weights_init(model)
# #------------------------------------------------------#
# 权值文件请看README，百度网盘下载
#------------------------------------------------------#
model_path = 'model_data/voc_weights_resnet.pth'
print('Loading weights into state dict...')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model_dict = model.state_dict()
pretrained_dict = torch.load(model_path, map_location=device)
pretrained_dict = {k: v for k, v in pretrained_dict.items() if np.shape(model_dict[k]) == np.shape(v)}
model_dict.update(pretrained_dict)
model.load_state_dict(model_dict)
print('Finished!')
net = model.train()
if Cuda:
net = torch.nn.DataParallel(model)
cudnn.benchmark = True
net = net.cuda()
loss_history = LossHistory("logs/")
annotation_path = '2007_train.txt'
#----------------------------------------------------------------------#
# 验证集的划分在train.py代码里面进行
# 2007_test.txt和2007_val.txt里面没有内容是正常的。训练不会使用到。
# 当前划分方式下，验证集和训练集的比例为1:9
#----------------------------------------------------------------------#
val_split = 0.1
with open(annotation_path) as f:
model_path = 'model_data/voc_weights_resnet.pth'
print('Loading weights into state dict...')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model_dict = model.state_dict() #OrderedDict :328
pretrained_dict = torch.load(model_path,
map_location=device) #OrderedDict :328
pretrained_dict = {
k: v
for k, v in pretrained_dict.items()
if np.shape(model_dict[k]) == np.shape(v)
}
model_dict.update(pretrained_dict) #更新模型的预训练参数
model.load_state_dict(model_dict)
print('Finished!')
net = model.train() #设置model为训练模式
if Cuda:
net = torch.nn.DataParallel(model)
cudnn.benchmark = True
net = net.cuda()
annotation_path = 'train.txt'
#----------------------------------------------------------------------#
# 验证集的划分在train.py代码里面进行
# 2007_test.txt和2007_val.txt里面没有内容是正常的。训练不会使用到。
# 当前划分方式下，验证集和训练集的比例为1:9
#----------------------------------------------------------------------#
val_split = 0.1
with open(annotation_path) as f:
lines = f.readlines()
np.random.seed(10101)
