1

我正在尝试使用 Talos 运行超参数优化。因为我有很多参数要测试，所以我想使用一个“grid_downsample”参数，它将选择所有可能的超参数组合的 30%。但是，当我运行我的代码时，我得到：TypeError: __init__() got an unexpected keyword argument 'grid_downsample'

我在没有“grid_downsample”选项和较少超参数的情况下测试了下面的代码。

#load data
data = pd.read_csv('data.txt', sep="\t", encoding = "latin1")
# split into input (X) and output (y) variables
Y = np.array(data['Y'])
data_bis = data.drop(['Y'], axis = 1)
X = np.array(data_bis)

p = {'activation':['relu'],
     'optimizer': ['Nadam'],
     'first_hidden_layer': [12],
     'second_hidden_layer': [12],
     'batch_size': [20],
     'epochs': [10,20],
     'dropout_rate':[0.0, 0.2]}

def dnn_model(x_train, y_train, x_val, y_val, params):
    model = Sequential()
    #input layer
    model.add(Dense(params['first_hidden_layer'], input_shape=(1024,))) 
    model.add(Dropout(params['dropout_rate']))
    model.add(Activation(params['activation']))
    #hidden layer 2
    model.add(Dense(params['second_hidden_layer']))
    model.add(Dropout(params['dropout_rate']))
    model.add(Activation(params['activation']))
    # output layer with one node
    model.add(Dense(1))
    model.add(Activation(params['activation']))
    # Compile model
    model.compile(loss='binary_crossentropy', optimizer=params['optimizer'], metrics=['accuracy'])
    out = model.fit(x_train, y_train,
                    batch_size=params['batch_size'],
                    epochs=params['epochs'],
                    validation_data=[x_val, y_val],
                    verbose=0)

    return out, model

scan_object = ta.Scan(X, Y, model=dnn_model, params=p, experiment_name="test")

reporting = ta.Reporting(scan_object)
report = reporting.data
report.to_csv('./Random_search/dnn/report_talos.txt', sep = '\t')

这段代码运行良好。如果我将 scan_object 作为结尾更改为: scan_object = ta.Scan(X, Y, model=dnn_model, grid_downsample=0.3, params=p, experiment_name="test")，它会给我错误：TypeError: __init__() got an unexpected keyword argument 'grid_downsample'虽然我期望结果格式与普通网格搜索相同，但组合更少。我错过了什么？参数的名称是否更改？我在 conda 环境中使用 Talos 0.6.3。谢谢！

4

1 回答 1

2

现在对您来说可能为时已晚，但他们已将其切换为 fraction_limit。它会给你这个

scan_object = ta.Scan(X, Y, model=dnn_model, params=p, experiment_name="test", fraction_limit = 0.1)

可悲的是，文档没有很好地更新

在 GitHub 上查看他们的示例： https ://github.com/autonomio/talos/blob/master/examples/Hyperparameter%20Optimization%20with%20Keras%20for%20the%20Iris%20Prediction.ipynb

于 2019-10-12T13:54:36.583 回答