加載預培訓的Keras模型並預測

我已經用基礎的Kaggle Cat vs Dog數據（https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition/data）在一些Keras示例上拼湊了一個簡單的神經網絡。我能訓練和保存使用加載預培訓的Keras模型並預測

model.fit_generator(
     #train_generator, 
     #samples_per_epoch=2000, 
     #nb_epoch=50, 
     #validation_data=validation_generator, 
     #nb_val_samples=800) 
model.save('first_model.h5')

模型但當我嘗試加載模型來預測，我得到

Traceback (most recent call last): 
    File "/Users/me/PycharmProjects/CatVsDog/SampleML.py", line 48, in <module> 
    print(saved_model.predict_generator(test_generator, 12500)) 
    File "/Library/Frameworks/Python.framework/Versions/3.4/lib/python3.4/site-packages/keras/models.py", line 1012, in predict_generator 
    pickle_safe=pickle_safe) 
    File "/Library/Frameworks/Python.framework/Versions/3.4/lib/python3.4/site-packages/keras/engine/training.py", line 1763, in predict_generator 
    outs = self.predict_on_batch(x) 
    File "/Library/Frameworks/Python.framework/Versions/3.4/lib/python3.4/site-packages/keras/engine/training.py", line 1371, in predict_on_batch 
    self.internal_input_shapes) 
    File "/Library/Frameworks/Python.framework/Versions/3.4/lib/python3.4/site-packages/keras/engine/training.py", line 85, in standardize_input_data 
    'Found: ' + str(data)[:200] + '...') 
TypeError: Error when checking : data should be a Numpy array, or list/dict of Numpy arrays. Found: None... 
Exception ignored in: <bound method Session.__del__ of <tensorflow.python.client.session.Session object at 0x10c7586d8>> 
Traceback (most recent call last): 
    File "/Library/Frameworks/Python.framework/Versions/3.4/lib/python3.4/site-packages/tensorflow/python/client/session.py", line 581, in __del__ 
UnboundLocalError: local variable 'status' referenced before assignment

在此處，將圖像保存在我的PyCharm的解決方案。 Test目錄中有1-12500個.jpg文件，每個訓練集cat和dog目錄中有11500個標記爲.jpgs，每個驗證目錄中有1000個標記爲.jpgs。

這裏是我的代碼

from __future__ import print_function 
from keras.models import Sequential 
from keras.layers import Dense, Dropout, Activation, Flatten 
from keras.layers import Convolution2D, MaxPooling2D 
from keras.preprocessing.image import ImageDataGenerator 
from keras.models import load_model 

train_datagen = ImageDataGenerator(
     rescale=1./255, 
     shear_range=0.2, 
     zoom_range=0.2, 
     horizontal_flip=True) 

test_datagen = ImageDataGenerator(rescale=1./255) 

train_generator = train_datagen.flow_from_directory(
     'train', 
     target_size=(64, 64), 
     batch_size=32, 
     class_mode='binary') 

validation_generator = test_datagen.flow_from_directory(
     'validate', 
     target_size=(64, 64), 
     batch_size=32, 
     class_mode='binary') 

test_generator = train_datagen.flow_from_directory(
     'test', 
     target_size=(64, 64), 
     batch_size=32, 
     class_mode='binary') 


nb_filters = 32 
kernel_size = (3,3) 
pool_size = (2, 2) 
nb_classes = 2 
input_shape = (64, 64, 3) 


saved_model = load_model('first_model.h5') 
score = saved_model.evaluate_generator(validation_generator, 2000) 


print('Test score:', score[0]) 
print('Test accuracy:', score[1]) 
print(saved_model.predict_generator(test_generator, 12500))

來源

2017-02-25 Amanda_Panda

我相信你喂到predict_generator什麼是不正確的格式。

當您預測值時，與培訓和評估相反，您不想喂標籤。所以我想嘗試改變你的test_generator這樣：

test_generator = train_datagen.flow_from_directory(
    'test', 
    target_size=(64, 64), 
    batch_size=32, 
    #This will not output the targets. 
    class_mode=None)

你可以找到documentation about the ImageDataGenerator here。

來源

2017-02-25 21:22:54

工作，我還需要爲我的測試數據添加更多的子目錄。 Keras喜歡在測試子目錄中的測試數據。似乎是人爲的，但它的工作原理！ –

加載預培訓的Keras模型並預測

回答

相關問題