我正在處理遷移學習問題。當我僅從 Mobilenet 創建新模型時，我設置了一個 dropout。base_model = MobileNet(weights='imagenet', include_top=False, input_shape=(200,200,3), dropout=.15)x = base_model.outputx = GlobalAveragePooling2D()(x)x = Dense(10, activation='softmax')(x)我在訓練時使用model_checkpoint_callback. 當我訓練時，我會發現過度擬合發生的地方，并調整凍結層的數量和學習率。當我再次保存加載的模型時，我是否也可以調整 dropout？我看到了這個答案，但是 Mobilenet 中沒有實際的 dropout 層，所以這個for layer in model.layers: if hasattr(layer, 'rate'): print(layer.name) layer.rate = 0.5什么都不做。
1 回答
UYOU
TA貢獻1878條經驗 獲得超4個贊
過去，您必須克隆模型才能讓新的 dropout 接受。我最近沒試過。
# This code allows you to change the dropout
# Load model from .json
model.load_weights(filenameToModelWeights) # Load weights
model.layers[-2].rate = 0.04 # layer[-2] is my dropout layer, rate is dropout attribute
model = keras.models.clone(model) # If I do not clone, the new rate is never used. Weights are re-init now.
model.load_weights(filenameToModelWeights) # Load weights
model.predict(x)
歸功于
http://www.gergltd.com/home/2018/03/changing-dropout-on-the-fly-during-training-time-test-time-in-keras/
如果模型一開始就沒有 dropout 層，就像 Keras 的預訓練移動網絡一樣，您必須使用方法添加它們。這是您可以做到的一種方法。
用于添加單層
def insert_single_layer_in_keras(model, layer_name, new_layer):
layers = [l for l in model.layers]
x = layers[0].output
for i in range(1, len(layers)):
x = layers[i](x)
# add layer afterward
if layers[i].name == layer_name:
x = new_layer(x)
new_model = Model(inputs=layers[0].input, outputs=x)
return new_model
用于系統地添加層
def insert_layers_in_model(model, layer_common_name, new_layer):
import re
layers = [l for l in model.layers]
x = layers[0].output
layer_config = new_layer.get_config()
base_name = layer_config['name']
layer_class = type(dropout_layer)
for i in range(1, len(layers)):
x = layers[i](x)
match = re.match(".+" + layer_common_name + "+", layers[i].name)
# add layer afterward
if match:
layer_config['name'] = base_name + "_" + str(i) # no duplicate names, could be done different
layer_copy = layer_class.from_config(layer_config)
x = layer_copy(x)
new_model = Model(inputs=layers[0].input, outputs=x)
return new_model
像這樣跑
import tensorflow as tf
from tensorflow.keras.applications.mobilenet import MobileNet
from tensorflow.keras.layers import Dropout
from tensorflow.keras.models import Model
base_model = MobileNet(weights='imagenet', include_top=False, input_shape=(192, 192, 3), dropout=.15)
dropout_layer = Dropout(0.5)
# add single layer after last dropout
mobile_net_with_dropout = insert_single_layer_in_model(base_model, "conv_pw_13_bn", dropout_layer)
# systematically add layers after any batchnorm layer
mobile_net_with_multi_dropout = insert_layers_in_model(base_model, "bn", dropout_layer)
順便說一句，您絕對應該進行實驗，但您不太可能希望在 batchnorm 之上對像 mobilenet 這樣的小型網絡進行額外的正則化。
添加回答
舉報
0/150
提交
取消