329 lines
13 KiB
Python
329 lines
13 KiB
Python
# YOLOv5 PyTorch utils
|
||
from loguru import logger
|
||
|
||
import math, os, platform, subprocess, time, torch, torchvision
|
||
from contextlib import contextmanager
|
||
from copy import deepcopy
|
||
from pathlib import Path
|
||
|
||
import torch.backends.cudnn as cudnn
|
||
import torch.nn as nn
|
||
import torch.nn.functional as F
|
||
|
||
try:
|
||
import thop # for FLOPS computation
|
||
except ImportError:
|
||
thop = None
|
||
|
||
|
||
def git_describe(path=Path(__file__).parent): # path must be a directory
|
||
"""
|
||
获取git仓库的人类可读描述信息
|
||
|
||
该函数调用git describe命令来获取当前仓库的标签描述信息，
|
||
返回格式类似于v5.0-5-g3e25f1e的字符串
|
||
|
||
参数:
|
||
path (Path): git仓库路径，默认为当前文件所在目录
|
||
|
||
返回:
|
||
str: git描述信息字符串，如果执行失败则返回空字符串
|
||
"""
|
||
# return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe
|
||
s = f'git -C {path} describe --tags --long --always'
|
||
try:
|
||
return subprocess.check_output(s, shell=True, stderr=subprocess.STDOUT).decode()[:-1]
|
||
except subprocess.CalledProcessError as e:
|
||
return '' # not a git repository
|
||
|
||
def select_device(device='', batch_size=None):
|
||
"""
|
||
选择并配置训练/推理设备(CPU或GPU)
|
||
|
||
参数:
|
||
device (str): 设备标识符，可以是'cpu'表示使用CPU，'0'表示使用第一个GPU，
|
||
'0,1,2,3'表示使用多个GPU
|
||
batch_size (int, optional): 批处理大小，用于验证是否与GPU数量兼容
|
||
|
||
返回:
|
||
torch.device: 配置好的PyTorch设备对象
|
||
"""
|
||
# device = 'cpu' or '0' or '0,1,2,3'
|
||
from DrGraph.util.drHelper import timeHelper
|
||
s = f'YOLOv5 🚀 {git_describe() or timeHelper.date_modified()} torch {torch.__version__} ' # string
|
||
cpu = device.lower() == 'cpu'
|
||
if cpu:
|
||
os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # force torch.cuda.is_available() = False
|
||
elif device: # non-cpu device requested
|
||
os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable
|
||
assert torch.cuda.is_available(), f'CUDA unavailable, invalid device {device} requested' # check availability
|
||
|
||
cuda = not cpu and torch.cuda.is_available()
|
||
if cuda:
|
||
n = torch.cuda.device_count()
|
||
if n > 1 and batch_size: # check that batch_size is compatible with device_count
|
||
assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}'
|
||
space = ' ' * len(s)
|
||
for i, d in enumerate(device.split(',') if device else range(n)):
|
||
p = torch.cuda.get_device_properties(i)
|
||
s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2}MB)\n" # bytes to MB
|
||
else:
|
||
s += 'CPU\n'
|
||
|
||
logger.info(f"select_device {s.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else s}") # emoji-safe
|
||
return torch.device('cuda:0' if cuda else 'cpu')
|
||
|
||
def init_torch_seeds(seed=0):
|
||
"""
|
||
初始化PyTorch的随机种子，用于控制随机性以实现结果的可重现性
|
||
|
||
参数:
|
||
seed (int): 随机种子值，默认为0
|
||
|
||
返回值:
|
||
无返回值
|
||
|
||
说明:
|
||
该函数通过设置不同的seed值来平衡运算速度和结果可重现性
|
||
seed=0时追求最大可重现性但速度较慢
|
||
seed!=0时追求更快的运算速度但可重现性降低
|
||
"""
|
||
# Speed-reproducibility tradeoff https://pytorch.org/docs/stable/notes/randomness.html
|
||
torch.manual_seed(seed)
|
||
# 根据seed值设置CUDA的运算模式以平衡速度和可重现性
|
||
if seed == 0: # slower, more reproducible
|
||
cudnn.benchmark, cudnn.deterministic = False, True
|
||
else: # faster, less reproducible
|
||
cudnn.benchmark, cudnn.deterministic = True, False
|
||
|
||
@contextmanager
|
||
def torch_distributed_zero_first(local_rank: int):
|
||
"""
|
||
Decorator to make all processes in distributed training wait for each local_master to do something.
|
||
"""
|
||
if local_rank not in [-1, 0]:
|
||
torch.distributed.barrier()
|
||
yield
|
||
if local_rank == 0:
|
||
torch.distributed.barrier()
|
||
|
||
def time_synchronized():
|
||
# pytorch-accurate time
|
||
if torch.cuda.is_available():
|
||
torch.cuda.synchronize()
|
||
return time.time()
|
||
|
||
|
||
def check_cuda_is_available():
|
||
if not torch.cuda.is_available():
|
||
raise Exception("cuda不在活动状态, 请检测显卡驱动是否正常！！！！")
|
||
|
||
def profile(x, ops, n=100, device=None):
|
||
# profile a pytorch module or list of modules. Example usage:
|
||
# x = torch.randn(16, 3, 640, 640) # input
|
||
# m1 = lambda x: x * torch.sigmoid(x)
|
||
# m2 = nn.SiLU()
|
||
# profile(x, [m1, m2], n=100) # profile speed over 100 iterations
|
||
|
||
device = device or torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
|
||
x = x.to(device)
|
||
x.requires_grad = True
|
||
print(torch.__version__, device.type, torch.cuda.get_device_properties(0) if device.type == 'cuda' else '')
|
||
print(f"\n{'Params':>12s}{'GFLOPS':>12s}{'forward (ms)':>16s}{'backward (ms)':>16s}{'input':>24s}{'output':>24s}")
|
||
for m in ops if isinstance(ops, list) else [ops]:
|
||
m = m.to(device) if hasattr(m, 'to') else m # device
|
||
m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m # type
|
||
dtf, dtb, t = 0., 0., [0., 0., 0.] # dt forward, backward
|
||
try:
|
||
flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # GFLOPS
|
||
except:
|
||
flops = 0
|
||
|
||
for _ in range(n):
|
||
t[0] = time_synchronized()
|
||
y = m(x)
|
||
t[1] = time_synchronized()
|
||
try:
|
||
_ = y.sum().backward()
|
||
t[2] = time_synchronized()
|
||
except: # no backward method
|
||
t[2] = float('nan')
|
||
dtf += (t[1] - t[0]) * 1000 / n # ms per op forward
|
||
dtb += (t[2] - t[1]) * 1000 / n # ms per op backward
|
||
|
||
s_in = tuple(x.shape) if isinstance(x, torch.Tensor) else 'list'
|
||
s_out = tuple(y.shape) if isinstance(y, torch.Tensor) else 'list'
|
||
p = sum(list(x.numel() for x in m.parameters())) if isinstance(m, nn.Module) else 0 # parameters
|
||
print(f'{p:12}{flops:12.4g}{dtf:16.4g}{dtb:16.4g}{str(s_in):>24s}{str(s_out):>24s}')
|
||
|
||
|
||
def is_parallel(model):
|
||
return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel)
|
||
|
||
|
||
def intersect_dicts(da, db, exclude=()):
|
||
# Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values
|
||
return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape}
|
||
|
||
|
||
def initialize_weights(model):
|
||
for m in model.modules():
|
||
t = type(m)
|
||
if t is nn.Conv2d:
|
||
pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
|
||
elif t is nn.BatchNorm2d:
|
||
m.eps = 1e-3
|
||
m.momentum = 0.03
|
||
elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
|
||
m.inplace = True
|
||
|
||
|
||
def find_modules(model, mclass=nn.Conv2d):
|
||
# Finds layer indices matching module class 'mclass'
|
||
return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)]
|
||
|
||
|
||
def sparsity(model):
|
||
# Return global model sparsity
|
||
a, b = 0., 0.
|
||
for p in model.parameters():
|
||
a += p.numel()
|
||
b += (p == 0).sum()
|
||
return b / a
|
||
|
||
|
||
def prune(model, amount=0.3):
|
||
# Prune model to requested global sparsity
|
||
import torch.nn.utils.prune as prune
|
||
print('Pruning model... ', end='')
|
||
for name, m in model.named_modules():
|
||
if isinstance(m, nn.Conv2d):
|
||
prune.l1_unstructured(m, name='weight', amount=amount) # prune
|
||
prune.remove(m, 'weight') # make permanent
|
||
print(' %.3g global sparsity' % sparsity(model))
|
||
|
||
|
||
def fuse_conv_and_bn(conv, bn):
|
||
# Fuse convolution and batchnorm layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/
|
||
fusedconv = nn.Conv2d(conv.in_channels,
|
||
conv.out_channels,
|
||
kernel_size=conv.kernel_size,
|
||
stride=conv.stride,
|
||
padding=conv.padding,
|
||
groups=conv.groups,
|
||
bias=True).requires_grad_(False).to(conv.weight.device)
|
||
|
||
# prepare filters
|
||
w_conv = conv.weight.clone().view(conv.out_channels, -1)
|
||
w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
|
||
fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape))
|
||
|
||
# prepare spatial bias
|
||
b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias
|
||
b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
|
||
fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn)
|
||
|
||
return fusedconv
|
||
|
||
|
||
def model_info(model, verbose=False, img_size=640):
|
||
# Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320]
|
||
n_p = sum(x.numel() for x in model.parameters()) # number parameters
|
||
n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients
|
||
if verbose:
|
||
print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
|
||
for i, (name, p) in enumerate(model.named_parameters()):
|
||
name = name.replace('module_list.', '')
|
||
print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
|
||
(i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
|
||
|
||
try: # FLOPS
|
||
from thop import profile
|
||
stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32
|
||
img = torch.zeros((1, model.yaml.get('ch', 3), stride, stride), device=next(model.parameters()).device) # input
|
||
flops = profile(deepcopy(model), inputs=(img,), verbose=False)[0] / 1E9 * 2 # stride GFLOPS
|
||
img_size = img_size if isinstance(img_size, list) else [img_size, img_size] # expand if int/float
|
||
fs = ', %.1f GFLOPS' % (flops * img_size[0] / stride * img_size[1] / stride) # 640x640 GFLOPS
|
||
except (ImportError, Exception):
|
||
fs = ''
|
||
|
||
logger.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}")
|
||
|
||
|
||
def load_classifier(name='resnet101', n=2):
|
||
# Loads a pretrained model reshaped to n-class output
|
||
model = torchvision.models.__dict__[name](pretrained=True)
|
||
|
||
# ResNet model properties
|
||
# input_size = [3, 224, 224]
|
||
# input_space = 'RGB'
|
||
# input_range = [0, 1]
|
||
# mean = [0.485, 0.456, 0.406]
|
||
# std = [0.229, 0.224, 0.225]
|
||
|
||
# Reshape output to n classes
|
||
filters = model.fc.weight.shape[1]
|
||
model.fc.bias = nn.Parameter(torch.zeros(n), requires_grad=True)
|
||
model.fc.weight = nn.Parameter(torch.zeros(n, filters), requires_grad=True)
|
||
model.fc.out_features = n
|
||
return model
|
||
|
||
|
||
def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416)
|
||
# scales img(bs,3,y,x) by ratio constrained to gs-multiple
|
||
if ratio == 1.0:
|
||
return img
|
||
else:
|
||
h, w = img.shape[2:]
|
||
s = (int(h * ratio), int(w * ratio)) # new size
|
||
img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize
|
||
if not same_shape: # pad/crop img
|
||
h, w = [math.ceil(x * ratio / gs) * gs for x in (h, w)]
|
||
return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean
|
||
|
||
|
||
def copy_attr(a, b, include=(), exclude=()):
|
||
# Copy attributes from b to a, options to only include [...] and to exclude [...]
|
||
for k, v in b.__dict__.items():
|
||
if (len(include) and k not in include) or k.startswith('_') or k in exclude:
|
||
continue
|
||
else:
|
||
setattr(a, k, v)
|
||
|
||
|
||
class ModelEMA:
|
||
""" Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models
|
||
Keep a moving average of everything in the model state_dict (parameters and buffers).
|
||
This is intended to allow functionality like
|
||
https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage
|
||
A smoothed version of the weights is necessary for some training schemes to perform well.
|
||
This class is sensitive where it is initialized in the sequence of model init,
|
||
GPU assignment and distributed training wrappers.
|
||
"""
|
||
|
||
def __init__(self, model, decay=0.9999, updates=0):
|
||
# Create EMA
|
||
self.ema = deepcopy(model.module if is_parallel(model) else model).eval() # FP32 EMA
|
||
# if next(model.parameters()).device.type != 'cpu':
|
||
# self.ema.half() # FP16 EMA
|
||
self.updates = updates # number of EMA updates
|
||
self.decay = lambda x: decay * (1 - math.exp(-x / 2000)) # decay exponential ramp (to help early epochs)
|
||
for p in self.ema.parameters():
|
||
p.requires_grad_(False)
|
||
|
||
def update(self, model):
|
||
# Update EMA parameters
|
||
with torch.no_grad():
|
||
self.updates += 1
|
||
d = self.decay(self.updates)
|
||
|
||
msd = model.module.state_dict() if is_parallel(model) else model.state_dict() # model state_dict
|
||
for k, v in self.ema.state_dict().items():
|
||
if v.dtype.is_floating_point:
|
||
v *= d
|
||
v += (1. - d) * msd[k].detach()
|
||
|
||
def update_attr(self, model, include=(), exclude=('process_group', 'reducer')):
|
||
# Update EMA attributes
|
||
copy_attr(self.ema, model, include, exclude)
|