def create_mtcnn_net(p_model_path=None, r_model_path=None, o_model_path=None, use_cuda=True):
pnet, rnet, onet = None, None, None
if p_model_path is not None:
pnet = PNet(use_cuda=use_cuda)
if(use_cuda):
pnet.load_state_dict(torch.load(p_model_path))
pnet.cuda()
else:
# forcing all GPU tensors to be in CPU while loading
pnet.load_state_dict(torch.load(p_model_path, map_location=lambda storage, loc: storage))
pnet.eval()
if r_model_path is not None:
rnet = RNet(use_cuda=use_cuda)
if (use_cuda):
rnet.load_state_dict(torch.load(r_model_path))
rnet.cuda()
else:
rnet.load_state_dict(torch.load(r_model_path, map_location=lambda storage, loc: storage))
rnet.eval()
if o_model_path is not None:
onet = ONet(use_cuda=use_cuda)
if (use_cuda):
onet.load_state_dict(torch.load(o_model_path))
onet.cuda()
else:
onet.load_state_dict(torch.load(o_model_path, map_location=lambda storage, loc: storage))
onet.eval()
return pnet,rnet,onet
def create_mtcnn_net(p_model_path=None,
r_model_path=None,
o_model_path=None,
use_cuda=True,
use_tucker2=False):
pnet, rnet, onet = None, None, None
if p_model_path is not None:
pnet = PNet(use_cuda=use_cuda)
if (use_cuda):
pnet.load_state_dict(torch.load(p_model_path))
pnet.cuda()
else:
# forcing all GPU tensors to be in CPU while loading
pnet.load_state_dict(
torch.load(p_model_path,
map_location=lambda storage, loc: storage))
pnet.eval()
if r_model_path is not None:
rnet = RNet(use_cuda=use_cuda)
if (use_cuda):
rnet.load_state_dict(torch.load(r_model_path))
rnet.cuda()
else:
rnet.load_state_dict(
torch.load(r_model_path,
map_location=lambda storage, loc: storage))
rnet.eval()
if o_model_path is not None:
onet = ONet(use_cuda=use_cuda)
if (use_cuda):
ckp = torch.load(o_model_path)
if use_tucker2:
onet.conv2 = Tkd2Conv(onet.conv2, 21, 25)
onet.conv3 = Tkd2Conv(onet.conv3, 36, 35)
onet.conv4 = Tkd2Conv(onet.conv4, 33, 18)
onet.load_state_dict(ckp)
onet.cuda()
else:
if use_tucker2:
onet.conv2 = Tkd2Conv(onet.conv2, 21, 25)
onet.conv3 = Tkd2Conv(onet.conv3, 36, 35)
onet.conv4 = Tkd2Conv(onet.conv4, 33, 18)
onet.load_state_dict(
torch.load(o_model_path,
map_location=lambda storage, loc: storage))
onet.eval()
return pnet, rnet, onet
def create_mtcnn_net(p_model_path=None,
r_model_path=None,
o_model_path=None,
use_cuda=True):
pnet, rnet, onet = None, None, None
if p_model_path is not None:
pnet = PNet(use_cuda=use_cuda)
pnet.load_state_dict(torch.load(p_model_path))
if (use_cuda):
pnet.cuda()
pnet.eval()
if r_model_path is not None:
rnet = RNet(use_cuda=use_cuda)
rnet.load_state_dict(torch.load(r_model_path))
if (use_cuda):
rnet.cuda()
rnet.eval()
if o_model_path is not None:
onet = ONet(use_cuda=use_cuda)
onet.load_state_dict(torch.load(o_model_path))
if (use_cuda):
onet.cuda()
onet.eval()
return pnet, rnet, onet
def create_mtcnn_net(p_model_path=None, r_model_path=None, o_model_path=None, use_cuda=True):
pnet, rnet, onet = None, None, None
if p_model_path is not None:
pnet = PNet(use_cuda=use_cuda)
if(use_cuda):
pnet = torch.nn.DataParallel(pnet,device_ids=[0]) #slove load pretrained error
pnet.load_state_dict(torch.load(p_model_path))
#pnet.cuda()
pnet = pnet.cuda()
#pnet = torch.nn.DataParallel(net, device_ids=range(torch.cuda.device_count()))
cudnn.benchmark = True
else:
# forcing all GPU tensors to be in CPU while loading
pnet.load_state_dict(torch.load(p_model_path, map_location=lambda storage, loc: storage))
pnet.eval()
if r_model_path is not None:
rnet = RNet(use_cuda=use_cuda)
if (use_cuda):
rnet = torch.nn.DataParallel(rnet,device_ids=[0])
rnet.load_state_dict(torch.load(r_model_path))
#rnet.cuda()
rnet=rnet.cuda()
cudnn.benchmark=True
else:
rnet.load_state_dict(torch.load(r_model_path, map_location=lambda storage, loc: storage))
rnet.eval()
if o_model_path is not None:
onet = ONet(use_cuda=use_cuda)
if (use_cuda):
onet = torch.nn.DataParallel(onet,device_ids=[0])
onet.load_state_dict(torch.load(o_model_path))
onet.cuda()
onet=onet.cuda()
cudnn.benchmark=True
else:
onet.load_state_dict(torch.load(o_model_path, map_location=lambda storage, loc: storage))
onet.eval()
return pnet,rnet,onet
def train_pnet(model_store_path,
end_epoch,
imdb,
batch_size,
frequent=50,
base_lr=0.01,
use_cuda=True):
if not os.path.exists(model_store_path):
os.makedirs(model_store_path)
lossfn = LossFn()
net = PNet(is_train=True, use_cuda=use_cuda)
net.train()
if use_cuda:
net.cuda()
optimizer = torch.optim.Adam(net.parameters(), lr=base_lr)
train_data = TrainImageReader(imdb, 12, batch_size, shuffle=True)
for cur_epoch in range(1, end_epoch + 1):
train_data.reset()
accuracy_list = []
cls_loss_list = []
bbox_loss_list = []
# landmark_loss_list=[]
for batch_idx, (image, (gt_label, gt_bbox,
gt_landmark)) in enumerate(train_data):
im_tensor = [
image_tools.convert_image_to_tensor(image[i, :, :, :])
for i in range(image.shape[0])
]
im_tensor = torch.stack(im_tensor)
im_tensor = Variable(im_tensor)
gt_label = Variable(torch.from_numpy(gt_label).float())
gt_bbox = Variable(torch.from_numpy(gt_bbox).float())
# gt_landmark = Variable(torch.from_numpy(gt_landmark).float())
if use_cuda:
im_tensor = im_tensor.cuda()
gt_label = gt_label.cuda()
gt_bbox = gt_bbox.cuda()
# gt_landmark = gt_landmark.cuda()
cls_pred, box_offset_pred = net(im_tensor)
# all_loss, cls_loss, offset_loss = lossfn.loss(gt_label=label_y,gt_offset=bbox_y, pred_label=cls_pred, pred_offset=box_offset_pred)
cls_loss = lossfn.cls_loss(gt_label, cls_pred)
box_offset_loss = lossfn.box_loss(gt_label, gt_bbox,
box_offset_pred)
# landmark_loss = lossfn.landmark_loss(gt_label,gt_landmark,landmark_offset_pred)
all_loss = cls_loss * 1.0 + box_offset_loss * 0.5
if batch_idx % frequent == 0:
accuracy = compute_accuracy(cls_pred, gt_label)
show1 = accuracy.data.tolist()
show2 = cls_loss.data.tolist()
show3 = box_offset_loss.data.tolist()
show5 = all_loss.data.tolist()
print(
"%s : Epoch: %d, Step: %d, accuracy: %s, det loss: %s, bbox loss: %s, all_loss: %s, lr:%s "
% (datetime.datetime.now(), cur_epoch, batch_idx, show1,
show2, show3, show5, base_lr))
accuracy_list.append(accuracy)
cls_loss_list.append(cls_loss)
bbox_loss_list.append(box_offset_loss)
optimizer.zero_grad()
all_loss.backward()
optimizer.step()
accuracy_avg = torch.mean(torch.stack(accuracy_list))
cls_loss_avg = torch.mean(torch.stack(cls_loss_list))
bbox_loss_avg = torch.mean(torch.stack(bbox_loss_list))
# landmark_loss_avg = torch.mean(torch.stack(landmark_loss_list))
show6 = accuracy_avg.data.tolist()
show7 = cls_loss_avg.data.tolist()
show8 = bbox_loss_avg.data.tolist()
print("Epoch: %d, accuracy: %s, cls loss: %s, bbox loss: %s" %
(cur_epoch, show6, show7, show8))
torch.save(
net.state_dict(),
os.path.join(model_store_path, "pnet_epoch_%d.pt" % cur_epoch))
torch.save(
net,
os.path.join(model_store_path,
"pnet_epoch_model_%d.pkl" % cur_epoch))