将 tensorflow 属性添加到配置 class
Adding tensorflow properties into Config class
我有一个名为 BalloonConfig 的 Config class，它继承了 Config (config.py) 的属性。在我的 main.py 文件中 -
class BalloonConfig(Config):
"""Configuration for training on the toy dataset.
Derives from the base Config class and overrides some values.
"""
# Give the configuration a recognizable name
NAME = "Bubbles"
# We use a GPU with 12GB memory, which can fit two images.
# Adjust down if you use a smaller GPU.
IMAGES_PER_GPU = 1
GPU_COUNT = 1
# Number of classes (including background)
NUM_CLASSES = 1 + 1 # Background + baloon
# Number of training steps per epoch
STEPS_PER_EPOCH = 1000
# Skip detections with < 90% confidence
DETECTION_MIN_CONFIDENCE = 0.7
LEARNING_RATE = 0.0001
在我的 config.py 我有
import math
import numpy as np
import tensorflow as tf
# Base Configuration Class
# Don't use this class directly. Instead, sub-class it and override
# the configurations you need to change.
class Config():
"""Base configuration class. For custom configurations, create a
sub-class that inherits from this one and override properties
that need to be changed.
"""
# Name the configurations. For example, 'COCO', 'Experiment 3', ...etc.
# Useful if your code needs to do things differently depending on which
# experiment is running.
NAME = None # Override in sub-classes
# NUMBER OF GPUs to use. For CPU training, use 1
GPU_COUNT = 1
# Number of images to train with on each GPU. A 12GB GPU can typically
# handle 2 images of 1024x1024px.
# Adjust based on your GPU memory and image sizes. Use the highest
# number that your GPU can handle for best performance.
IMAGES_PER_GPU = 1
# Number of training steps per epoch
# This doesn't need to match the size of the training set. Tensorboard
# updates are saved at the end of each epoch, so setting this to a
# smaller number means getting more frequent TensorBoard updates.
# Validation stats are also calculated at each epoch end and they
# might take a while, so don't set this too small to avoid spending
# a lot of time on validation stats.
STEPS_PER_EPOCH = 1000
# Number of validation steps to run at the end of every training epoch.
# A bigger number improves accuracy of validation stats, but slows
# down the training.
VALIDATION_STEPS = 50
# Backbone network architecture
# Supported values are: resnet50, resnet101
BACKBONE = "resnet101"
# The strides of each layer of the FPN Pyramid. These values
# are based on a Resnet101 backbone.
BACKBONE_STRIDES = [4, 8, 16, 32, 64]
# Number of classification classes (including background)
NUM_CLASSES = 1 # Override in sub-classes
# Length of square anchor side in pixels
RPN_ANCHOR_SCALES = (32, 64, 128, 256, 512)
# Ratios of anchors at each cell (width/height)
# A value of 1 represents a square anchor, and 0.5 is a wide anchor
RPN_ANCHOR_RATIOS = [0.5, 1, 2]
# Anchor stride
# If 1 then anchors are created for each cell in the backbone feature map.
# If 2, then anchors are created for every other cell, and so on.
RPN_ANCHOR_STRIDE = 1
# Non-max suppression threshold to filter RPN proposals.
# You can increase this during training to generate more propsals.
RPN_NMS_THRESHOLD = 0.7
# How many anchors per image to use for RPN training
RPN_TRAIN_ANCHORS_PER_IMAGE = 256
# ROIs kept after non-maximum supression (training and inference)
POST_NMS_ROIS_TRAINING = 2000
POST_NMS_ROIS_INFERENCE = 1000
# If enabled, resizes instance masks to a smaller size to reduce
# memory load. Recommended when using high-resolution images.
USE_MINI_MASK = True
MINI_MASK_SHAPE = (56, 56) # (height, width) of the mini-mask
# Input image resizing
# Generally, use the "square" resizing mode for training and inferencing
# and it should work well in most cases. In this mode, images are scaled
# up such that the small side is = IMAGE_MIN_DIM, but ensuring that the
# scaling doesn't make the long side > IMAGE_MAX_DIM. Then the image is
# padded with zeros to make it a square so multiple images can be put
# in one batch.
# Available resizing modes:
# none: No resizing or padding. Return the image unchanged.
# square: Resize and pad with zeros to get a square image
# of size [max_dim, max_dim].
# pad64: Pads width and height with zeros to make them multiples of 64.
# If IMAGE_MIN_DIM or IMAGE_MIN_SCALE are not None, then it scales
# up before padding. IMAGE_MAX_DIM is ignored in this mode.
# The multiple of 64 is needed to ensure smooth scaling of feature
# maps up and down the 6 levels of the FPN pyramid (2**6=64).
# crop: Picks random crops from the image. First, scales the image based
# on IMAGE_MIN_DIM and IMAGE_MIN_SCALE, then picks a random crop of
# size IMAGE_MIN_DIM x IMAGE_MIN_DIM. Can be used in training only.
# IMAGE_MAX_DIM is not used in this mode.
IMAGE_RESIZE_MODE = "square"
IMAGE_MIN_DIM = 800
IMAGE_MAX_DIM = 1024
# Minimum scaling ratio. Checked after MIN_IMAGE_DIM and can force further
# up scaling. For example, if set to 2 then images are scaled up to double
# the width and height, or more, even if MIN_IMAGE_DIM doesn't require it.
# Howver, in 'square' mode, it can be overruled by IMAGE_MAX_DIM.
IMAGE_MIN_SCALE = 0
# Image mean (RGB)
MEAN_PIXEL = np.array([123.7, 116.8, 103.9])
# Number of ROIs per image to feed to classifier/mask heads
# The Mask RCNN paper uses 512 but often the RPN doesn't generate
# enough positive proposals to fill this and keep a positive:negative
# ratio of 1:3. You can increase the number of proposals by adjusting
# the RPN NMS threshold.
TRAIN_ROIS_PER_IMAGE = 200
# Percent of positive ROIs used to train classifier/mask heads
ROI_POSITIVE_RATIO = 0.33
# Pooled ROIs
POOL_SIZE = 7
MASK_POOL_SIZE = 14
# Shape of output mask
# To change this you also need to change the neural network mask branch
MASK_SHAPE = [28, 28]
# Maximum number of ground truth instances to use in one image
MAX_GT_INSTANCES = 100
# Bounding box refinement standard deviation for RPN and final detections.
RPN_BBOX_STD_DEV = np.array([0.1, 0.1, 0.2, 0.2])
BBOX_STD_DEV = np.array([0.1, 0.1, 0.2, 0.2])
# Max number of final detections
DETECTION_MAX_INSTANCES = 100
# Minimum probability value to accept a detected instance
# ROIs below this threshold are skipped
DETECTION_MIN_CONFIDENCE = 0.7
# Non-maximum suppression threshold for detection
DETECTION_NMS_THRESHOLD = 0.3
# Learning rate and momentum
# The Mask RCNN paper uses lr=0.02, but on TensorFlow it causes
# weights to explode. Likely due to differences in optimzer
# implementation.
LEARNING_RATE = 0.001
LEARNING_MOMENTUM = 0.9
# Weight decay regularization
WEIGHT_DECAY = 0.0001
# Use RPN ROIs or externally generated ROIs for training
# Keep this True for most situations. Set to False if you want to train
# the head branches on ROI generated by code rather than the ROIs from
# the RPN. For example, to debug the classifier head without having to
# train the RPN.
USE_RPN_ROIS = True
# Train or freeze batch normalization layers
# None: Train BN layers. This is the normal mode
# False: Freeze BN layers. Good when using a small batch size
# True: (don't use). Set layer in training mode even when inferencing
TRAIN_BN = False # Defaulting to False since batch size is often small
# Gradient norm clipping
GRADIENT_CLIP_NORM = 5.0
def __init__(self):
"""Set values of computed attributes."""
# Effective batch size
self.BATCH_SIZE = self.IMAGES_PER_GPU * self.GPU_COUNT
# Input image size
if self.IMAGE_RESIZE_MODE == "crop":
self.IMAGE_SHAPE = np.array([self.IMAGE_MIN_DIM, self.IMAGE_MIN_DIM, 3])
else:
self.IMAGE_SHAPE = np.array([self.IMAGE_MAX_DIM, self.IMAGE_MAX_DIM, 3])
# Image meta data length
# See compose_image_meta() for details
self.IMAGE_META_SIZE = 1 + 3 + 3 + 4 + 1 + self.NUM_CLASSES
def display(self):
"""Display Configuration values."""
print("\nConfigurations:")
for a in dir(self):
if not a.startswith("__") and not callable(getattr(self, a)):
print("{:30} {}".format(a, getattr(self, a)))
print("\n")
我将使用 argpars
在我的 main.py 中启动 运行 脚本
# Configurations
if args.command == "train":
config = BalloonConfig()
# Create model
if args.command == "train":
# print('test')
model = modellib.MaskRCNN(mode="training", config=config,
model_dir=args.logs)
它会创建模型并将配置文件分配给 BalloonConfig()。但是发现是GPU显存不够，训练启动失败。经过一些研究，我在 tensorflow 中遇到了一种叫做 GPU 增长的东西，它可以解决我的内存不足问题 -
config = tf.ConfigProto()
config.gpu_options.allow_growth=True
sess = tf.Session(config=config)
但是，我不知道如何将它实现到我的代码中，因为我无法将我的配置文件分配给 tf.ConfigProto()，因为我已经将它分配给了 BalloonConfig()。那么我可以知道如何在我的脚本中设置 gpu_options.allow_growth 吗？谢谢。
如果 tf.session 可以理解您的 BalloonConfig，只需将 属性 添加到您的配置中即可：
# Configurations
if args.command == "train":
config = BalloonConfig()
config.gpu_options.allow_growth=True
如果没有，您应该像这样定义 BalloonConfig class（然后执行上述操作）：
class BalloonConfig(tf.ConfigProto):
#...
对于可能面临同样问题并想添加 config.gpu_options.allow_growth=True 的任何人，我设法通过添加 3 行解决了问题：
conf = tf.ConfigProto()
conf.gpu_options.allow_growth=True
session = tf.Session(config=conf)
在文件中导入tensorflow（import tensorflow as tf）后进行训练或推理，然后gpu allow growth选项将立即激活。不太清楚它为什么有效，但希望它能帮助任何需要它的人！
我有一个名为 BalloonConfig 的 Config class，它继承了 Config (config.py) 的属性。在我的 main.py 文件中 -
class BalloonConfig(Config):
"""Configuration for training on the toy dataset.
Derives from the base Config class and overrides some values.
"""
# Give the configuration a recognizable name
NAME = "Bubbles"
# We use a GPU with 12GB memory, which can fit two images.
# Adjust down if you use a smaller GPU.
IMAGES_PER_GPU = 1
GPU_COUNT = 1
# Number of classes (including background)
NUM_CLASSES = 1 + 1 # Background + baloon
# Number of training steps per epoch
STEPS_PER_EPOCH = 1000
# Skip detections with < 90% confidence
DETECTION_MIN_CONFIDENCE = 0.7
LEARNING_RATE = 0.0001
在我的 config.py 我有
import math
import numpy as np
import tensorflow as tf
# Base Configuration Class
# Don't use this class directly. Instead, sub-class it and override
# the configurations you need to change.
class Config():
"""Base configuration class. For custom configurations, create a
sub-class that inherits from this one and override properties
that need to be changed.
"""
# Name the configurations. For example, 'COCO', 'Experiment 3', ...etc.
# Useful if your code needs to do things differently depending on which
# experiment is running.
NAME = None # Override in sub-classes
# NUMBER OF GPUs to use. For CPU training, use 1
GPU_COUNT = 1
# Number of images to train with on each GPU. A 12GB GPU can typically
# handle 2 images of 1024x1024px.
# Adjust based on your GPU memory and image sizes. Use the highest
# number that your GPU can handle for best performance.
IMAGES_PER_GPU = 1
# Number of training steps per epoch
# This doesn't need to match the size of the training set. Tensorboard
# updates are saved at the end of each epoch, so setting this to a
# smaller number means getting more frequent TensorBoard updates.
# Validation stats are also calculated at each epoch end and they
# might take a while, so don't set this too small to avoid spending
# a lot of time on validation stats.
STEPS_PER_EPOCH = 1000
# Number of validation steps to run at the end of every training epoch.
# A bigger number improves accuracy of validation stats, but slows
# down the training.
VALIDATION_STEPS = 50
# Backbone network architecture
# Supported values are: resnet50, resnet101
BACKBONE = "resnet101"
# The strides of each layer of the FPN Pyramid. These values
# are based on a Resnet101 backbone.
BACKBONE_STRIDES = [4, 8, 16, 32, 64]
# Number of classification classes (including background)
NUM_CLASSES = 1 # Override in sub-classes
# Length of square anchor side in pixels
RPN_ANCHOR_SCALES = (32, 64, 128, 256, 512)
# Ratios of anchors at each cell (width/height)
# A value of 1 represents a square anchor, and 0.5 is a wide anchor
RPN_ANCHOR_RATIOS = [0.5, 1, 2]
# Anchor stride
# If 1 then anchors are created for each cell in the backbone feature map.
# If 2, then anchors are created for every other cell, and so on.
RPN_ANCHOR_STRIDE = 1
# Non-max suppression threshold to filter RPN proposals.
# You can increase this during training to generate more propsals.
RPN_NMS_THRESHOLD = 0.7
# How many anchors per image to use for RPN training
RPN_TRAIN_ANCHORS_PER_IMAGE = 256
# ROIs kept after non-maximum supression (training and inference)
POST_NMS_ROIS_TRAINING = 2000
POST_NMS_ROIS_INFERENCE = 1000
# If enabled, resizes instance masks to a smaller size to reduce
# memory load. Recommended when using high-resolution images.
USE_MINI_MASK = True
MINI_MASK_SHAPE = (56, 56) # (height, width) of the mini-mask
# Input image resizing
# Generally, use the "square" resizing mode for training and inferencing
# and it should work well in most cases. In this mode, images are scaled
# up such that the small side is = IMAGE_MIN_DIM, but ensuring that the
# scaling doesn't make the long side > IMAGE_MAX_DIM. Then the image is
# padded with zeros to make it a square so multiple images can be put
# in one batch.
# Available resizing modes:
# none: No resizing or padding. Return the image unchanged.
# square: Resize and pad with zeros to get a square image
# of size [max_dim, max_dim].
# pad64: Pads width and height with zeros to make them multiples of 64.
# If IMAGE_MIN_DIM or IMAGE_MIN_SCALE are not None, then it scales
# up before padding. IMAGE_MAX_DIM is ignored in this mode.
# The multiple of 64 is needed to ensure smooth scaling of feature
# maps up and down the 6 levels of the FPN pyramid (2**6=64).
# crop: Picks random crops from the image. First, scales the image based
# on IMAGE_MIN_DIM and IMAGE_MIN_SCALE, then picks a random crop of
# size IMAGE_MIN_DIM x IMAGE_MIN_DIM. Can be used in training only.
# IMAGE_MAX_DIM is not used in this mode.
IMAGE_RESIZE_MODE = "square"
IMAGE_MIN_DIM = 800
IMAGE_MAX_DIM = 1024
# Minimum scaling ratio. Checked after MIN_IMAGE_DIM and can force further
# up scaling. For example, if set to 2 then images are scaled up to double
# the width and height, or more, even if MIN_IMAGE_DIM doesn't require it.
# Howver, in 'square' mode, it can be overruled by IMAGE_MAX_DIM.
IMAGE_MIN_SCALE = 0
# Image mean (RGB)
MEAN_PIXEL = np.array([123.7, 116.8, 103.9])
# Number of ROIs per image to feed to classifier/mask heads
# The Mask RCNN paper uses 512 but often the RPN doesn't generate
# enough positive proposals to fill this and keep a positive:negative
# ratio of 1:3. You can increase the number of proposals by adjusting
# the RPN NMS threshold.
TRAIN_ROIS_PER_IMAGE = 200
# Percent of positive ROIs used to train classifier/mask heads
ROI_POSITIVE_RATIO = 0.33
# Pooled ROIs
POOL_SIZE = 7
MASK_POOL_SIZE = 14
# Shape of output mask
# To change this you also need to change the neural network mask branch
MASK_SHAPE = [28, 28]
# Maximum number of ground truth instances to use in one image
MAX_GT_INSTANCES = 100
# Bounding box refinement standard deviation for RPN and final detections.
RPN_BBOX_STD_DEV = np.array([0.1, 0.1, 0.2, 0.2])
BBOX_STD_DEV = np.array([0.1, 0.1, 0.2, 0.2])
# Max number of final detections
DETECTION_MAX_INSTANCES = 100
# Minimum probability value to accept a detected instance
# ROIs below this threshold are skipped
DETECTION_MIN_CONFIDENCE = 0.7
# Non-maximum suppression threshold for detection
DETECTION_NMS_THRESHOLD = 0.3
# Learning rate and momentum
# The Mask RCNN paper uses lr=0.02, but on TensorFlow it causes
# weights to explode. Likely due to differences in optimzer
# implementation.
LEARNING_RATE = 0.001
LEARNING_MOMENTUM = 0.9
# Weight decay regularization
WEIGHT_DECAY = 0.0001
# Use RPN ROIs or externally generated ROIs for training
# Keep this True for most situations. Set to False if you want to train
# the head branches on ROI generated by code rather than the ROIs from
# the RPN. For example, to debug the classifier head without having to
# train the RPN.
USE_RPN_ROIS = True
# Train or freeze batch normalization layers
# None: Train BN layers. This is the normal mode
# False: Freeze BN layers. Good when using a small batch size
# True: (don't use). Set layer in training mode even when inferencing
TRAIN_BN = False # Defaulting to False since batch size is often small
# Gradient norm clipping
GRADIENT_CLIP_NORM = 5.0
def __init__(self):
"""Set values of computed attributes."""
# Effective batch size
self.BATCH_SIZE = self.IMAGES_PER_GPU * self.GPU_COUNT
# Input image size
if self.IMAGE_RESIZE_MODE == "crop":
self.IMAGE_SHAPE = np.array([self.IMAGE_MIN_DIM, self.IMAGE_MIN_DIM, 3])
else:
self.IMAGE_SHAPE = np.array([self.IMAGE_MAX_DIM, self.IMAGE_MAX_DIM, 3])
# Image meta data length
# See compose_image_meta() for details
self.IMAGE_META_SIZE = 1 + 3 + 3 + 4 + 1 + self.NUM_CLASSES
def display(self):
"""Display Configuration values."""
print("\nConfigurations:")
for a in dir(self):
if not a.startswith("__") and not callable(getattr(self, a)):
print("{:30} {}".format(a, getattr(self, a)))
print("\n")
我将使用 argpars
在我的 main.py 中启动 运行 脚本 # Configurations
if args.command == "train":
config = BalloonConfig()
# Create model
if args.command == "train":
# print('test')
model = modellib.MaskRCNN(mode="training", config=config,
model_dir=args.logs)
它会创建模型并将配置文件分配给 BalloonConfig()。但是发现是GPU显存不够，训练启动失败。经过一些研究，我在 tensorflow 中遇到了一种叫做 GPU 增长的东西，它可以解决我的内存不足问题 -
config = tf.ConfigProto()
config.gpu_options.allow_growth=True
sess = tf.Session(config=config)
但是，我不知道如何将它实现到我的代码中，因为我无法将我的配置文件分配给 tf.ConfigProto()，因为我已经将它分配给了 BalloonConfig()。那么我可以知道如何在我的脚本中设置 gpu_options.allow_growth 吗？谢谢。
如果 tf.session 可以理解您的 BalloonConfig，只需将 属性 添加到您的配置中即可：
# Configurations
if args.command == "train":
config = BalloonConfig()
config.gpu_options.allow_growth=True
如果没有，您应该像这样定义 BalloonConfig class（然后执行上述操作）：
class BalloonConfig(tf.ConfigProto):
#...
对于可能面临同样问题并想添加 config.gpu_options.allow_growth=True 的任何人，我设法通过添加 3 行解决了问题：
conf = tf.ConfigProto()
conf.gpu_options.allow_growth=True
session = tf.Session(config=conf)
在文件中导入tensorflow（import tensorflow as tf）后进行训练或推理，然后gpu allow growth选项将立即激活。不太清楚它为什么有效，但希望它能帮助任何需要它的人！