{"id":13499078,"url":"https://github.com/taki0112/ResNeXt-Tensorflow","last_synced_at":"2025-03-29T03:32:20.395Z","repository":{"id":98366093,"uuid":"101144707","full_name":"taki0112/ResNeXt-Tensorflow","owner":"taki0112","description":"Simple Tensorflow implementation of ResNeXt using Cifar10","archived":false,"fork":false,"pushed_at":"2018-08-14T04:35:00.000Z","size":285,"stargazers_count":157,"open_issues_count":4,"forks_count":57,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-03-23T22:07:10.999Z","etag":null,"topics":[],"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/taki0112.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}},"created_at":"2017-08-23T06:16:24.000Z","updated_at":"2025-01-21T04:09:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"ed630a4c-51f3-4c97-a990-b2403d127974","html_url":"https://github.com/taki0112/ResNeXt-Tensorflow","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/taki0112%2FResNeXt-Tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taki0112%2FResNeXt-Tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taki0112%2FResNeXt-Tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/taki0112%2FResNeXt-Tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/taki0112","download_url":"https://codeload.github.com/taki0112/ResNeXt-Tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246135765,"owners_count":20729056,"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":"2024-07-31T22:00:28.126Z","updated_at":"2025-03-29T03:32:20.075Z","avatar_url":"https://github.com/taki0112.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes"],"sub_categories":["ResNext"],"readme":"# ResNeXt-Tensorflow\nTensorflow implementation of [ResNeXt](https://arxiv.org/abs/1611.05431) using **Cifar10**\n\nIf you want to see the ***original author's code***, please refer to this [link](https://github.com/facebookresearch/ResNeXt)\n\n## Requirements\n* Tensorflow 1.x\n* Python 3.x\n* tflearn (If you are easy to use ***global average pooling***, you should install ***tflearn***)\n\n## Issue\n* If not enough GPU memory, Please edit the code\n```python\nwith tf.Session() as sess : NO\nwith tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess : OK\n```\n## Compare Architecture\n### ResNet\n![ResNet](./assests/ResNet.JPG)\n\n### ResNeXt\n![ResNeXt](./assests/ResNeXt.JPG)\n\n* I implemented (b) \n* (b) is ***split + transform(bottleneck) + concatenate + transition + merge***\n\n## Idea\n### What is the \"split\" ?\n```python\n  def split_layer(self, input_x, stride, layer_name):\n      with tf.name_scope(layer_name) :\n          layers_split = list()\n          for i in range(cardinality) :\n              splits = self.transform_layer(input_x, stride=stride, scope=layer_name + '_splitN_' + str(i))\n              layers_split.append(splits)\n\n          return Concatenation(layers_split)            \n```\n* ***Cardinality*** means how many times you want to split.\n\n### What is the \"transform\" ?\n```python\n  def transform_layer(self, x, stride, scope):\n      with tf.name_scope(scope) :\n          x = conv_layer(x, filter=depth, kernel=[1,1], stride=stride, layer_name=scope+'_conv1')\n          x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')\n          x = Relu(x)\n\n          x = conv_layer(x, filter=depth, kernel=[3,3], stride=1, layer_name=scope+'_conv2')\n          x = Batch_Normalization(x, training=self.training, scope=scope+'_batch2')\n          x = Relu(x)\n          return x\n```\n\n### What is the \"transition\" ?\n```python\n  def transition_layer(self, x, out_dim, scope):\n      with tf.name_scope(scope):\n          x = conv_layer(x, filter=out_dim, kernel=[1,1], stride=1, layer_name=scope+'_conv1')\n          x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')\n\n          return x\n````\n\n## Comapre Results (ResNet, DenseNet, ResNeXt)\n![compare](./assests/comparision.png)\n\n## Related works\n* [DenseNet-Tensorflow](https://github.com/taki0112/Densenet-Tensorflow)\n* [SENet-Tensorflow](https://github.com/taki0112/SENet-Tensorflow)\n* [ResNet-Tensorflow](https://github.com/taki0112/ResNet-Tensorflow)\n\n## References\n* [Classification Datasets Results](http://rodrigob.github.io/are_we_there_yet/build/classification_datasets_results.html)\n\n## Author\nJunho Kim\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftaki0112%2FResNeXt-Tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftaki0112%2FResNeXt-Tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftaki0112%2FResNeXt-Tensorflow/lists"}