检测YOLOV5的SPP和SPPF和推理性能
from common import SPP,SPPF
import torch.nn as nn
import torch,time,thop
def time_synchronized():
# pytorch-accurate time
if torch.cuda.is_available():
torch.cuda.synchronize()
return time.time()
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}')
m1 = SPP(1024,1024)
m2 = SPPF(1024,1024)
result = profile(torch.randn(16,1024,64,64),ops=[m1,m2],n=100)
