小编ash*_*l16的帖子

我正在尝试建立一个conditional CNN模型。模型是，

在first stage我的模型中，我将我的数据提供给Model 1然后，based on the prediction of Model 1我想train the model to Conditional Cat model or Conditional Dog model最后给出来自 Conditional Cat 模型或 Conditional Dog 模型的输出。我怎样才能做到这一点？

注意： 我的努力是，

import keras
from keras.layers import *
from keras.models import *
from keras.utils import *

img_rows,img_cols,number_of_class = 256,256,2
input = Input(shape=(img_rows,img_cols,3))

#----------- main model (Model 1) ------------------------------------
conv_01 = Convolution2D(64, 3, 3, activation='relu',name = 'conv_01') (input)
conv_02 = Convolution2D(64, 3, 3, …

大家好，我一直在尝试将输出图表保存为plt.savefig("coeff.png")svg或 png，但我得到的只是一张空白图片。

无论如何，我可以将我的绘图导出为图片格式吗？

下面是我的代码。

# These are the (standardized) coefficients found
# when it refit using that best alpha
list(zip(X.columns, LGBMR.feature_importances_))

#Now let's make it more presentable in Pandas DataFrame and also in standard form for numbers
df_LGBM_model_coefficients = pd.DataFrame(list(zip(X_train.columns, LGBMR.feature_importances_)))
df_LGBM_model_coefficients.rename(columns={0:'Features', 1: 'Coefficients'}, inplace=True)

df_LGBM_model_coefficients = df_LGBM_model_coefficients.iloc[1:]
df_LGBM_model_coefficients = df_LGBM_model_coefficients.sort_values(by = 'Coefficients', ascending = False)

#only retain the important ones.
df_LGBM_model_coefficients_top_10 = df_LGBM_model_coefficients.head(10)



plt.figure(figsize=(12,12))
sns.set_style('whitegrid')
sns.set(font_scale=0.8)

ax = sns.barplot(x = 'Coefficients',y='Features', data = df_LGBM_model_coefficients_top_10)
ax.set_title("LGBMR …