本文整理汇总了Python中core.config.cfg.ROOT_DIR属性的典型用法代码示例。如果您正苦于以下问题：Python cfg.ROOT_DIR属性的具体用法？Python cfg.ROOT_DIR怎么用？Python cfg.ROOT_DIR使用的例子？那么恭喜您, 这里精选的属性代码示例或许可以为您提供帮助。您也可以进一步了解该属性所在类core.config.cfg的用法示例。
在下文中一共展示了cfg.ROOT_DIR属性的5个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _do_matlab_eval
# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import ROOT_DIR [as 别名]
def _do_matlab_eval(json_dataset, salt, output_dir='output'):
import subprocess
logger.info('-----------------------------------------------------')
logger.info('Computing results with the official MATLAB eval code.')
logger.info('-----------------------------------------------------')
info = voc_info(json_dataset)
path = os.path.join(
cfg.ROOT_DIR, 'lib', 'datasets', 'VOCdevkit-matlab-wrapper')
cmd = 'cd {} && '.format(path)
cmd += '{:s} -nodisplay -nodesktop '.format(cfg.MATLAB)
cmd += '-r "dbstop if error; '
cmd += 'voc_eval(\'{:s}\',\'{:s}\',\'{:s}\',\'{:s}\'); quit;"' \
.format(info['devkit_path'], 'comp4' + salt, info['image_set'],
output_dir)
logger.info('Running:\n{}'.format(cmd))
subprocess.call(cmd, shell=True) 示例2: mobilenet_load_pretrained_imagenet_weights
# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import ROOT_DIR [as 别名]
def mobilenet_load_pretrained_imagenet_weights(model):
"""Load pretrained weights
Args:
model: the generalized rcnnn module
"""
_, ext = os.path.splitext(cfg.TRAIN.IMAGENET_PRETRAINED_WEIGHTS)
if ext == '.pkl':
with open(cfg.TRAIN.IMAGENET_PRETRAINED_WEIGHTS, 'rb') as fp:
src_blobs = pickle.load(fp, encoding='latin1')
if 'blobs' in src_blobs:
src_blobs = src_blobs['blobs']
pretrianed_state_dict = src_blobs
else:
weights_file = os.path.join(cfg.ROOT_DIR, cfg.TRAIN.IMAGENET_PRETRAINED_WEIGHTS)
pretrianed_state_dict = mobilenet_convert_state_dict(torch.load(weights_file))
model.Conv_Body.conv.load_state_dict(pretrianed_state_dict, strict=False)
if hasattr(model, 'Box_Head'):
model.Box_Head.conv.load_state_dict(pretrianed_state_dict, strict=False) 示例3: vgg_load_pretrained_imagenet_weights
# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import ROOT_DIR [as 别名]
def vgg_load_pretrained_imagenet_weights(model, convert_state_dict):
"""Load pretrained weights
Args:
model: the generalized rcnnn module
"""
_, ext = os.path.splitext(cfg.TRAIN.IMAGENET_PRETRAINED_WEIGHTS)
if ext == '.pkl':
with open(cfg.TRAIN.IMAGENET_PRETRAINED_WEIGHTS, 'rb') as fp:
src_blobs = pickle.load(fp, encoding='latin1')
if 'blobs' in src_blobs:
src_blobs = src_blobs['blobs']
pretrianed_state_dict = src_blobs
else:
weights_file = os.path.join(cfg.ROOT_DIR, cfg.TRAIN.IMAGENET_PRETRAINED_WEIGHTS)
pretrianed_state_dict = convert_state_dict(torch.load(weights_file))
model.Conv_Body.load_state_dict(pretrianed_state_dict, strict=False)
if hasattr(model, 'Box_Head'):
model.Box_Head.load_state_dict(pretrianed_state_dict, strict=False) 示例4: load_pretrained_imagenet_weights
# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import ROOT_DIR [as 别名]
def load_pretrained_imagenet_weights(model):
"""Load pretrained weights
Args:
num_layers: 50 for res50 and so on.
model: the generalized rcnnn module
"""
_, ext = os.path.splitext(cfg.VGG.IMAGENET_PRETRAINED_WEIGHTS)
if ext == '.pkl':
with open(cfg.VGG.IMAGENET_PRETRAINED_WEIGHTS, 'rb') as fp:
src_blobs = pickle.load(fp, encoding='latin1')
if 'blobs' in src_blobs:
src_blobs = src_blobs['blobs']
pretrianed_state_dict = src_blobs
else:
weights_file = os.path.join(cfg.ROOT_DIR, cfg.VGG.IMAGENET_PRETRAINED_WEIGHTS)
pretrianed_state_dict = convert_state_dict(torch.load(weights_file))
model_state_dict = model.state_dict()
pattern = dwh.vgg_weights_name_pattern()
name_mapping, _ = model.detectron_weight_mapping
for k, v in name_mapping.items():
if isinstance(v, str): # maybe a str, None or True
if pattern.match(v):
pretrianed_key = k.split('.', 1)[-1]
if ext == '.pkl':
model_state_dict[k].copy_(torch.Tensor(pretrianed_state_dict[v]))
else:
model_state_dict[k].copy_(pretrianed_state_dict[pretrianed_key]) 示例5: load_pretrained_imagenet_weights
# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import ROOT_DIR [as 别名]
def load_pretrained_imagenet_weights(model):
"""Load pretrained weights
Args:
num_layers: 50 for res50 and so on.
model: the generalized rcnnn module
"""
_, ext = os.path.splitext(cfg.RESNETS.IMAGENET_PRETRAINED_WEIGHTS)
if ext == '.pkl':
with open(cfg.RESNETS.IMAGENET_PRETRAINED_WEIGHTS, 'rb') as fp:
src_blobs = pickle.load(fp, encoding='latin1')
if 'blobs' in src_blobs:
src_blobs = src_blobs['blobs']
pretrianed_state_dict = src_blobs
else:
weights_file = os.path.join(cfg.ROOT_DIR, cfg.RESNETS.IMAGENET_PRETRAINED_WEIGHTS)
pretrianed_state_dict = convert_state_dict(torch.load(weights_file))
# Convert batchnorm weights
for name, mod in model.named_modules():
if isinstance(mod, mynn.AffineChannel2d):
if cfg.FPN.FPN_ON:
pretrianed_name = name.split('.', 2)[-1]
else:
pretrianed_name = name.split('.', 1)[-1]
bn_mean = pretrianed_state_dict[pretrianed_name + '.running_mean']
bn_var = pretrianed_state_dict[pretrianed_name + '.running_var']
scale = pretrianed_state_dict[pretrianed_name + '.weight']
bias = pretrianed_state_dict[pretrianed_name + '.bias']
std = torch.sqrt(bn_var + 1e-5)
new_scale = scale / std
new_bias = bias - bn_mean * scale / std
pretrianed_state_dict[pretrianed_name + '.weight'] = new_scale
pretrianed_state_dict[pretrianed_name + '.bias'] = new_bias
model_state_dict = model.state_dict()
pattern = dwh.resnet_weights_name_pattern()
name_mapping, _ = model.detectron_weight_mapping
for k, v in name_mapping.items():
if isinstance(v, str): # maybe a str, None or True
if pattern.match(v):
if cfg.FPN.FPN_ON:
pretrianed_key = k.split('.', 2)[-1]
else:
pretrianed_key = k.split('.', 1)[-1]
if ext == '.pkl':
model_state_dict[k].copy_(torch.Tensor(pretrianed_state_dict[v]))
else:
model_state_dict[k].copy_(pretrianed_state_dict[pretrianed_key])