{
  "id": 252094,
  "title": "ResNet and EfficientNet Variants in Tensorflow",
  "url": "/competitions/g2net-gravitational-wave-detection/discussion/252094",
  "author_name": "",
  "post_date": "2021-07-10T12:58:02.594554400Z",
  "votes": 7,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hello everyone 👋🏻, this is going to be my first Wave competition and based on the past competitions  it seems like Convolutional Neural Networks are the way to the top (Contradictions welcome below 😊)</p>\n<p>I've collected some Tensorflow implementations of various ResNet and EfficientNet variants and listed them down below (PyTorch post coming soon). I'll keep adding new variants over time or additions from the comments </p>\n<h2>ResNet Variants</h2>\n<table>\n<thead>\n<tr>\n<th><strong>Model Type</strong></th>\n<th><strong>Link</strong></th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td><strong>ResNet50</strong></td>\n<td><a href=\"https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet50\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNetV2(50,101,152)</strong></td>\n<td><a href=\"https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet_v2\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNest</strong></td>\n<td><a href=\"https://github.com/QiaoranC/tf_ResNeSt_RegNet_model/blob/master/models/ResNest.py\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>RegNet</strong></td>\n<td><a href=\"https://github.com/QiaoranC/tf_ResNeSt_RegNet_model/blob/master/models/RegNet.py\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNeXt</strong></td>\n<td><a href=\"https://github.com/qubvel/classification_models/blob/master/classification_models/models/resnext.py\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>SEResNet</strong></td>\n<td><a href=\"https://github.com/qubvel/classification_models/blob/master/classification_models/models/senet.py\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>SEResNeXt</strong></td>\n<td><a href=\"https://github.com/qubvel/classification_models/blob/master/classification_models/models/senet.py\" target=\"_blank\">Link</a></td>\n</tr>\n</tbody>\n</table>\n<h2>EfficientNet Variants</h2>\n<table>\n<thead>\n<tr>\n<th><strong>Model Type</strong></th>\n<th><strong>Link</strong></th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td><strong>Base Variants(B0-B7)</strong></td>\n<td><a href=\"https://www.tensorflow.org/api_docs/python/tf/keras/applications/efficientnet\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>EfficientNetV2</strong></td>\n<td><a href=\"https://github.com/google/automl/tree/master/efficientnetv2\" target=\"_blank\">Link</a></td>\n</tr>\n</tbody>\n</table>\n<p>Anything I missed 🧐, drop your suggestions down below 👇👇👇</p>",
  "messages": [
    {
      "id": "1383041",
      "postDate": "07/10/2021 12:58:02",
      "content": "<p>Hello everyone 👋🏻, this is going to be my first Wave competition and based on the past competitions  it seems like Convolutional Neural Networks are the way to the top (Contradictions welcome below 😊)</p>\n<p>I've collected some Tensorflow implementations of various ResNet and EfficientNet variants and listed them down below (PyTorch post coming soon). I'll keep adding new variants over time or additions from the comments </p>\n<h2>ResNet Variants</h2>\n<table>\n<thead>\n<tr>\n<th><strong>Model Type</strong></th>\n<th><strong>Link</strong></th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td><strong>ResNet50</strong></td>\n<td><a href=\"https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet50\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNetV2(50,101,152)</strong></td>\n<td><a href=\"https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet_v2\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNest</strong></td>\n<td><a href=\"https://github.com/QiaoranC/tf_ResNeSt_RegNet_model/blob/master/models/ResNest.py\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>RegNet</strong></td>\n<td><a href=\"https://github.com/QiaoranC/tf_ResNeSt_RegNet_model/blob/master/models/RegNet.py\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNeXt</strong></td>\n<td><a href=\"https://github.com/qubvel/classification_models/blob/master/classification_models/models/resnext.py\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>SEResNet</strong></td>\n<td><a href=\"https://github.com/qubvel/classification_models/blob/master/classification_models/models/senet.py\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>SEResNeXt</strong></td>\n<td><a href=\"https://github.com/qubvel/classification_models/blob/master/classification_models/models/senet.py\" target=\"_blank\">Link</a></td>\n</tr>\n</tbody>\n</table>\n<h2>EfficientNet Variants</h2>\n<table>\n<thead>\n<tr>\n<th><strong>Model Type</strong></th>\n<th><strong>Link</strong></th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td><strong>Base Variants(B0-B7)</strong></td>\n<td><a href=\"https://www.tensorflow.org/api_docs/python/tf/keras/applications/efficientnet\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>EfficientNetV2</strong></td>\n<td><a href=\"https://github.com/google/automl/tree/master/efficientnetv2\" target=\"_blank\">Link</a></td>\n</tr>\n</tbody>\n</table>\n<p>Anything I missed 🧐, drop your suggestions down below 👇👇👇</p>",
      "rawMarkdown": "Hello everyone 👋🏻, this is going to be my first Wave competition and based on the past competitions  it seems like Convolutional Neural Networks are the way to the top (Contradictions welcome below 😊)\n\nI've collected some Tensorflow implementations of various ResNet and EfficientNet variants and listed them down below (PyTorch post coming soon). I'll keep adding new variants over time or additions from the comments \n\n## ResNet Variants\n\n| **Model Type** | **Link** |\n|:---:|:---:|\n| **ResNet50** | [Link](https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet50) |\n| **ResNetV2(50,101,152)** | [Link](https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet_v2) |\n| **ResNest** | [Link](https://github.com/QiaoranC/tf_ResNeSt_RegNet_model/blob/master/models/ResNest.py) |\n| **RegNet** | [Link](https://github.com/QiaoranC/tf_ResNeSt_RegNet_model/blob/master/models/RegNet.py) |\n| **ResNeXt** | [Link](https://github.com/qubvel/classification_models/blob/master/classification_models/models/resnext.py) |\n| **SEResNet** | [Link](https://github.com/qubvel/classification_models/blob/master/classification_models/models/senet.py) |\n| **SEResNeXt** | [Link](https://github.com/qubvel/classification_models/blob/master/classification_models/models/senet.py) |\n\n## EfficientNet Variants\n\n| **Model Type** | **Link** |\n|:---:|:---:|\n| **Base Variants(B0-B7)** | [Link](https://www.tensorflow.org/api_docs/python/tf/keras/applications/efficientnet) |\n| **EfficientNetV2** | [Link](https://github.com/google/automl/tree/master/efficientnetv2) |\n\nAnything I missed 🧐, drop your suggestions down below 👇👇👇",
      "votes": null
    },
    {
      "id": "1563267",
      "postDate": "10/28/2021 06:52:39",
      "content": "<p>Hey,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "rawMarkdown": "Hey,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1563267,
      "author_name": "zerafachris",
      "author_url": "",
      "post_date": "10/28/2021 06:52:39",
      "content": "<p>Hey,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1383041": "Hello everyone 👋🏻, this is going to be my first Wave competition and based on the past competitions  it seems like Convolutional Neural Networks are the way to the top (Contradictions welcome below 😊)\n\nI've collected some Tensorflow implementations of various ResNet and EfficientNet variants and listed them down below (PyTorch post coming soon). I'll keep adding new variants over time or additions from the comments \n\n## ResNet Variants\n\n| **Model Type** | **Link** |\n|:---:|:---:|\n| **ResNet50** | [Link](https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet50) |\n| **ResNetV2(50,101,152)** | [Link](https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet_v2) |\n| **ResNest** | [Link](https://github.com/QiaoranC/tf_ResNeSt_RegNet_model/blob/master/models/ResNest.py) |\n| **RegNet** | [Link](https://github.com/QiaoranC/tf_ResNeSt_RegNet_model/blob/master/models/RegNet.py) |\n| **ResNeXt** | [Link](https://github.com/qubvel/classification_models/blob/master/classification_models/models/resnext.py) |\n| **SEResNet** | [Link](https://github.com/qubvel/classification_models/blob/master/classification_models/models/senet.py) |\n| **SEResNeXt** | [Link](https://github.com/qubvel/classification_models/blob/master/classification_models/models/senet.py) |\n\n## EfficientNet Variants\n\n| **Model Type** | **Link** |\n|:---:|:---:|\n| **Base Variants(B0-B7)** | [Link](https://www.tensorflow.org/api_docs/python/tf/keras/applications/efficientnet) |\n| **EfficientNetV2** | [Link](https://github.com/google/automl/tree/master/efficientnetv2) |\n\nAnything I missed 🧐, drop your suggestions down below 👇👇👇",
    "1563267": "Hey,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris"
  },
  "source": "meta"
}