问题
I'm using transfer learning method to use per-trained VGG19 model in Keras according to [this tutorial](https://towardsdatascience.com/keras-transfer-learning-for-beginners-6c9b8b7143e ). It shows how to train the model but NOT how to prepare test images for the predictions.
In the comments section it says:
Get an image, preprocess the image using the same
preprocess_imagefunction, and callmodel.predict(image). This will give you the prediction of the model on that image. Usingargmax(prediction), you can find the class to which the image belongs.
I can not find a function named preprocess_image used in the code. I did some searches and thought of using the method proposed by this tutorial.
But this give an error saying:
decode_predictions expects a batch of predictions (i.e. a 2D array of shape (samples, 1000)). Found array with shape: (1, 12)
My dataset has 12 categories. Here is the full code for training the model and how I got this error:
import pandas as pd
import numpy as np
import os
import keras
import matplotlib.pyplot as plt
from keras.layers import Dense, GlobalAveragePooling2D
from keras.applications.vgg19 import VGG19
from keras.preprocessing import image
from keras.applications.vgg19 import preprocess_input
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Model
from keras.optimizers import Adam
base_model = VGG19(weights='imagenet', include_top=False)
x=base_model.output
x=GlobalAveragePooling2D()(x)
x=Dense(1024,activation='relu')(x)
x=Dense(1024,activation='relu')(x)
x=Dense(512,activation='relu')(x)
preds=Dense(12,activation='softmax')(x)
model=Model(inputs=base_model.input,outputs=preds)
# view the layer architecture
# for i,layer in enumerate(model.layers):
# print(i,layer.name)
for layer in model.layers:
layer.trainable=False
for layer in model.layers[:20]:
layer.trainable=False
for layer in model.layers[20:]:
layer.trainable=True
train_datagen=ImageDataGenerator(preprocessing_function=preprocess_input)
train_generator=train_datagen.flow_from_directory('dataset',
target_size=(96,96), # 224, 224
color_mode='rgb',
batch_size=64,
class_mode='categorical',
shuffle=True)
model.compile(optimizer='Adam',loss='categorical_crossentropy',metrics=['accuracy'])
step_size_train=train_generator.n//train_generator.batch_size
model.fit_generator(generator=train_generator,
steps_per_epoch=step_size_train,
epochs=5)
# model.predict(new_image)
IPython:
In [3]: import classify_tl
Found 4750 images belonging to 12 classes.
Epoch 1/5
74/74 [==============================] - 583s 8s/step - loss: 2.0113 - acc: 0.4557
Epoch 2/5
74/74 [==============================] - 576s 8s/step - loss: 0.8222 - acc: 0.7170
Epoch 3/5
74/74 [==============================] - 563s 8s/step - loss: 0.5875 - acc: 0.7929
Epoch 4/5
74/74 [==============================] - 585s 8s/step - loss: 0.3897 - acc: 0.8627
Epoch 5/5
74/74 [==============================] - 610s 8s/step - loss: 0.2689 - acc: 0.9071
In [6]: model = classify_tl.model
In [7]: print(model)
<keras.engine.training.Model object at 0x7fb3ad988518>
In [8]: from keras.preprocessing.image import load_img
In [9]: image = load_img('examples/0021e90e4.png', target_size=(96,96))
In [10]: from keras.preprocessing.image import img_to_array
In [11]: image = img_to_array(image)
In [12]: image = image.reshape((1, image.shape[0], image.shape[1], image.shape[2]))
In [13]: from keras.applications.vgg19 import preprocess_input
In [14]: image = preprocess_input(image)
In [15]: yhat = model.predict(image)
In [16]: print(yhat)
[[1.3975363e-06 3.1069856e-05 9.9680350e-05 1.7175063e-03 6.2767825e-08
2.6133494e-03 7.2859187e-08 6.0187017e-07 2.0794137e-06 1.3714411e-03
9.9416250e-01 2.6067207e-07]]
In [17]: from keras.applications.vgg19 import decode_predictions
In [18]: label = decode_predictions(yhat)
Last line in the IPython prompt lead to the following error:
ValueError: `decode_predictions` expects a batch of predictions (i.e. a 2D array of shape (samples, 1000)). Found array with shape: (1, 12)
How should I properly feed my test image and get the predictions?
回答1:
decode_predictions is used for decoding predictions of a model according to the labels of classes in ImageNet dataset which has 1000 classes. However, your fine-tuned model has only 12 classes. Therefore, it does not make sense to use decode_predictions here. Surely, you must know what the labels for those 12 classes are. Therefore, just take the index of maximum score in the prediction and find its label:
# create a list containing the class labels
class_labels = ['class1', 'class2', 'class3', ...., 'class12']
# find the index of the class with maximum score
pred = np.argmax(class_labels, axis=-1)
# print the label of the class with maximum score
print(class_labels[pred[0]])
来源：https://stackoverflow.com/questions/53941590/cannot-predict-the-label-for-a-single-image-with-vgg19-in-keras