Computer Vision 计算机视觉瞟一眼

The Convolutional Classifier

Step 1 - Load Data

代码过于复杂，省略，暂不学习

Step 2 - Define Pretrained Base

pretrained_base = tf.keras.models.load_model(
    '../input/cv-course-models/cv-course-models/vgg16-pretrained-base',
)
pretrained_base.trainable = False

Step 3 - Attach Head

from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
   # Preprocessing
    preprocessing.RandomFlip('horizontal'), # flip left-to-right
    preprocessing.RandomContrast(0.5), # contrast change by up to 50%
    pretrained_base,
    layers.Flatten(),
    layers.Dense(6, activation='relu'),
    layers.Dense(1, activation='sigmoid'),
])

Step 4 - Train

model.compile(
    optimizer='adam',
    loss='binary_crossentropy',
    metrics=['binary_accuracy'],
)

history = model.fit(
    ds_train,
    validation_data=ds_valid,
    epochs=30,
    verbose=0,
)

Step 5 - Show

import pandas as pd

history_frame = pd.DataFrame(history.history)
history_frame.loc[:, ['loss', 'val_loss']].plot()
history_frame.loc[:, ['binary_accuracy', 'val_binary_accuracy']].plot();

Convolution and ReLU

作为layer

from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
    layers.Conv2D(filters=64, kernel_size=3, activation='relu')
    # More layers follow
])

直接应用在图片上

import tensorflow as tf

kernel = tf.constant([
    [-1, -1, -1],
    [-1,  8, -1],
    [-1, -1, -1],
])

plt.figure(figsize=(3, 3))
show_kernel(kernel)

image_filter = tf.nn.conv2d(
    input=image,
    filters=kernel,
    # we'll talk about these two in lesson 4!
    strides=1,
    padding='SAME',
)

plt.figure(figsize=(6, 6))
plt.imshow(tf.squeeze(image_filter))
plt.axis('off')
plt.show();

image_detect = tf.nn.relu(image_filter)

plt.figure(figsize=(6, 6))
plt.imshow(tf.squeeze(image_detect))
plt.axis('off')
plt.show();

Maximum Pooling

import tensorflow as tf

image_condense = tf.nn.pool(
    input=image_detect, # image in the Detect step above
    window_shape=(2, 2),
    pooling_type='MAX',
    # we'll see what these do in the next lesson!
    strides=(2, 2),
    padding='SAME',
)

plt.figure(figsize=(6, 6))
plt.imshow(tf.squeeze(image_condense))
plt.axis('off')
plt.show();