如何导入经过训练的模型来预测单个图像？

Question

我通过 Keras 训练了一个 CNN 模型，并通过 model.save('model.h5') 保存了该模型。 但是我想在单个图像上测试我的模型，我不知道如何将自己的图像导入到我的模型中。

# Image generators
train_datagen = ImageDataGenerator(rescale= 1./255)
validation_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(  
    train_data_dir,
    target_size=(image_size, image_size),
    shuffle=True,
    batch_size=batch_size,
    class_mode='categorical'
    )

validation_generator = validation_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(image_size, image_size),
    batch_size=batch_size,
    shuffle=True,
    class_mode='categorical'
    )

# Fit model
history = model.fit_generator(train_generator,
                steps_per_epoch=(nb_train_samples // batch_size),
                epochs=nb_epoch,
                validation_data=validation_generator,
                callbacks=[early_stopping],# save_best_model],
                validation_steps=(nb_validation_samples // batch_size)
               )

# Save model
model.save_weights('full_model_weights.h5')
model.save('model.h5')

我是 keras 的新手。如何将图像处理给我的模型并将我的图像分类到某个类。

输入的形状：

if K.image_data_format() == 'channels_first':
    input_shape = (3, image_size, image_size)
else:
    input_shape = (image_size, image_size, 3)

我的导入图片代码：

from keras.models import load_model
m=load_model("model.h5")

if K.image_data_format() == 'channels_first':
    input_shape = (3, image_size, image_size)
else:
    input_shape = (image_size, image_size, 3)

cloudy_pic="./Weather/weather_database/cloudy/4152.jpg"
im=Image.open(cloudy_pic).convert('RGB')
data=np.array(im,dtype=np.float32)
data=np.reshape(500, 500,3)
pre=m.predict_classes(data)
pre

还有错误：

AttributeError: 'int' object has no attribute 'reshape'
During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
<ipython-input-30-ebc72e185819> in <module>()
     10 im=Image.open(cloudy_pic).convert('RGB')
     11 data=np.array(im,dtype=np.float32)
---> 12 data=np.reshape(500, 500,3)
     13 pre=m.predict_classes(data)
     14 pre

~/anaconda3/envs/tensorflow/lib/python3.6/site- packages/numpy/core/fromnumeric.py in reshape(a, newshape, order)
    230            [5, 6]])
    231     """
--> 232     return _wrapfunc(a, 'reshape', newshape, order=order)
    233 
    234 

~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/numpy/core/fromnumeric.py in _wrapfunc(obj, method, *args, **kwds)
     65     # a downstream library like 'pandas'.
     66     except (AttributeError, TypeError):
---> 67         return _wrapit(obj, method, *args, **kwds)
     68 
     69 

~/anaconda3/envs/tensorflow/lib/python3.6/site-packages/numpy/core/fromnumeric.py in _wrapit(obj, method, *args, **kwds)
     45     except AttributeError:
     46         wrap = None
---> 47     result = getattr(asarray(obj), method)(*args, **kwds)
     48     if wrap:
     49         if not isinstance(result, mu.ndarray):

ValueError: cannot reshape array of size 1 into shape (500,)

Answer 1

# code for predicting an image stored locally against a trained model
# my local image is 28 x 28 already
import numpy as np
from PIL import Image
from keras.preprocessing import image
img = image.load_img('file path include full file name')# , target_size=(32,32))
img  = image.img_to_array(img)
img  = img.reshape((1,) + img.shape)
# img  = img/255
img = img.reshape(-1,784)
img_class=model.predict_classes(img) 
# this model above was already trained 
# code from https://machinelearningmastery.com/handwritten-digit-recognition-using-convolutional-#neural-networks-python-keras/
prediction = img_class[0]
classname = img_class[0]
print("Class: ",classname)

Answer 2

您可以在将图像转换为 np 数组之前调整其大小。

img = Image.open(img_path)
img = img.resize((image_size,image_size))
img = np.array(img)
img = img / 255.0
img = img.reshape(1,image_size,image_size,3)
m.predict_classes(img)

模型的输入形状必须是[None,image_size,image_size,3]，如果channels_first，则为[None,3,image_size,image_size]。

Answer 3

你可以这样做

model = load_model('model.h5')
img=#YOUR IMAGE (Let's say it's 32,32,1)
image_x = 32
image_y = 32
img = cv2.resize(img, (image_x, image_y))
img = np.array(img, dtype=np.float32)
img = np.reshape(img, (-1, image_x, image_y, 1))
pred_probab = model.predict(img)[0]
pred_class = list(pred_probab).index(max(pred_probab))
return max(pred_probab), pred_class