-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
3 changed files
with
70 additions
and
180 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,68 +1,53 @@ | ||
| from model_zoo.model import BaseModel | ||
| from model_zoo import Model | ||
| import tensorflow as tf | ||
|
|
||
|
|
||
| class BasicCNNModel(BaseModel): | ||
| class BasicCNNModel(Model): | ||
| """ | ||
| Basic CNN Model | ||
| """ | ||
|
|
||
| def __init__(self, config): | ||
| """ | ||
| init layers | ||
| :param config: | ||
| """ | ||
| super(BasicCNNModel, self).__init__(config) | ||
| self.bn1 = tf.keras.layers.BatchNormalization() | ||
| self.conv1 = tf.keras.layers.Conv2D(32, (2, 2), padding='same', activation='relu', | ||
| kernel_initializer='random_uniform') | ||
| self.pool1 = tf.keras.layers.MaxPool2D(padding='same') | ||
| self.dropout1 = tf.keras.layers.Dropout(0.5) | ||
| self.conv2 = tf.keras.layers.Conv2D(32, (2, 2), padding='same', activation='relu', | ||
| kernel_initializer='random_uniform') | ||
| self.pool2 = tf.keras.layers.MaxPool2D(padding='same') | ||
| self.dropout2 = tf.keras.layers.Dropout(0.5) | ||
| self.flatten1 = tf.keras.layers.Flatten() | ||
| self.dense1 = tf.keras.layers.Dense(128, activation='relu', kernel_initializer='random_uniform') | ||
| self.dense2 = tf.keras.layers.Dense(10, activation='softmax') | ||
|
|
||
| def call(self, inputs, training=False, mask=None): | ||
|
|
||
| def inputs(self): | ||
| """ | ||
| build model | ||
| :param inputs: inputs image | ||
| :param training: | ||
| :param mask: | ||
| Define inputs. | ||
| :return: | ||
| """ | ||
| o = self.bn1(inputs) | ||
| o = self.conv1(o) | ||
| o = self.pool1(o) | ||
| o = self.dropout1(o) if training else o | ||
| o = self.conv2(o) | ||
| o = self.pool2(o) | ||
| o = self.dropout2(o) if training else o | ||
| o = self.flatten1(o) | ||
| o = self.dense1(o) | ||
| o = self.dense2(o) | ||
| return o | ||
|
|
||
| def get_optimizer(self): | ||
| """ | ||
| build optimizer | ||
| return tf.keras.Input(shape=(28, 28, 1)) | ||
|
|
||
| def outputs(self, inputs): | ||
| """ | ||
| Define outputs. | ||
| """ | ||
| x = tf.keras.layers.BatchNormalization()(inputs) | ||
| x = tf.keras.layers.Conv2D(32, (2, 2), padding='same', activation='relu', | ||
| kernel_initializer='random_uniform')(x) | ||
| x = tf.keras.layers.MaxPool2D(padding='same')(x) | ||
| x = tf.keras.layers.Dropout(0.5)(x) | ||
| x = tf.keras.layers.Conv2D(32, (2, 2), padding='same', activation='relu', | ||
| kernel_initializer='random_uniform')(x) | ||
| x = tf.keras.layers.MaxPool2D(padding='same')(x) | ||
| x = tf.keras.layers.Dropout(0.5)(x) | ||
| x = tf.keras.layers.Flatten()(x) | ||
| x = tf.keras.layers.Dense(128, activation='relu', kernel_initializer='random_uniform')(x) | ||
| return tf.keras.layers.Dense(10, activation='softmax')(x) | ||
|
|
||
| def optimizer(self): | ||
| """ | ||
| build optimizer. | ||
| :return: | ||
| """ | ||
| return tf.keras.optimizers.Adam(lr=self.config.get('learning_rate')) | ||
|
|
||
| def get_loss(self): | ||
| def loss(self): | ||
| """ | ||
| define loss | ||
| define loss. | ||
| :return: | ||
| """ | ||
| return 'categorical_crossentropy' | ||
|
|
||
| def get_metrics(self): | ||
| def metrics(self): | ||
| """ | ||
| define metrics | ||
| define metrics. | ||
| :return: | ||
| """ | ||
| return ['accuracy'] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,149 +1,54 @@ | ||
| from model_zoo.model import BaseModel | ||
| from tensorflow_core.python.keras.applications.vgg19 import VGG19 | ||
|
|
||
| from model_zoo import Model | ||
| import tensorflow as tf | ||
|
|
||
|
|
||
| class VGG19Model(BaseModel): | ||
| class VGG19Model(Model): | ||
| """ | ||
| This model gets no good results, deprecated. | ||
| """ | ||
|
|
||
| def __init__(self, config): | ||
| super(VGG19Model, self).__init__(config) | ||
| self.num_features = 64 | ||
| # layer1 | ||
| self.conv11 = tf.keras.layers.Conv2D(filters=self.num_features, kernel_size=(3, 3), activation='relu', | ||
| padding='same') | ||
| self.conv12 = tf.keras.layers.Conv2D(filters=self.num_features, kernel_size=(3, 3), activation='relu', | ||
| padding='same') | ||
| self.bn1 = tf.keras.layers.BatchNormalization() | ||
| self.pool1 = tf.keras.layers.MaxPool2D(pool_size=(2, 2), strides=(2, 2)) | ||
| self.drop1 = tf.keras.layers.Dropout(rate=0.5) | ||
|
|
||
| # layer2 | ||
| self.conv21 = tf.keras.layers.Conv2D(filters=2 * self.num_features, kernel_size=(3, 3), activation='relu', | ||
| padding='same') | ||
| self.conv22 = tf.keras.layers.Conv2D(filters=2 * self.num_features, kernel_size=(3, 3), activation='relu', | ||
| padding='same') | ||
| self.bn2 = tf.keras.layers.BatchNormalization() | ||
| self.pool2 = tf.keras.layers.MaxPool2D(pool_size=(2, 2), strides=(2, 2)) | ||
| self.drop2 = tf.keras.layers.Dropout(rate=0.5) | ||
|
|
||
| # layer3 | ||
| self.conv31 = tf.keras.layers.Conv2D(filters=2 * 2 * self.num_features, kernel_size=(3, 3), activation='relu', | ||
| padding='same') | ||
| self.conv32 = tf.keras.layers.Conv2D(filters=2 * 2 * self.num_features, kernel_size=(3, 3), activation='relu', | ||
| padding='same') | ||
| self.conv33 = tf.keras.layers.Conv2D(filters=2 * 2 * self.num_features, kernel_size=(3, 3), activation='relu', | ||
| padding='same') | ||
| self.bn3 = tf.keras.layers.BatchNormalization() | ||
| self.pool3 = tf.keras.layers.MaxPool2D(pool_size=(2, 2), strides=(2, 2)) | ||
| self.drop3 = tf.keras.layers.Dropout(rate=0.5) | ||
|
|
||
| # layer4 | ||
| self.conv41 = tf.keras.layers.Conv2D(filters=2 * 2 * 2 * self.num_features, kernel_size=(3, 3), | ||
| activation='relu', | ||
| padding='same') | ||
| self.conv42 = tf.keras.layers.Conv2D(filters=2 * 2 * 2 * self.num_features, kernel_size=(3, 3), | ||
| activation='relu', | ||
| padding='same') | ||
| self.conv43 = tf.keras.layers.Conv2D(filters=2 * 2 * 2 * self.num_features, kernel_size=(3, 3), | ||
| activation='relu', | ||
| padding='same') | ||
| self.bn4 = tf.keras.layers.BatchNormalization() | ||
| self.pool4 = tf.keras.layers.MaxPool2D(pool_size=(2, 2), strides=(2, 2)) | ||
| self.drop4 = tf.keras.layers.Dropout(rate=0.5) | ||
|
|
||
| # layer5 | ||
| self.conv51 = tf.keras.layers.Conv2D(filters=2 * 2 * 2 * self.num_features, kernel_size=(3, 3), | ||
| activation='relu', | ||
| padding='same') | ||
| self.conv52 = tf.keras.layers.Conv2D(filters=2 * 2 * 2 * self.num_features, kernel_size=(3, 3), | ||
| activation='relu', | ||
| padding='same') | ||
| self.conv53 = tf.keras.layers.Conv2D(filters=2 * 2 * 2 * self.num_features, kernel_size=(3, 3), | ||
| activation='relu', | ||
| padding='same') | ||
| self.bn5 = tf.keras.layers.BatchNormalization() | ||
| self.pool5 = tf.keras.layers.MaxPool2D(pool_size=(2, 2), strides=(2, 2)) | ||
| self.drop5 = tf.keras.layers.Dropout(rate=0.5) | ||
|
|
||
| # flatten | ||
| self.flatten = tf.keras.layers.Flatten() | ||
|
|
||
| # dense | ||
| self.dense1 = tf.keras.layers.Dense(2 * 2 * 2 * self.num_features, activation='relu') | ||
| self.drop5 = tf.keras.layers.Dropout(0.5) | ||
| self.dense2 = tf.keras.layers.Dense(2 * 2 * self.num_features, activation='relu') | ||
| self.drop6 = tf.keras.layers.Dropout(0.5) | ||
| self.dense3 = tf.keras.layers.Dense(2 * self.num_features, activation='relu') | ||
| self.drop7 = tf.keras.layers.Dropout(0.5) | ||
|
|
||
| self.dense4 = tf.keras.layers.Dense(10, activation='softmax') | ||
|
|
||
| def call(self, inputs, training=None, mask=None): | ||
| # layer1 | ||
| x = self.conv11(inputs) | ||
| x = self.conv12(x) | ||
| x = self.bn1(x, training=training) | ||
| x = self.pool1(x) | ||
| x = self.drop1(x, training=training) | ||
| # layer2 | ||
| x = self.conv21(x) | ||
| x = self.conv22(x) | ||
| x = self.bn2(x, training=training) | ||
| x = self.pool2(x) | ||
| x = self.drop2(x, training=training) | ||
| # # layer3 | ||
| x = self.conv31(x) | ||
| x = self.conv32(x) | ||
| x = self.conv33(x) | ||
| x = self.bn3(x, training=training) | ||
| x = self.pool3(x) | ||
| x = self.drop3(x, training=training) | ||
| # # layer4 | ||
| x = self.conv41(x) | ||
| x = self.conv42(x) | ||
| x = self.conv43(x) | ||
| x = self.bn4(x, training=training) | ||
| x = self.pool4(x) | ||
| x = self.drop4(x, training=training) | ||
| # layer5 | ||
| x = self.conv51(x) | ||
| x = self.conv52(x) | ||
| x = self.conv53(x) | ||
| x = self.bn5(x, training=training) | ||
| x = self.pool5(x) | ||
| x = self.drop5(x, training=training) | ||
|
|
||
| # flatten | ||
| x = self.flatten(x) | ||
| # dense | ||
| x = self.dense1(x) | ||
| x = self.drop5(x, training=training) | ||
| x = self.dense2(x) | ||
| x = self.drop6(x, training=training) | ||
| x = self.dense3(x) | ||
| x = self.drop7(x, training=training) | ||
| x = self.dense4(x) | ||
| return x | ||
|
|
||
| def get_optimizer(self): | ||
|
|
||
| def __init__(self, **kwargs): | ||
| """ | ||
| Init base model. | ||
| """ | ||
| self.base_model = VGG19() | ||
| super(VGG19Model, self).__init__(**kwargs) | ||
|
|
||
| def inputs(self): | ||
| """ | ||
| Define inputs. | ||
| :return: | ||
| """ | ||
| return self.base_model.input | ||
|
|
||
| def outputs(self, inputs): | ||
| """ | ||
| build optimizer | ||
| Define outputs. | ||
| :param inputs: | ||
| :return: | ||
| """ | ||
| x = self.base_model.output | ||
| return tf.keras.layers.Dense(10, activation='softmax')(x) | ||
|
|
||
| def optimizer(self): | ||
| """ | ||
| Build optimizer. | ||
| :return: | ||
| """ | ||
| return tf.keras.optimizers.Adam(lr=self.config.get('learning_rate')) | ||
|
|
||
| def get_loss(self): | ||
| def loss(self): | ||
| """ | ||
| define loss | ||
| Define loss. | ||
| :return: | ||
| """ | ||
| return 'categorical_crossentropy' | ||
|
|
||
| def get_metrics(self): | ||
| def metrics(self): | ||
| """ | ||
| define metrics | ||
| Define metrics. | ||
| :return: | ||
| """ | ||
| return ['accuracy'] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters