{
  "id": 37323,
  "title": "98 precent 4 short epochs with keras",
  "url": "/competitions/state-farm-distracted-driver-detection/discussion/37323",
  "author_name": "AviWolfson",
  "post_date": "2017-07-31T08:08:47.552000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p><strong>i skipped the usual imports here but dont forget them</strong></p>\n\n<pre><code>from keras.layers.convolutional import Conv2D\nfrom keras.layers.pooling import MaxPooling2D \nfrom keras.layers.normalization import BatchNormalization\nmodel = Sequential()\n\nmodel.add(Conv2D(16, 3, input_shape = (32, 32, 3), activation = 'relu'))\n\nmodel.add(Conv2D(16, 3,  activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2)))\n\nmodel.add(Conv2D(32, 3,  activation = 'relu'))       \nmodel.add(Conv2D(32, 3,  activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2))) \n\nmodel.add(Flatten())\nmodel.add(Dense(10, activation='softmax'))\n\nfrom keras.preprocessing.image import ImageDataGenerator\n\ntrain_datagen = ImageDataGenerator(rescale = 1./255,\n                                   shear_range = 0.1,\n                                   zoom_range = 0.1,\n                                               )\n\ntest_datagen = ImageDataGenerator(rescale = 1./255)\n\ntraining_set = train_datagen.flow_from_directory('train',\n                                                 target_size = (32, 32),\n                                                 batch_size = 4,\n                                                 class_mode = 'categorical')\n\ntest_set = test_datagen.flow_from_directory('val',\n                                            target_size = (32, 32),\n                                            batch_size = 4,\n                                            class_mode = 'categorical')\nmodel.compile(optimizer=SGD(lr=0.01, momentum=0.0, decay=0.0, nesterov=False), loss='categorical_crossentropy', metrics=['accuracy'])\n\nmodel.fit_generator(training_set,\n                         steps_per_epoch = 22400/4,\n                         epochs = 2,\n                         validation_data = test_set,\n                         validation_steps = 4000/4)\n</code></pre>",
  "messages": [
    {
      "id": 208841,
      "postDate": "2017-07-31T08:08:47.553Z",
      "content": "<p><strong>i skipped the usual imports here but dont forget them</strong></p>\n\n<pre><code>from keras.layers.convolutional import Conv2D\nfrom keras.layers.pooling import MaxPooling2D \nfrom keras.layers.normalization import BatchNormalization\nmodel = Sequential()\n\nmodel.add(Conv2D(16, 3, input_shape = (32, 32, 3), activation = 'relu'))\n\nmodel.add(Conv2D(16, 3,  activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2)))\n\nmodel.add(Conv2D(32, 3,  activation = 'relu'))       \nmodel.add(Conv2D(32, 3,  activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2))) \n\nmodel.add(Flatten())\nmodel.add(Dense(10, activation='softmax'))\n\nfrom keras.preprocessing.image import ImageDataGenerator\n\ntrain_datagen = ImageDataGenerator(rescale = 1./255,\n                                   shear_range = 0.1,\n                                   zoom_range = 0.1,\n                                               )\n\ntest_datagen = ImageDataGenerator(rescale = 1./255)\n\ntraining_set = train_datagen.flow_from_directory('train',\n                                                 target_size = (32, 32),\n                                                 batch_size = 4,\n                                                 class_mode = 'categorical')\n\ntest_set = test_datagen.flow_from_directory('val',\n                                            target_size = (32, 32),\n                                            batch_size = 4,\n                                            class_mode = 'categorical')\nmodel.compile(optimizer=SGD(lr=0.01, momentum=0.0, decay=0.0, nesterov=False), loss='categorical_crossentropy', metrics=['accuracy'])\n\nmodel.fit_generator(training_set,\n                         steps_per_epoch = 22400/4,\n                         epochs = 2,\n                         validation_data = test_set,\n                         validation_steps = 4000/4)\n</code></pre>",
      "rawMarkdown": "   **i skipped the usual imports here but dont forget them**\n\n    from keras.layers.convolutional import Conv2D\n    from keras.layers.pooling import MaxPooling2D \n    from keras.layers.normalization import BatchNormalization\n    model = Sequential()\n       \n    model.add(Conv2D(16, 3, input_shape = (32, 32, 3), activation = 'relu'))\n           \n    model.add(Conv2D(16, 3,  activation = 'relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2)))\n    \n    model.add(Conv2D(32, 3,  activation = 'relu'))       \n    model.add(Conv2D(32, 3,  activation = 'relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2))) \n    \n    model.add(Flatten())\n    model.add(Dense(10, activation='softmax'))\n    \n    from keras.preprocessing.image import ImageDataGenerator\n    \n    train_datagen = ImageDataGenerator(rescale = 1./255,\n                                       shear_range = 0.1,\n                                       zoom_range = 0.1,\n                                                   )\n    \n    test_datagen = ImageDataGenerator(rescale = 1./255)\n    \n    training_set = train_datagen.flow_from_directory('train',\n                                                     target_size = (32, 32),\n                                                     batch_size = 4,\n                                                     class_mode = 'categorical')\n    \n    test_set = test_datagen.flow_from_directory('val',\n                                                target_size = (32, 32),\n                                                batch_size = 4,\n                                                class_mode = 'categorical')\n    model.compile(optimizer=SGD(lr=0.01, momentum=0.0, decay=0.0, nesterov=False), loss='categorical_crossentropy', metrics=['accuracy'])\n    \n    model.fit_generator(training_set,\n                             steps_per_epoch = 22400/4,\n                             epochs = 2,\n                             validation_data = test_set,\n                             validation_steps = 4000/4)\n\n\n",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "208841": "   **i skipped the usual imports here but dont forget them**\n\n    from keras.layers.convolutional import Conv2D\n    from keras.layers.pooling import MaxPooling2D \n    from keras.layers.normalization import BatchNormalization\n    model = Sequential()\n       \n    model.add(Conv2D(16, 3, input_shape = (32, 32, 3), activation = 'relu'))\n           \n    model.add(Conv2D(16, 3,  activation = 'relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2)))\n    \n    model.add(Conv2D(32, 3,  activation = 'relu'))       \n    model.add(Conv2D(32, 3,  activation = 'relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2,2))) \n    \n    model.add(Flatten())\n    model.add(Dense(10, activation='softmax'))\n    \n    from keras.preprocessing.image import ImageDataGenerator\n    \n    train_datagen = ImageDataGenerator(rescale = 1./255,\n                                       shear_range = 0.1,\n                                       zoom_range = 0.1,\n                                                   )\n    \n    test_datagen = ImageDataGenerator(rescale = 1./255)\n    \n    training_set = train_datagen.flow_from_directory('train',\n                                                     target_size = (32, 32),\n                                                     batch_size = 4,\n                                                     class_mode = 'categorical')\n    \n    test_set = test_datagen.flow_from_directory('val',\n                                                target_size = (32, 32),\n                                                batch_size = 4,\n                                                class_mode = 'categorical')\n    model.compile(optimizer=SGD(lr=0.01, momentum=0.0, decay=0.0, nesterov=False), loss='categorical_crossentropy', metrics=['accuracy'])\n    \n    model.fit_generator(training_set,\n                             steps_per_epoch = 22400/4,\n                             epochs = 2,\n                             validation_data = test_set,\n                             validation_steps = 4000/4)\n\n\n"
  }
}