我有個問題。我想使用 MobileNevV2 訓練一個網路，但據我所知，你只能將彩色影像傳遞給它。
我的資料集僅包含黑白影像。如果我嘗試將影像的形狀傳遞為 (224, 224, 1) 顯然錯誤會回傳給我：
Traceback (most recent call last):
File "/home/andrea/Scrivania/COMPUTER-VISION/MobileNet_train.py", line 40, in <module>
mobielNetV2 = tensorflow.keras.applications.MobileNetV2(input_shape=IMG_SHAPE, include_top=False, weights='imagenet')
File "/home/andrea/.local/lib/python3.9/site-packages/keras/applications/mobilenet_v2.py", line 279, in MobileNetV2
input_shape = imagenet_utils.obtain_input_shape(
File "/home/andrea/.local/lib/python3.9/site-packages/keras/applications/imagenet_utils.py", line 372, in obtain_input_shape
raise ValueError('The input must have 3 channels; Received '
ValueError: The input must have 3 channels; Received `input_shape=(224, 224, 1)`
如何訓練黑白影像模型？以下是我創建的代碼：
import matplotlib.pyplot as plt
import tensorflow
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.models import Model
from tensorflow.keras.preprocessing.image import ImageDataGenerator
IMAGE_SIZE = (224, 224)
IMG_SHAPE = IMAGE_SIZE (1,)
DATASET_DIR = "/home/andrea/Scrivania/COMPUTER-VISION/DATASET/KAGGLE/new_train"
BATCH_SIZE = 32
EPOCHS = 5
datagen = ImageDataGenerator(
validation_split=0.2,
rescale=1. / 255, # per processare più velocemente i dati
brightness_range=[1, 2]
)
train_generator = datagen.flow_from_directory(
DATASET_DIR,
target_size=IMAGE_SIZE,
batch_size=BATCH_SIZE,
class_mode="categorical",
subset="training"
)
test_generator = datagen.flow_from_directory(
DATASET_DIR,
target_size=IMAGE_SIZE,
batch_size=BATCH_SIZE,
class_mode="categorical",
subset="validation"
)
mobielNetV2 = tensorflow.keras.applications.MobileNetV2(input_shape=IMG_SHAPE, include_top=False, weights='imagenet')
for layer in mobielNetV2.layers:
layer.trainable = False
x = Flatten()(mobielNetV2.output)
prediction = Dense(6, activation='softmax')(x)
model = Model(inputs=mobielNetV2.input, outputs=prediction)
# tell the model what cost and optimization method to use
model.summary()
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
r = model.fit(train_generator, validation_data=test_generator, epochs=EPOCHS, steps_per_epoch=len(train_generator),
validation_steps=len(test_generator))
model.save("MobileNet_Hand.h5")
uj5u.com熱心網友回復：
假設您已經有灰度影像，并且您想將它們轉換為rgb影像來訓練您的模型：
import tensorflow as tf
import matplotlib.pyplot as plt
flowers = tf.keras.utils.get_file(
'flower_photos',
'https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz',
untar=True)
img_gen = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)
ds = tf.data.Dataset.from_generator(
lambda: img_gen.flow_from_directory(flowers, batch_size=32, shuffle=False),
output_types=(tf.float32, tf.float32))
ds = ds.map(lambda x, y: (tf.image.rgb_to_grayscale(x), y))
images, _ = next(iter(ds.take(1)))
image = images[0]
print(image.shape)
plt.imshow(image.numpy()[:,:,0], cmap='gray')
(256, 256, 1)
灰度：
RGB：
ds = ds.map(lambda x, y: (tf.image.grayscale_to_rgb(x), y))
images, _ = next(iter(ds.take(1)))
image = images[0]
print(image.shape)
plt.imshow(image.numpy())
(256, 256, 3)
所以，只需tf.image.grayscale_to_rgb結合使用dataset.map，你就可以開始使用了。
更新 1：
datagen = ImageDataGenerator(
validation_split=0.2,
rescale=1. / 255, # per processare più velocemente i dati
brightness_range=[1, 2]
)
train_generator = datagen.flow_from_directory(
DATASET_DIR,
target_size=IMAGE_SIZE,
batch_size=BATCH_SIZE,
class_mode="categorical",
subset="training"
)
ds = tf.data.Dataset.from_generator(
lambda: train_generator,
output_types=(tf.float32, tf.float32))
uj5u.com熱心網友回復：
您收到的錯誤可能是因為您正在傳遞灰度輸入，但color_model = rgb默認情況下您的資料加載器期望。在此處查看顏色模式的可能選項- ( ISSUE 1 )。此外，您還將灰度輸入 ( h, w, 1) 傳遞給具有ImageNet權重的模型，該模型在 RGB 輸入 ( h, w, 3) - ( ISSUE 2 ) 上進行了訓練。
IMAGE_SIZE = (224, 224)
IMG_SHAPE = IMAGE_SIZE (1,)
.. .flow_from_directory(
DATASET_DIR,
color_mode='rgb', # < ------ ISSUE 1
target_size=IMAGE_SIZE,
batch_size=BATCH_SIZE,
class_mode="categorical",
subset="training"
)
mobielNetV2 = ..applications.MobileNetV2(
input_shape=IMG_SHAPE, # < ------ ISSUE 2
include_top=False,
weights='imagenet')
...
...
ValueError: The input must have 3 channels; Received `input_shape=(224, 224, 1)`
解決方案 1
如果您不關心ImageNet 的預訓練權重，那么您需要在設定中進行如下更改：
.. .flow_from_directory(
DATASET_DIR,
color_mode='grayscale', # < ------ SOVLED ISSUE 1
...
)
mobielNetV2 = ...applications.MobileNetV2(
input_shape=IMG_SHAPE,
include_top=False,
weights=None) # < ------ SOVLED ISSUE 2
解決方案 2
如果您想要 ImageNet 權重并且同時希望您的灰度作為輸入，那么有兩個選項可供選擇。
- 選項a：（推薦）
使用可訓練層和 ImageNet 模型將灰度輸入映射到 RGB。
.. .flow_from_directory(
DATASET_DIR,
color_mode='grayscale', # < ------ SOVLED ISSUE 1
...
)
# rgb-imagenet-model
mobilenet = keras.applications.MobileNetV2(include_top=False,
weights='imagenet',
input_shape=(100, 100, 3))
# mapping grayscale to RGB
input_tensor = keras.Input(shape=(100, 100, 1))
x = keras.layers.Conv2D(3, (3, 3), padding='same')(input_tensor)
# followed by image-net model
x = mobilenet(x)
y = keras.layers.GlobalAveragePooling2D()(x)
y = ....
model = keras.Model(input_tensor, y)
- 選項 b：
使用不可訓練的張量流操作將灰度輸入映射到 RGB，然后是 ImageNet 模型。
.. .flow_from_directory(
DATASET_DIR,
color_mode='grayscale', # < ------ SOVLED ISSUE 1
....
)
# rgb-imagenet-model
mobilenet = keras.applications.MobileNetV2(include_top=False,
weights='imagenet',
input_shape=(100, 100, 3))
# mapping grayscale to RGB
input_tensor = keras.Input(shape=(100, 100, 1))
gray_to_rgb = keras.layers.Lambda(lambda x:tf.image.grayscale_to_rgb(x),
output_shape=lambda x:x)
x = gray_to_rgb(input_tensor)
# followed by image-net model
x = mobilenet(x)
y = keras.layers.GlobalAveragePooling2D()(x)
model = keras.Model(input_tensor, y)
``
轉載請註明出處，本文鏈接：https://www.uj5u.com/shujuku/422905.html
標籤：
上一篇：獲取屬于一個用戶的所有帖子