.929Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["computer-vision","deep-learning","image-classification","neural-networks","pytorch","resnet","transfer-learning"],"created_at":"2024-11-05T09:16:03.474Z","updated_at":"2026-04-30T10:08:55.947Z","avatar_url":"https://github.com/ManikantaSanjay.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Transfer Learning With Pytorch\n\n### :one: Motive :\nTrying to Understand the power of Transfer Learning by making use of a Pre-Trained Model, Resnet-50\n\n### :two: Description : \n\ni\u003e We are making use of the Imagewoof dataset to create a classification model by  making use of a pre-trained model Resnet-50.\n\nii\u003e We are achieving a accuracy of over 90% by training with just 10 epochs involved.\n\niii\u003e We look at how the model performs without the help of the pre-trained model giving an accuracy of just over 30% with the same number of epochs and not performing well enough for further more epochs also.\n \n\n### 3️⃣ About the Dataset :\nImagewoof is a subset of 10 dog breed classes from Imagenet.\n\nThe breeds are: Australian terrier, Border terrier, Samoyed, Beagle, Shih-Tzu, English foxhound, Rhodesian ridgeback, Dingo, Golden retriever, Old English sheepdog.\n\nCheck the Below URL for the dataset 👇\n#### https://s3.amazonaws.com/fast-ai-imageclas/imagewoof2-160.tgz 🔗\n\n### 4️⃣ Libraries Used :\n\ni\u003e PyTorch\n\nii\u003e MatplotLib\n\niii\u003e OS\n\n### 5️⃣ Steps involved in the notebook file :\n\n#### Step 1 :  Importing Libraries\n\n#### Step 2 : Downloading Dataset\n\n#### Step 3 : Data Transformations\n\n#### Step 4 : Creating the Train and Test Dataset\n\n#### Step 5 : Setting the Batch Size\n\n#### Step 6 : Creating Data Loaders\n\n#### Step 7 : A Look at Sample Images from the Training Dataloader\n\n#### Step 8 : Making Use of the GPU \n\n#### Step 9 : Moving Dataloaders to Device\n\n#### Step 10 : Defining the Classification Model\n\n#### Step 11 : Loading the Pre-Trained Model Class\n\n#### Step 12 : Defining the Function for the Training Process\n\n#### Step 13 : Training the Model using the pre-trained model class\n\n#### Step 14 : Plotting graphs for Accuracy vs number of Epochs involved and Loss per Epoch\n\n#### Step 15 : Loading the Non Pre-Trained Model Class\n\n#### Step 16 : Training the model using the above class ☝️\n\n#### Step 17 : Plotting Graphs for Accuracy and Loss Per Epoch\n\n### 6️⃣ Link to Jupyter Notebook File 👇\n\n#### https://github.com/ManikantaSanjay/TransferLearning_with_pytorch/blob/master/Transfer_Learning.ipynb 🔗\n\n### 7️⃣ Conclusion :\n\nFrom the above models, it is clear that with the help of pre-trained model Resnet-50 we were able to generate a whooping accuracy of over 90% whereas without the pre-trained model, we were barely achieving a mere 30% accuracy which is totally unacceptable and emphasising the importance of \u003cb\u003e Transfer Learning in building Deep Learning Applications .\u003c/b\u003e\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanikantasanjay%2Ftransferlearning_with_pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmanikantasanjay%2Ftransferlearning_with_pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanikantasanjay%2Ftransferlearning_with_pytorch/lists"}