Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updates

This commit is contained in:
Glenn Jocher 2020-03-04 10:26:35 -08:00
parent 35eae3ace9
commit 1430a1e408
2 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
test.py
View File

@ -84,18 +84,18 @@ def test(cfg,
# Disable gradients # Disable gradients
with torch.no_grad(): with torch.no_grad():
# Run model # Run model
t = time.time() t = torch_utils.time_synchronized()
inf_out, train_out = model(imgs) # inference and training outputs inf_out, train_out = model(imgs) # inference and training outputs
t0 += time.time() - t t0 += torch_utils.time_synchronized() - t
# Compute loss # Compute loss
if hasattr(model, 'hyp'): # if model has loss hyperparameters if hasattr(model, 'hyp'): # if model has loss hyperparameters
loss += compute_loss(train_out, targets, model)[1][:3].cpu() # GIoU, obj, cls loss += compute_loss(train_out, targets, model)[1][:3].cpu() # GIoU, obj, cls
# Run NMS # Run NMS
t = time.time() t = torch_utils.time_synchronized()
output = non_max_suppression(inf_out, conf_thres=conf_thres, iou_thres=iou_thres) output = non_max_suppression(inf_out, conf_thres=conf_thres, iou_thres=iou_thres) # nms
t1 += time.time() - t t1 += torch_utils.time_synchronized() - t
# Statistics per image # Statistics per image
for si, pred in enumerate(output): for si, pred in enumerate(output):

6
utils/torch_utils.py
View File

@ -1,4 +1,5 @@
import os import os
import time
import torch import torch
import torch.backends.cudnn as cudnn import torch.backends.cudnn as cudnn
@ -40,6 +41,11 @@ def select_device(device='', apex=False, batch_size=None):
return torch.device('cuda:0' if cuda else 'cpu') return torch.device('cuda:0' if cuda else 'cpu')
def time_synchronized():
torch.cuda.synchronize() if torch.cuda.is_available() else None
return time.time()
def fuse_conv_and_bn(conv, bn): def fuse_conv_and_bn(conv, bn):
# https://tehnokv.com/posts/fusing-batchnorm-and-conv/ # https://tehnokv.com/posts/fusing-batchnorm-and-conv/
with torch.no_grad(): with torch.no_grad():