{
  "id": 492239,
  "title": "Training (RNN model) history",
  "url": "/competitions/birdclef-2024/discussion/492239",
  "author_name": "Elmaddin Guliyev",
  "post_date": "2024-04-09T02:20:26.159000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>I tried to apply the RNN model!<br>\n<code>def build_rnn_model(input_shape, num_classes):\n    model = Sequential([\n        SimpleRNN(64, input_shape=input_shape, return_sequences=True),\n        Dropout(0.3),\n        SimpleRNN(64),\n        Dropout(0.3),\n        Dense(128, activation='relu'),\n        Dense(num_classes, activation='softmax')\n    ])\n    model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n    return model</code></p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7290198%2Fb87974729fd1693650489aa9febbcabc%2FUntitled.png?generation=1712629255937219&amp;alt=media\"></p>",
  "messages": [
    {
      "id": 2742638,
      "postDate": "2024-04-09T02:20:26.160Z",
      "content": "<p>I tried to apply the RNN model!<br>\n<code>def build_rnn_model(input_shape, num_classes):\n    model = Sequential([\n        SimpleRNN(64, input_shape=input_shape, return_sequences=True),\n        Dropout(0.3),\n        SimpleRNN(64),\n        Dropout(0.3),\n        Dense(128, activation='relu'),\n        Dense(num_classes, activation='softmax')\n    ])\n    model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n    return model</code></p>\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7290198%2Fb87974729fd1693650489aa9febbcabc%2FUntitled.png?generation=1712629255937219&amp;alt=media\"></p>",
      "rawMarkdown": "I tried to apply the RNN model!\n`def build_rnn_model(input_shape, num_classes):\n    model = Sequential([\n        SimpleRNN(64, input_shape=input_shape, return_sequences=True),\n        Dropout(0.3),\n        SimpleRNN(64),\n        Dropout(0.3),\n        Dense(128, activation='relu'),\n        Dense(num_classes, activation='softmax')\n    ])\n    model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n    return model`\n \n ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7290198%2Fb87974729fd1693650489aa9febbcabc%2FUntitled.png?generation=1712629255937219&alt=media)\n"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2742638": "I tried to apply the RNN model!\n`def build_rnn_model(input_shape, num_classes):\n    model = Sequential([\n        SimpleRNN(64, input_shape=input_shape, return_sequences=True),\n        Dropout(0.3),\n        SimpleRNN(64),\n        Dropout(0.3),\n        Dense(128, activation='relu'),\n        Dense(num_classes, activation='softmax')\n    ])\n    model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n    return model`\n \n ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F7290198%2Fb87974729fd1693650489aa9febbcabc%2FUntitled.png?generation=1712629255937219&alt=media)\n"
  }
}