File size: 9,876 Bytes
f12ab4c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 |
# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
#
# NVIDIA CORPORATION and its licensors retain all intellectual property
# and proprietary rights in and to this software, related documentation
# and any modifications thereto. Any use, reproduction, disclosure or
# distribution of this software and related documentation without an express
# license agreement from NVIDIA CORPORATION is strictly prohibited.
import os
import numpy as np
import tensorflow as tf
# Silence deprecation warnings from TensorFlow 1.13 onwards
import logging
logging.getLogger('tensorflow').setLevel(logging.ERROR)
from typing import Any, List
#----------------------------------------------------------------------------
# Projection and transformation matrix helpers.
#----------------------------------------------------------------------------
def projection(x=0.1, n=1.0, f=50.0):
return np.array([[n/x, 0, 0, 0],
[ 0, n/-x, 0, 0],
[ 0, 0, -(f+n)/(f-n), -(2*f*n)/(f-n)],
[ 0, 0, -1, 0]]).astype(np.float32)
def translate(x, y, z):
return np.array([[1, 0, 0, x],
[0, 1, 0, y],
[0, 0, 1, z],
[0, 0, 0, 1]]).astype(np.float32)
def rotate_x(a):
s, c = np.sin(a), np.cos(a)
return np.array([[1, 0, 0, 0],
[0, c, s, 0],
[0, -s, c, 0],
[0, 0, 0, 1]]).astype(np.float32)
def rotate_y(a):
s, c = np.sin(a), np.cos(a)
return np.array([[ c, 0, s, 0],
[ 0, 1, 0, 0],
[-s, 0, c, 0],
[ 0, 0, 0, 1]]).astype(np.float32)
def random_rotation_translation(t):
m = np.random.normal(size=[3, 3])
m[1] = np.cross(m[0], m[2])
m[2] = np.cross(m[0], m[1])
m = m / np.linalg.norm(m, axis=1, keepdims=True)
m = np.pad(m, [[0, 1], [0, 1]], mode='constant')
m[3, 3] = 1.0
m[:3, 3] = np.random.uniform(-t, t, size=[3])
return m
#----------------------------------------------------------------------------
# Bilinear downsample by 2x.
#----------------------------------------------------------------------------
def bilinear_downsample(x):
w = tf.constant([[1, 3, 3, 1], [3, 9, 9, 3], [3, 9, 9, 3], [1, 3, 3, 1]], dtype=tf.float32) / 64.0
w = w[..., tf.newaxis, tf.newaxis] * tf.eye(x.shape[-1].value, batch_shape=[1, 1])
x = tf.nn.conv2d(x, w, strides=2, padding='SAME')
return x
#----------------------------------------------------------------------------
# Image display function using OpenGL.
#----------------------------------------------------------------------------
_glfw_window = None
def display_image(image, zoom=None, size=None, title=None): # HWC
# Import OpenGL and glfw.
import OpenGL.GL as gl
import glfw
# Zoom image if requested.
image = np.asarray(image)
if size is not None:
assert zoom is None
zoom = max(1, size // image.shape[0])
if zoom is not None:
image = image.repeat(zoom, axis=0).repeat(zoom, axis=1)
height, width, channels = image.shape
# Initialize window.
if title is None:
title = 'Debug window'
global _glfw_window
if _glfw_window is None:
glfw.init()
_glfw_window = glfw.create_window(width, height, title, None, None)
glfw.make_context_current(_glfw_window)
glfw.show_window(_glfw_window)
glfw.swap_interval(0)
else:
glfw.make_context_current(_glfw_window)
glfw.set_window_title(_glfw_window, title)
glfw.set_window_size(_glfw_window, width, height)
# Update window.
glfw.poll_events()
gl.glClearColor(0, 0, 0, 1)
gl.glClear(gl.GL_COLOR_BUFFER_BIT)
gl.glWindowPos2f(0, 0)
gl.glPixelStorei(gl.GL_UNPACK_ALIGNMENT, 1)
gl_format = {3: gl.GL_RGB, 2: gl.GL_RG, 1: gl.GL_LUMINANCE}[channels]
gl_dtype = {'uint8': gl.GL_UNSIGNED_BYTE, 'float32': gl.GL_FLOAT}[image.dtype.name]
gl.glDrawPixels(width, height, gl_format, gl_dtype, image[::-1])
glfw.swap_buffers(_glfw_window)
if glfw.window_should_close(_glfw_window):
return False
return True
#----------------------------------------------------------------------------
# Image save helper.
#----------------------------------------------------------------------------
def save_image(fn, x):
import imageio
x = np.rint(x * 255.0)
x = np.clip(x, 0, 255).astype(np.uint8)
imageio.imsave(fn, x)
#----------------------------------------------------------------------------
# TensorFlow utilities
#----------------------------------------------------------------------------
def _sanitize_tf_config(config_dict: dict = None) -> dict:
# Defaults.
cfg = dict()
cfg["rnd.np_random_seed"] = None # Random seed for NumPy. None = keep as is.
cfg["rnd.tf_random_seed"] = "auto" # Random seed for TensorFlow. 'auto' = derive from NumPy random state. None = keep as is.
cfg["env.TF_CPP_MIN_LOG_LEVEL"] = "1" # 0 = Print all available debug info from TensorFlow. 1 = Print warnings and errors, but disable debug info.
cfg["env.HDF5_USE_FILE_LOCKING"] = "FALSE" # Disable HDF5 file locking to avoid concurrency issues with network shares.
cfg["graph_options.place_pruned_graph"] = True # False = Check that all ops are available on the designated device. True = Skip the check for ops that are not used.
cfg["gpu_options.allow_growth"] = True # False = Allocate all GPU memory at the beginning. True = Allocate only as much GPU memory as needed.
# Remove defaults for environment variables that are already set.
for key in list(cfg):
fields = key.split(".")
if fields[0] == "env":
assert len(fields) == 2
if fields[1] in os.environ:
del cfg[key]
# User overrides.
if config_dict is not None:
cfg.update(config_dict)
return cfg
def init_tf(config_dict: dict = None) -> None:
"""Initialize TensorFlow session using good default settings."""
# Skip if already initialized.
if tf.get_default_session() is not None:
return
# Setup config dict and random seeds.
cfg = _sanitize_tf_config(config_dict)
np_random_seed = cfg["rnd.np_random_seed"]
if np_random_seed is not None:
np.random.seed(np_random_seed)
tf_random_seed = cfg["rnd.tf_random_seed"]
if tf_random_seed == "auto":
tf_random_seed = np.random.randint(1 << 31)
if tf_random_seed is not None:
tf.set_random_seed(tf_random_seed)
# Setup environment variables.
for key, value in cfg.items():
fields = key.split(".")
if fields[0] == "env":
assert len(fields) == 2
os.environ[fields[1]] = str(value)
# Create default TensorFlow session.
create_session(cfg, force_as_default=True)
def assert_tf_initialized():
"""Check that TensorFlow session has been initialized."""
if tf.get_default_session() is None:
raise RuntimeError("No default TensorFlow session found. Please call util.init_tf().")
def create_session(config_dict: dict = None, force_as_default: bool = False) -> tf.Session:
"""Create tf.Session based on config dict."""
# Setup TensorFlow config proto.
cfg = _sanitize_tf_config(config_dict)
config_proto = tf.ConfigProto()
for key, value in cfg.items():
fields = key.split(".")
if fields[0] not in ["rnd", "env"]:
obj = config_proto
for field in fields[:-1]:
obj = getattr(obj, field)
setattr(obj, fields[-1], value)
# Create session.
session = tf.Session(config=config_proto)
if force_as_default:
# pylint: disable=protected-access
session._default_session = session.as_default()
session._default_session.enforce_nesting = False
session._default_session.__enter__()
return session
def is_tf_expression(x: Any) -> bool:
"""Check whether the input is a valid Tensorflow expression, i.e., Tensorflow Tensor, Variable, or Operation."""
return isinstance(x, (tf.Tensor, tf.Variable, tf.Operation))
def absolute_name_scope(scope: str) -> tf.name_scope:
"""Forcefully enter the specified name scope, ignoring any surrounding scopes."""
return tf.name_scope(scope + "/")
def init_uninitialized_vars(target_vars: List[tf.Variable] = None) -> None:
"""Initialize all tf.Variables that have not already been initialized.
Equivalent to the following, but more efficient and does not bloat the tf graph:
tf.variables_initializer(tf.report_uninitialized_variables()).run()
"""
assert_tf_initialized()
if target_vars is None:
target_vars = tf.global_variables()
test_vars = []
test_ops = []
with tf.control_dependencies(None): # ignore surrounding control_dependencies
for var in target_vars:
assert is_tf_expression(var)
try:
tf.get_default_graph().get_tensor_by_name(var.name.replace(":0", "/IsVariableInitialized:0"))
except KeyError:
# Op does not exist => variable may be uninitialized.
test_vars.append(var)
with absolute_name_scope(var.name.split(":")[0]):
test_ops.append(tf.is_variable_initialized(var))
init_vars = [var for var, inited in zip(test_vars, run(test_ops)) if not inited]
run([var.initializer for var in init_vars])
def run(*args, **kwargs) -> Any:
"""Run the specified ops in the default session."""
assert_tf_initialized()
return tf.get_default_session().run(*args, **kwargs)
|