网格搜索“估算器应该是实现“拟合”方法的估算器，<function my_model at 0x000002047186C8B0> 已通过'

问题描述

我正在尝试将 gridsearch 应用于图像分类。为此，我正在应用 KerasClassifier。但是对于 fit 函数，我不断收到错误消息：TypeError: estimator should be an estimator implementation 'fit' method, waspassed

您可以在下面找到我的代码：

from sklearn.model_selection import gridsearchcv

model = KerasClassifier(build_fn = my_model,epochs = 100,batch_size = 10)

optimizer = ['SGD','RMSprop','Adam']
loss_fct = []

batch_size = [10,20,40,60,80,100]
epochs = [10,50,100]

param_grid = dict(batch_size=batch_size,epochs=epochs)

grid = gridsearchcv(estimator=my_model,param_grid = param_grid,verbose=1)
grid_result = grid.fit(train_images,y_train)#,**fit_parameters
                 #validation_data=([train_images,train_weight,train_room_humidity,train_temp],y_train)
    
print("Best: %f using %s" % (grid_result.best_score_,grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean,stdev,param in zip(means,stds,params):
    print("%f (%f) with: %r" % (mean,param))

有人可以给我一个提示，希望我做错了吗？

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）