{
  "id": 252098,
  "title": "ResNet and EfficientNet Variants in PyTorch (Thanks to @rwightman)",
  "url": "/competitions/g2net-gravitational-wave-detection/discussion/252098",
  "author_name": "",
  "post_date": "2021-07-10T13:06:28.947594500Z",
  "votes": 8,
  "comment_count": 3,
  "views": 0,
  "content": "<h3><a href=\"https://www.kaggle.com/c/g2net-gravitational-wave-detection/discussion/252094\" target=\"_blank\">Link to the Tensorflow Post</a></h3>\n<p>I've collected some PyTorch implementations of various ResNet and EfficientNet variants and listed them down below. I'll keep adding new variants over time or additions from the comments </p>\n<h3>ResNet Variants</h3>\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>ResNet</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/resnet/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNest</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/resnest/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNet-D</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/resnet-d/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNeXt</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/resnext/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>RegNetX / RegNetY</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/regnetx/\" target=\"_blank\">Link</a> / <a href=\"https://rwightman.github.io/pytorch-image-models/models/regnety/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>SE-ResNet</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/se-resnet/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>SE-ResNeXt</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/seresnext/\" target=\"_blank\">Link</a></td>\n</tr>\n</tbody>\n</table>\n<h3>EfficientNet Variants</h3>\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://rwightman.github.io/pytorch-image-models/models/efficientnet/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>EfficientNet (Knapsack Pruned)</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/efficientnet-pruned/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>EfficientNetB8</strong> thanks to <a href=\"https://www.kaggle.com/saurabhbagchi\" target=\"_blank\">@saurabhbagchi</a></td>\n<td><a href=\"https://github.com/lukemelas/EfficientNet-PyTorch\" target=\"_blank\">Link</a></td>\n</tr>\n</tbody>\n</table>\n<p>Anything I missed 🧐, drop your suggestions down below 👇👇👇</p>",
  "messages": [
    {
      "id": "1383050",
      "postDate": "07/10/2021 13:06:28",
      "content": "<h3><a href=\"https://www.kaggle.com/c/g2net-gravitational-wave-detection/discussion/252094\" target=\"_blank\">Link to the Tensorflow Post</a></h3>\n<p>I've collected some PyTorch implementations of various ResNet and EfficientNet variants and listed them down below. I'll keep adding new variants over time or additions from the comments </p>\n<h3>ResNet Variants</h3>\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>ResNet</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/resnet/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNest</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/resnest/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNet-D</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/resnet-d/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>ResNeXt</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/resnext/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>RegNetX / RegNetY</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/regnetx/\" target=\"_blank\">Link</a> / <a href=\"https://rwightman.github.io/pytorch-image-models/models/regnety/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>SE-ResNet</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/se-resnet/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>SE-ResNeXt</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/seresnext/\" target=\"_blank\">Link</a></td>\n</tr>\n</tbody>\n</table>\n<h3>EfficientNet Variants</h3>\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://rwightman.github.io/pytorch-image-models/models/efficientnet/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>EfficientNet (Knapsack Pruned)</strong></td>\n<td><a href=\"https://rwightman.github.io/pytorch-image-models/models/efficientnet-pruned/\" target=\"_blank\">Link</a></td>\n</tr>\n<tr>\n<td><strong>EfficientNetB8</strong> thanks to <a href=\"https://www.kaggle.com/saurabhbagchi\" target=\"_blank\">@saurabhbagchi</a></td>\n<td><a href=\"https://github.com/lukemelas/EfficientNet-PyTorch\" target=\"_blank\">Link</a></td>\n</tr>\n</tbody>\n</table>\n<p>Anything I missed 🧐, drop your suggestions down below 👇👇👇</p>",
      "rawMarkdown": "### [Link to the Tensorflow Post](https://www.kaggle.com/c/g2net-gravitational-wave-detection/discussion/252094)\n\nI've collected some PyTorch implementations of various ResNet and EfficientNet variants and listed them down below. I'll keep adding new variants over time or additions from the comments \n\n### ResNet Variants\n\n| **Model Type** | **Link** |\n|:---:|:---:|\n| **ResNet** | [Link](https://rwightman.github.io/pytorch-image-models/models/resnet/) |\n| **ResNest** | [Link](https://rwightman.github.io/pytorch-image-models/models/resnest/) |\n| **ResNet-D** | [Link](https://rwightman.github.io/pytorch-image-models/models/resnet-d/) |\n| **ResNeXt** | [Link](https://rwightman.github.io/pytorch-image-models/models/resnext/) |\n| **RegNetX / RegNetY** | [Link](https://rwightman.github.io/pytorch-image-models/models/regnetx/) / [Link](https://rwightman.github.io/pytorch-image-models/models/regnety/)|\n| **SE-ResNet** | [Link](https://rwightman.github.io/pytorch-image-models/models/se-resnet/) |\n| **SE-ResNeXt** | [Link](https://rwightman.github.io/pytorch-image-models/models/seresnext/) |\n\n### EfficientNet Variants\n\n| **Model Type** | **Link** |\n|:---:|:---:|\n| **Base Variants(B0-B7)** | [Link](https://rwightman.github.io/pytorch-image-models/models/efficientnet/) |\n| **EfficientNet (Knapsack Pruned)** | [Link](https://rwightman.github.io/pytorch-image-models/models/efficientnet-pruned/) |\n| **EfficientNetB8** thanks to @saurabhbagchi | [Link](https://github.com/lukemelas/EfficientNet-PyTorch) |\n\nAnything I missed 🧐, drop your suggestions down below 👇👇👇",
      "votes": null
    },
    {
      "id": "1386534",
      "postDate": "07/13/2021 14:34:05",
      "content": "<p>We have EfficientNet(B8) on a github repo (<a href=\"https://github.com/lukemelas/EfficientNet-PyTorch\" target=\"_blank\">https://github.com/lukemelas/EfficientNet-PyTorch</a>) <a href=\"https://www.kaggle.com/sauravmaheshkar\" target=\"_blank\">@sauravmaheshkar</a> </p>",
      "rawMarkdown": "We have EfficientNet(B8) on a github repo (https://github.com/lukemelas/EfficientNet-PyTorch) @sauravmaheshkar",
      "votes": null
    },
    {
      "id": "1387160",
      "postDate": "07/14/2021 02:38:33",
      "content": "<p>Thanks, I'll add it right away</p>",
      "rawMarkdown": "Thanks, I'll add it right away",
      "votes": null
    },
    {
      "id": "1563276",
      "postDate": "10/28/2021 06:53:10",
      "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": 1386534,
      "author_name": "saurabhbagchi",
      "author_url": "",
      "post_date": "07/13/2021 14:34:05",
      "content": "<p>We have EfficientNet(B8) on a github repo (<a href=\"https://github.com/lukemelas/EfficientNet-PyTorch\" target=\"_blank\">https://github.com/lukemelas/EfficientNet-PyTorch</a>) <a href=\"https://www.kaggle.com/sauravmaheshkar\" target=\"_blank\">@sauravmaheshkar</a> </p>",
      "votes": null,
      "replies": [
        {
          "id": 1387160,
          "author_name": "sauravmaheshkar",
          "author_url": "",
          "post_date": "07/14/2021 02:38:33",
          "content": "<p>Thanks, I'll add it right away</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1563276,
      "author_name": "zerafachris",
      "author_url": "",
      "post_date": "10/28/2021 06:53:10",
      "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": {
    "1383050": "### [Link to the Tensorflow Post](https://www.kaggle.com/c/g2net-gravitational-wave-detection/discussion/252094)\n\nI've collected some PyTorch implementations of various ResNet and EfficientNet variants and listed them down below. I'll keep adding new variants over time or additions from the comments \n\n### ResNet Variants\n\n| **Model Type** | **Link** |\n|:---:|:---:|\n| **ResNet** | [Link](https://rwightman.github.io/pytorch-image-models/models/resnet/) |\n| **ResNest** | [Link](https://rwightman.github.io/pytorch-image-models/models/resnest/) |\n| **ResNet-D** | [Link](https://rwightman.github.io/pytorch-image-models/models/resnet-d/) |\n| **ResNeXt** | [Link](https://rwightman.github.io/pytorch-image-models/models/resnext/) |\n| **RegNetX / RegNetY** | [Link](https://rwightman.github.io/pytorch-image-models/models/regnetx/) / [Link](https://rwightman.github.io/pytorch-image-models/models/regnety/)|\n| **SE-ResNet** | [Link](https://rwightman.github.io/pytorch-image-models/models/se-resnet/) |\n| **SE-ResNeXt** | [Link](https://rwightman.github.io/pytorch-image-models/models/seresnext/) |\n\n### EfficientNet Variants\n\n| **Model Type** | **Link** |\n|:---:|:---:|\n| **Base Variants(B0-B7)** | [Link](https://rwightman.github.io/pytorch-image-models/models/efficientnet/) |\n| **EfficientNet (Knapsack Pruned)** | [Link](https://rwightman.github.io/pytorch-image-models/models/efficientnet-pruned/) |\n| **EfficientNetB8** thanks to @saurabhbagchi | [Link](https://github.com/lukemelas/EfficientNet-PyTorch) |\n\nAnything I missed 🧐, drop your suggestions down below 👇👇👇",
    "1386534": "We have EfficientNet(B8) on a github repo (https://github.com/lukemelas/EfficientNet-PyTorch) @sauravmaheshkar",
    "1387160": "Thanks, I'll add it right away",
    "1563276": "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"
}