{
  "id": 206309,
  "title": "With Efficientnet, Loading the model file that I have learned.",
  "url": "/competitions/cassava-leaf-disease-classification/discussion/206309",
  "author_name": "",
  "post_date": "2020-12-24T04:13:07.704277400Z",
  "votes": 3,
  "comment_count": 3,
  "views": 0,
  "content": "<p>Hi, all.</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2737964%2Fb003fa48c9e970d232558d4e57afc39f%2FScrShot%2033.png?generation=1608783086442084&amp;alt=media\" alt=\"\"></p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2737964%2Fe94a1951efe2439e9db6e0a38d1491b6%2FScrShot%2034.png?generation=1608783100968954&amp;alt=media\" alt=\"\"></p>\n<p>I am trying to infer after learning with Efficientnet… but I don't know how to load the model file that I have learned.</p>\n<p>For the source code I used, I refer to <a href=\"https://github.com/lukemelas/EfficientNet-PyTorch\" target=\"_blank\">https://github.com/lukemelas/EfficientNet-PyTorch</a>.</p>\n<p>-Is it correct to load the model trained with Efficientnet that way?<br>\n-Inference works, but is it correct to load like this… It's a little weird.<br>\n-Why don't you explicitly load the \"xxx.pth.tar\" file?</p>\n<p>I wonder.</p>\n<p>Thanks in advance.</p>\n<p>Best,<br>\n<a href=\"https://www.kaggle.com/bemoregt\" target=\"_blank\">@bemoregt</a>.</p>",
  "messages": [
    {
      "id": "1124580",
      "postDate": "12/24/2020 04:13:07",
      "content": "<p>Hi, all.</p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2737964%2Fb003fa48c9e970d232558d4e57afc39f%2FScrShot%2033.png?generation=1608783086442084&amp;alt=media\" alt=\"\"></p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2737964%2Fe94a1951efe2439e9db6e0a38d1491b6%2FScrShot%2034.png?generation=1608783100968954&amp;alt=media\" alt=\"\"></p>\n<p>I am trying to infer after learning with Efficientnet… but I don't know how to load the model file that I have learned.</p>\n<p>For the source code I used, I refer to <a href=\"https://github.com/lukemelas/EfficientNet-PyTorch\" target=\"_blank\">https://github.com/lukemelas/EfficientNet-PyTorch</a>.</p>\n<p>-Is it correct to load the model trained with Efficientnet that way?<br>\n-Inference works, but is it correct to load like this… It's a little weird.<br>\n-Why don't you explicitly load the \"xxx.pth.tar\" file?</p>\n<p>I wonder.</p>\n<p>Thanks in advance.</p>\n<p>Best,<br>\n<a href=\"https://www.kaggle.com/bemoregt\" target=\"_blank\">@bemoregt</a>.</p>",
      "rawMarkdown": "Hi, all.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2737964%2Fb003fa48c9e970d232558d4e57afc39f%2FScrShot%2033.png?generation=1608783086442084&alt=media)\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2737964%2Fe94a1951efe2439e9db6e0a38d1491b6%2FScrShot%2034.png?generation=1608783100968954&alt=media)\n\nI am trying to infer after learning with Efficientnet... but I don't know how to load the model file that I have learned.\n\nFor the source code I used, I refer to https://github.com/lukemelas/EfficientNet-PyTorch.\n\n-Is it correct to load the model trained with Efficientnet that way?\n-Inference works, but is it correct to load like this... It's a little weird.\n-Why don't you explicitly load the \"xxx.pth.tar\" file?\n\nI wonder.\n\nThanks in advance.\n\nBest,\n@bemoregt.",
      "votes": null
    },
    {
      "id": "1124700",
      "postDate": "12/24/2020 06:37:58",
      "content": "<p><a href=\"https://blog.csdn.net/lscelory/article/details/81482586\" target=\"_blank\">https://blog.csdn.net/lscelory/article/details/81482586</a></p>",
      "rawMarkdown": "https://blog.csdn.net/lscelory/article/details/81482586",
      "votes": null
    },
    {
      "id": "1125029",
      "postDate": "12/24/2020 10:56:39",
      "content": "<p>Thanks. <a href=\"https://www.kaggle.com/Juyan\" target=\"_blank\">@Juyan</a> Ba.</p>",
      "rawMarkdown": "Thanks. @Juyan Ba.",
      "votes": null
    },
    {
      "id": "1127953",
      "postDate": "12/27/2020 04:17:38",
      "content": "<p>I met the same problem before.<br>\nSometimes Pycharm would mistake reading the default path.<br>\nMaybe you can <strong>change the model name with the absolute path</strong>.</p>",
      "rawMarkdown": "I met the same problem before.\nSometimes Pycharm would mistake reading the default path.\nMaybe you can **change the model name with the absolute path**.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1124700,
      "author_name": "bajuyan",
      "author_url": "",
      "post_date": "12/24/2020 06:37:58",
      "content": "<p><a href=\"https://blog.csdn.net/lscelory/article/details/81482586\" target=\"_blank\">https://blog.csdn.net/lscelory/article/details/81482586</a></p>",
      "votes": null,
      "replies": [
        {
          "id": 1125029,
          "author_name": "bemorekgg",
          "author_url": "",
          "post_date": "12/24/2020 10:56:39",
          "content": "<p>Thanks. <a href=\"https://www.kaggle.com/Juyan\" target=\"_blank\">@Juyan</a> Ba.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1127953,
      "author_name": "xzy777",
      "author_url": "",
      "post_date": "12/27/2020 04:17:38",
      "content": "<p>I met the same problem before.<br>\nSometimes Pycharm would mistake reading the default path.<br>\nMaybe you can <strong>change the model name with the absolute path</strong>.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1124580": "Hi, all.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2737964%2Fb003fa48c9e970d232558d4e57afc39f%2FScrShot%2033.png?generation=1608783086442084&alt=media)\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2737964%2Fe94a1951efe2439e9db6e0a38d1491b6%2FScrShot%2034.png?generation=1608783100968954&alt=media)\n\nI am trying to infer after learning with Efficientnet... but I don't know how to load the model file that I have learned.\n\nFor the source code I used, I refer to https://github.com/lukemelas/EfficientNet-PyTorch.\n\n-Is it correct to load the model trained with Efficientnet that way?\n-Inference works, but is it correct to load like this... It's a little weird.\n-Why don't you explicitly load the \"xxx.pth.tar\" file?\n\nI wonder.\n\nThanks in advance.\n\nBest,\n@bemoregt.",
    "1124700": "https://blog.csdn.net/lscelory/article/details/81482586",
    "1125029": "Thanks. @Juyan Ba.",
    "1127953": "I met the same problem before.\nSometimes Pycharm would mistake reading the default path.\nMaybe you can **change the model name with the absolute path**."
  },
  "source": "meta"
}