python - TensorFlow 将所有图像分类为同一类

Question

问题

我在 TensorFlow 中创建了一个图像分类器 CNN，用于将图形分类为以下三个类之一：线性、二次或三次。我遵循了https://www.tensorflow.org/tutorials/images/classification上的文档。我已经对代码的所有前面部分进行了单元测试，它们工作得非常好。但是在对图的图像进行标记时，每个图都被归类为与任何图像This image most likely belongs to Cubic Sinusoidal with a 88.71 percent confidence.完全相同的分类和概率。

尝试修复

我已经将我的代码与文档进行了比较，似乎没有任何问题。如果有人可以提供帮助，那就太好了。我什至在这里找到了类似的问答。

代码

我的代码如下。Colab 笔记本在这里。我已经包含了我的所有代码，因为我不确定问题是什么：

pip install tensorflow

pip install numpy

pip install matplotlib

!git clone https://github.com/Refath/SinusoidalAnalyzer.git

# Import Libraries
import tensorflow as tf
from tensorflow import keras
from keras.models import Sequential
from keras.layers import Dense, Flatten, Conv2D, MaxPooling2D, Dropout
from tensorflow.keras import layers
from tensorflow.keras.utils import to_categorical
import numpy as np
import matplotlib.pyplot as plt

plt.style.use('fivethirtyeight')

# Load the Data
from keras.datasets import cifar10
(x_train, y_train), (x_test, y_test) = cifar10.load_data()

import pathlib
dataset_url = "https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz"
data_dir = tf.keras.utils.get_file(origin = dataset_url,
                                   fname = "flower_photos",
                                   untar = True)
data_dir = pathlib.Path(data_dir)

import pathlib
dataset_url = "https://barisciencelab.tech/Graphs.tar.gz"
data_dir = tf.keras.utils.get_file(origin = dataset_url,
                                   fname = "FunctionIdentifier",
                                   untar = True)
data_dir = pathlib.Path(data_dir)

print(list(data_dir.glob('*/*.png')))
image_count = len(list(data_dir.glob('*/*.png')))
print(image_count)

import numpy as np
import os
import PIL
import PIL.Image
import tensorflow as tf
import tensorflow_datasets as tfds
graphs = list(data_dir.glob('*/*.png'))
print(graphs)
PIL.Image.open(str(graphs[6]))

batch_size = 32
img_height = 36
img_width = 36

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="training",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="validation",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

class_names = ['Cubic Sinusoidal', 'Linear Sinusoidal', 'Quadratic Sinusoidal']
print(class_names)

import matplotlib.pyplot as plt

plt.figure(figsize=(10, 10))
for images, labels in train_ds.take(1):
  for i in range(9):
    ax = plt.subplot(3, 3, i + 1)
    plt.imshow(images[i].numpy().astype("uint8"))
    plt.title(class_names[labels[i]])
    plt.axis("off")

for image_batch, labels_batch in train_ds:
  print(image_batch.shape)
  print(labels_batch.shape)
  break

normalization_layer = tf.keras.layers.experimental.preprocessing.Rescaling(1./255)

normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
image_batch, labels_batch = next(iter(normalized_ds))
first_image = image_batch[0]
# Notice the pixels values are now in `[0,1]`.
print(np.min(first_image), np.max(first_image))

AUTOTUNE = tf.data.AUTOTUNE

train_ds = train_ds.cache().prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

num_classes = 3

model = tf.keras.Sequential([
  tf.keras.layers.experimental.preprocessing.Rescaling(1./255),
  tf.keras.layers.Conv2D(32, 3, activation='relu'),
  tf.keras.layers.MaxPooling2D(),
  tf.keras.layers.Conv2D(32, 3, activation='relu'),
  tf.keras.layers.MaxPooling2D(),
  tf.keras.layers.Conv2D(32, 3, activation='relu'),
  tf.keras.layers.MaxPooling2D(),
  tf.keras.layers.Flatten(),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dense(num_classes)
])

model.compile(
  optimizer='adam',
  loss=tf.losses.SparseCategoricalCrossentropy(from_logits=True),
  metrics=['accuracy'])

model.summary()

epochs = 3
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=3
)

acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(epochs)

plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

"""# 1-Sample *Cubic* Test (Passed; Accuracy: 99.91%)"""

cubic_url = "https://raw.githubusercontent.com/Refath/SinusoidalAnalyzer/main/CubicSinusoidal_1.png"
cubic_path = tf.keras.utils.get_file('CubicSinusoidal_1', origin=cubic_url)

img = keras.preprocessing.image.load_img(
    cubic_path, target_size=(img_height, img_width)
)
img_array = keras.preprocessing.image.img_to_array(img)
img_array = tf.expand_dims(img_array, 0) # Create a batch

predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])

print(
    "This image most likely belongs to {} with a {:.2f} percent confidence."
    .format(class_names[np.argmax(score)], 100 * np.max(score))
)

"""# 1-Sample *Quadratic* Test (Failed :( )"""

quad_url = "https://raw.githubusercontent.com/Refath/SinusoidalAnalyzer/main/QuadSinusoidal_1.png"
quad_path = tf.keras.utils.get_file('QuadSinusoidal_1', origin=quad_url)

img = keras.preprocessing.image.load_img(
    quad_path, target_size=(img_height, img_width)
)
img_array = keras.preprocessing.image.img_to_array(img)
img_array = tf.expand_dims(img_array, 0) # Create a batch

predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])

print(
    "This image most likely belongs to {} with a {:.2f} percent confidence."
    .format(class_names[np.argmax(score)], 100 * np.max(score))
)

lin_url = "https://raw.githubusercontent.com/Refath/SinusoidalAnalyzer/main/LinSinusoidal_1.png"
lin_path = tf.keras.utils.get_file('QuadSinusoidal_1', origin=lin_url)

img = keras.preprocessing.image.load_img(
    lin_path, target_size=(img_height, img_width)
)
img_array = keras.preprocessing.image.img_to_array(img)
img_array = tf.expand_dims(img_array, 0) # Create a batch

predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])

print(
    "This image most likely belongs to {} with a {:.2f} percent confidence."
    .format(class_names[np.argmax(score)], 100 * np.max(score))
)

标签： pythontensorflow