TensorFlow 和 keras 得到相同的输出预测误差

Question

所以我学会了为石头、纸、剪刀创建图像识别。所以模型的类型将是分类的。 当我试图预测输出时程序出错总是相同的。所以这里的输出和代码：

import numpy as np
from google.colab import files
from keras.preprocessing import image
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
%matplotlib inline

uploaded = files.upload()

for fn in uploaded.keys():

  # predicting images
  path = fn
  img = image.load_img(path, target_size=(150,150))
  imgplot = plt.imshow(img)
  x = image.img_to_array(img)
  x = np.expand_dims(x, axis=0)

  images = np.vstack([x])
  classes = model.predict(images, batch_size=30)
  model.summary()
  print(classes[0:10])

输出：

Saving p4.jpg to p4 (4).jpg
Model: "sequential_4"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_12 (Conv2D)           (None, 148, 148, 32)      896       
_________________________________________________________________
max_pooling2d_12 (MaxPooling (None, 74, 74, 32)        0         
_________________________________________________________________
conv2d_13 (Conv2D)           (None, 72, 72, 64)        18496     
_________________________________________________________________
max_pooling2d_13 (MaxPooling (None, 36, 36, 64)        0         
_________________________________________________________________
conv2d_14 (Conv2D)           (None, 34, 34, 128)       73856     
_________________________________________________________________
max_pooling2d_14 (MaxPooling (None, 17, 17, 128)       0         
_________________________________________________________________
conv2d_15 (Conv2D)           (None, 15, 15, 128)       147584    
_________________________________________________________________
max_pooling2d_15 (MaxPooling (None, 7, 7, 128)         0         
_________________________________________________________________
flatten_3 (Flatten)          (None, 6272)              0         
_________________________________________________________________
dense_8 (Dense)              (None, 256)               1605888   
_________________________________________________________________
dropout (Dropout)            (None, 256)               0         
_________________________________________________________________
dense_9 (Dense)              (None, 3)                 771       
=================================================================
Total params: 1,847,491
Trainable params: 1,847,491
Non-trainable params: 0
_________________________________________________________________
[[1. 0. 0.]]

我不太了解机器学习。所以我希望能解决这个程序的一些问题。此外，我从我的程序中添加了一些完整的代码。这里是：

train_datagen = ImageDataGenerator(
                    rescale=1./255,
                    rotation_range=20,
                    horizontal_flip=True,
                    shear_range = 0.2,
                    fill_mode = 'nearest')

test_datagen = ImageDataGenerator(
                    rescale=1./255,
                    rotation_range=20,
                    horizontal_flip=True,
                    shear_range = 0.2,
                    fill_mode = 'nearest')

train_generator = train_datagen.flow_from_directory(
        train_dir,  
        target_size=(150, 150),  
        batch_size=32,
        class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(
        validation_dir, 
        target_size=(150, 150), 
        batch_size=32, 
        class_mode='categorical')


model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(150, 150, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(256, activation='relu'),
    tf.keras.layers.Dropout(0.5),
    tf.keras.layers.Dense(3, activation = 'softmax')
])


model.compile(loss='categorical_crossentropy',
              optimizer=tf.optimizers.Adam(),
              metrics=['accuracy'])

model.fit(
      train_generator,
      # steps_per_epoch=25,
      epochs=20,
      batch_size=32,
      validation_data=validation_generator, 
      # validation_steps=5,
      verbose=2)

对于输出拟合： output.fit

Answer 1

您没有对输入图像进行重新缩放。在运行 predict() 之前尝试将输入图像除以 255

classes = model.predict(images/255.0, batch_size=30)