{"id":18995136,"url":"https://github.com/fitushar/3dcnns_tf2modelhub","last_synced_at":"2025-04-22T13:10:01.944Z","repository":{"id":109982384,"uuid":"323788846","full_name":"fitushar/3DCNNs_TF2Modelhub","owner":"fitushar","description":"Almost all the deeplearning libraries provide ready to use 2D models with/without imagenet weights, But In the case of 3D, CNN models are not as available. This repo will contain commonly used 2D CNNs 3D implementations.","archived":false,"fork":false,"pushed_at":"2020-12-23T03:46:09.000Z","size":24,"stargazers_count":10,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-22T13:08:29.778Z","etag":null,"topics":["3d-models","classification","cnn-classification","cnn-keras","segmentation","tf2"],"latest_commit_sha":null,"homepage":"","language":"Python","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/fitushar.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":"2020-12-23T03:06:45.000Z","updated_at":"2024-01-02T05:49:30.000Z","dependencies_parsed_at":"2023-03-29T05:18:40.323Z","dependency_job_id":null,"html_url":"https://github.com/fitushar/3DCNNs_TF2Modelhub","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fitushar%2F3DCNNs_TF2Modelhub","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fitushar%2F3DCNNs_TF2Modelhub/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fitushar%2F3DCNNs_TF2Modelhub/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fitushar%2F3DCNNs_TF2Modelhub/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fitushar","download_url":"https://codeload.github.com/fitushar/3DCNNs_TF2Modelhub/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250246727,"owners_count":21398919,"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":["3d-models","classification","cnn-classification","cnn-keras","segmentation","tf2"],"created_at":"2024-11-08T17:28:36.477Z","updated_at":"2025-04-22T13:10:01.809Z","avatar_url":"https://github.com/fitushar.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 3DCNNs_TF2Modelhub\n\nAlmost all the deeplearning libraries provide ready to use 2D models with/without imagenet weights, But In the case of 3D, CNN models are not as available. This repo will contain commonly used 2D CNNs 3D implementations.\n\n\n## Libraries Needed:\n```ruby\n* Python 3.x \n* Tensorflow 2.X\n* Numpy\n* random\n```\n\n## 3D-Models Avaible:\n\n### Classification:\n```ruby\n* Resnet_3D.py \n* DenseNet_3D.py\n* VGG_3D.py\n* Inception_3D.py\n```\n### Segmentation:\n```ruby\n* DenseVnet3D.py -\u003e (https://github.com/fitushar/DenseVNet3D_Chest_Abdomen_Pelvis_Segmentation_tf2/)  \n* Unet3D.py-\u003e (https://github.com/fitushar/3DUnet_tensorflow2.0/)\n```\n### How to run\nConfigure the models based on your need and GPUs running capability using *config.py*:\n```ruby\n\n##-----Network Configuration----#####\nNUMBER_OF_CLASSES=5\nINPUT_PATCH_SIZE=(96,128,128, 1)\n##------Resnet3D----####\nTRAIN_NUM_RES_UNIT=3\nTRAIN_NUM_FILTERS=(16, 32, 64, 128)\nTRAIN_STRIDES=((1, 1, 1), (2, 2, 2), (2, 2, 2), (2, 2, 2))\nTRAIN_CLASSIFY_ACTICATION=tf.nn.relu6\nTRAIN_KERNAL_INITIALIZER=tf.keras.initializers.VarianceScaling(distribution='uniform')\n#-------DenseNet13D----#####\n# DenseNet\nDENSE_NET_BLOCKS = 3\nDENSE_NET_BLOCK_LAYERS = 5\nDENSE_NET_INITIAL_CONV_DIM = 16\nDENSE_NET_GROWTH_RATE = DENSE_NET_INITIAL_CONV_DIM // 2\nDENSE_NET_ENABLE_BOTTLENETCK = False # called DenseNet-BC if ENABLE_BOTTLENETCK and COMPRESSION \u003c 1 in paper\nDENSE_NET_TRANSITION_COMPRESSION = 1.0\nDENSE_NET_ENABLE_DROPOUT = True\nDENSE_NET_DROPOUT = 0.5\n#-------Inception3D----#####\nINCEPTION_BLOCKS = 6\nINCEPTION_REDUCTION_STEPS = 2\nINCEPTION_KEEP_FILTERS = 128\nINCEPTION_ENABLE_DEPTHWISE_SEPARABLE_CONV_SHRINKAGE = 0.333\nINCEPTION_ENABLE_SPATIAL_SEPARABLE_CONV = True\nINCEPTION_DROPOUT = 0.5\n#---------VGG3D----####\nTRAIN_CLASSIFY_USE_BN = False\n\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffitushar%2F3dcnns_tf2modelhub","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffitushar%2F3dcnns_tf2modelhub","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffitushar%2F3dcnns_tf2modelhub/lists"}