def main(args):
env_info = get_sys_env()
place = 'gpu' if env_info['Paddle compiled with cuda'] and env_info[
'GPUs used'] else 'cpu'
paddle.set_device(place)
if not args.cfg:
raise RuntimeError('No configuration file specified.')
cfg = Config(args.cfg)
# Only support for the DeepLabv3+ model
if args.data_format == 'NHWC':
if cfg.dic['model']['type'] != 'DeepLabV3P':
raise ValueError(
'The "NHWC" data format only support the DeepLabV3P model!')
cfg.dic['model']['data_format'] = args.data_format
cfg.dic['model']['backbone']['data_format'] = args.data_format
loss_len = len(cfg.dic['loss']['types'])
for i in range(loss_len):
cfg.dic['loss']['types'][i]['data_format'] = args.data_format
val_dataset = cfg.val_dataset
if val_dataset is None:
raise RuntimeError(
'The verification dataset is not specified in the configuration file.'
)
elif len(val_dataset) == 0:
raise ValueError(
'The length of val_dataset is 0. Please check if your dataset is valid'
)
msg = '\n---------------Config Information---------------\n'
msg += str(cfg)
msg += '------------------------------------------------'
logger.info(msg)
model = cfg.model
skip_quant(model)
quantizer = QAT(config=quant_config)
quant_model = quantizer.quantize(model)
logger.info('Quantize the model successfully')
if args.model_path:
utils.load_entire_model(quant_model, args.model_path)
logger.info('Loaded trained params of model successfully')
test_config = get_test_config(cfg, args)
config_check(cfg, val_dataset=val_dataset)
evaluate(quant_model,
val_dataset,
num_workers=args.num_workers,
**test_config)
def main(args):
env_info = get_sys_env()
place = 'gpu' if env_info['Paddle compiled with cuda'] and env_info[
'GPUs used'] else 'cpu'
paddle.set_device(place)
if not args.cfg:
raise RuntimeError('No configuration file specified.')
cfg = Config(args.cfg)
if cfg.dic["data"]["target"]["dataset"] == 'cityscapes':
val_dataset = CityDataset(split='val',
**cfg.dic["data"]["target"]["kwargs"])
else:
raise NotImplementedError()
if len(val_dataset) < 500:
print(len(val_dataset))
for i in range(len(val_dataset)):
print(val_dataset[i])
if val_dataset is None:
raise RuntimeError(
'The verification dataset is not specified in the configuration file.'
)
elif len(val_dataset) == 0:
raise ValueError(
'The length of val_dataset is 0. Please check if your dataset is valid'
)
msg = '\n---------------Config Information---------------\n'
msg += str(cfg)
msg += '------------------------------------------------'
logger.info(msg)
model = cfg.model
if args.model_path:
utils.load_entire_model(model, args.model_path)
logger.info('Loaded trained params of model successfully')
test_config = get_test_config(cfg, args)
val.evaluate(model,
val_dataset,
num_workers=args.num_workers,
**test_config)
def main(args):
env_info = get_sys_env()
place = 'gpu' if env_info['Paddle compiled with cuda'] and env_info[
'GPUs used'] else 'cpu'
paddle.set_device(place)
if not args.cfg:
raise RuntimeError('No configuration file specified.')
cfg = Config(args.cfg)
val_dataset = cfg.val_dataset
if val_dataset is None:
raise RuntimeError(
'The verification dataset is not specified in the configuration file.'
)
elif len(val_dataset) == 0:
raise ValueError(
'The length of val_dataset is 0. Please check if your dataset is valid'
)
msg = '\n---------------Config Information---------------\n'
msg += str(cfg)
msg += '------------------------------------------------'
logger.info(msg)
model = cfg.model
if args.model_path:
utils.load_entire_model(model, args.model_path)
logger.info('Loaded trained params of model successfully')
config_check(cfg, val_dataset=val_dataset)
evaluate(
model,
val_dataset,
aug_eval=args.aug_eval,
scales=args.scales,
flip_horizontal=args.flip_horizontal,
flip_vertical=args.flip_vertical,
is_slide=args.is_slide,
crop_size=args.crop_size,
stride=args.stride,
num_workers=args.num_workers,
)
def main(args):
os.environ['PADDLESEG_EXPORT_STAGE'] = 'True'
cfg = Config(args.cfg)
net = cfg.model
skip_quant(net)
quantizer = QAT(config=quant_config)
quant_net = quantizer.quantize(net)
logger.info('Quantize the model successfully')
if args.model_path:
utils.load_entire_model(quant_net, args.model_path)
logger.info('Loaded trained params of model successfully')
if not args.without_argmax or args.with_softmax:
new_net = SavedSegmentationNet(quant_net, args.without_argmax,
args.with_softmax)
else:
new_net = net
new_net.eval()
save_path = os.path.join(args.save_dir, 'model')
input_spec = [
paddle.static.InputSpec(shape=[None, 3, None, None], dtype='float32')
]
quantizer.save_quantized_model(new_net, save_path, input_spec=input_spec)
yml_file = os.path.join(args.save_dir, 'deploy.yaml')
with open(yml_file, 'w') as file:
transforms = cfg.export_config.get('transforms', [{
'type': 'Normalize'
}])
data = {
'Deploy': {
'transforms': transforms,
'model': 'model.pdmodel',
'params': 'model.pdiparams'
}
}
yaml.dump(data, file)
logger.info(f'Model is saved in {args.save_dir}.')
def init_weight(self):
if self.pretrained is not None:
utils.load_entire_model(self, self.pretrained)
def __init__(self,
img_size=384,
patch_size=4,
in_chans=3,
class_num=1000,
embed_dim=192,
depths=[2, 2, 18, 2],
num_heads=[6, 12, 24, 48],
window_size=12,
mlp_ratio=4.,
qkv_bias=True,
qk_scale=None,
drop_rate=0.,
attn_drop_rate=0.,
drop_path_rate=0.1,
norm_layer=nn.LayerNorm,
ape=False,
patch_norm=True,
use_checkpoint=False,
pretrained=False):
super(SwinTransformer_large_patch4_window12_384, self).__init__()
self.num_classes = num_classes = class_num
self.num_layers = len(depths)
self.embed_dim = embed_dim
self.ape = ape
self.patch_norm = patch_norm
self.num_features = int(embed_dim * 2**(self.num_layers - 1))
self.mlp_ratio = mlp_ratio
self.pretrained = pretrained
# split image into non-overlapping patches
self.patch_embed = PatchEmbed(
img_size=img_size,
patch_size=patch_size,
in_chans=in_chans,
embed_dim=embed_dim,
norm_layer=norm_layer if self.patch_norm else None)
num_patches = self.patch_embed.num_patches
patches_resolution = self.patch_embed.patches_resolution
self.patches_resolution = patches_resolution
# absolute position embedding
if self.ape:
self.absolute_pos_embed = self.create_parameter(
shape=(1, num_patches, embed_dim), default_initializer=zeros_)
self.add_parameter("absolute_pos_embed", self.absolute_pos_embed)
trunc_normal_(self.absolute_pos_embed)
self.pos_drop = nn.Dropout(p=drop_rate)
# stochastic depth
dpr = np.linspace(0, drop_path_rate,
sum(depths)).tolist() # stochastic depth decay rule
# build layers
self.layers = nn.LayerList()
for i_layer in range(self.num_layers):
layer = BasicLayer(
dim=int(embed_dim * 2**i_layer),
input_resolution=(patches_resolution[0] // (2**i_layer),
patches_resolution[1] // (2**i_layer)),
depth=depths[i_layer],
num_heads=num_heads[i_layer],
window_size=window_size,
mlp_ratio=self.mlp_ratio,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
drop=drop_rate,
attn_drop=attn_drop_rate,
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
norm_layer=norm_layer,
downsample=PatchMerging if
(i_layer < self.num_layers - 1) else None,
use_checkpoint=use_checkpoint)
self.layers.append(layer)
self.norm = norm_layer(self.num_features)
# self.avgpool = nn.AdaptiveAvgPool1D(1)
# self.head = nn.Linear(
# self.num_features,
# num_classes) if self.num_classes > 0 else nn.Identity()
self.apply(self._init_weights)
if pretrained:
utils.load_entire_model(
self,
'https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SwinTransformer_large_patch4_window12_384_22kto1k_pretrained.pdparams'
)
def __init__(self, layers=101, cardinality=32, width=16, pretrained=False):
super(ResNeXt101_32x16d_wsl, self).__init__()
self.pretrained = pretrained
self.layers = layers
self.cardinality = cardinality
self.width = width
self.scale = width // 8
self.depth = [3, 4, 23, 3]
self.base_width = cardinality * width
num_filters = [self.base_width * i
for i in [1, 2, 4, 8]] # [256, 512, 1024, 2048]
self._conv_stem = ConvBNLayer(
3, 64, 7, stride=2, act="relu", name="conv1")
self._pool = MaxPool2D(kernel_size=3, stride=2, padding=1)
self._conv1_0 = BottleneckBlock(
64,
num_filters[0],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer1.0")
self._conv1_1 = BottleneckBlock(
num_filters[0] // (width // 8),
num_filters[0],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer1.1")
self._conv1_2 = BottleneckBlock(
num_filters[0] // (width // 8),
num_filters[0],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer1.2")
self._conv2_0 = BottleneckBlock(
num_filters[0] // (width // 8),
num_filters[1],
stride=2,
cardinality=self.cardinality,
width=self.width,
name="layer2.0")
self._conv2_1 = BottleneckBlock(
num_filters[1] // (width // 8),
num_filters[1],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer2.1")
self._conv2_2 = BottleneckBlock(
num_filters[1] // (width // 8),
num_filters[1],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer2.2")
self._conv2_3 = BottleneckBlock(
num_filters[1] // (width // 8),
num_filters[1],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer2.3")
self._conv3_0 = BottleneckBlock(
num_filters[1] // (width // 8),
num_filters[2],
stride=2,
cardinality=self.cardinality,
width=self.width,
name="layer3.0")
self._conv3_1 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.1")
self._conv3_2 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.2")
self._conv3_3 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.3")
self._conv3_4 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.4")
self._conv3_5 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.5")
self._conv3_6 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.6")
self._conv3_7 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.7")
self._conv3_8 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.8")
self._conv3_9 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.9")
self._conv3_10 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.10")
self._conv3_11 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.11")
self._conv3_12 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.12")
self._conv3_13 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.13")
self._conv3_14 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.14")
self._conv3_15 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.15")
self._conv3_16 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.16")
self._conv3_17 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.17")
self._conv3_18 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.18")
self._conv3_19 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.19")
self._conv3_20 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.20")
self._conv3_21 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.21")
self._conv3_22 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[2],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer3.22")
self._conv4_0 = BottleneckBlock(
num_filters[2] // (width // 8),
num_filters[3],
stride=2,
cardinality=self.cardinality,
width=self.width,
name="layer4.0")
self._conv4_1 = BottleneckBlock(
num_filters[3] // (width // 8),
num_filters[3],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer4.1")
self._conv4_2 = BottleneckBlock(
num_filters[3] // (width // 8),
num_filters[3],
stride=1,
cardinality=self.cardinality,
width=self.width,
name="layer4.2")
if pretrained:
utils.load_entire_model(self, 'https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNeXt101_32x16_wsl_pretrained.pdparams')
def main(args):
if args.seed is not None:
paddle.seed(args.seed)
np.random.seed(args.seed)
random.seed(args.seed)
env_info = get_sys_env()
info = ['{}: {}'.format(k, v) for k, v in env_info.items()]
info = '\n'.join(['', format('Environment Information', '-^48s')] + info +
['-' * 48])
logger.info(info)
place = 'gpu' if env_info['Paddle compiled with cuda'] and env_info[
'GPUs used'] else 'cpu'
paddle.set_device(place)
if not args.cfg:
raise RuntimeError('No configuration file specified.')
cfg = Config(
args.cfg,
learning_rate=args.learning_rate,
iters=args.iters,
batch_size=args.batch_size)
train_dataset = cfg.train_dataset
if train_dataset is None:
raise RuntimeError(
'The training dataset is not specified in the configuration file.')
elif len(train_dataset) == 0:
raise ValueError(
'The length of train_dataset is 0. Please check if your dataset is valid'
)
val_dataset = cfg.val_dataset if args.do_eval else None
losses = cfg.loss
msg = '\n---------------Config Information---------------\n'
msg += str(cfg)
msg += '------------------------------------------------'
logger.info(msg)
config_check(cfg, train_dataset=train_dataset, val_dataset=val_dataset)
model = cfg.model
if args.model_path:
utils.load_entire_model(model, args.model_path)
logger.info('Loaded trained params of model successfully')
skip_quant(model)
quantizer = QAT(config=quant_config)
quant_model = quantizer.quantize(model)
logger.info('Quantize the model successfully')
train(
quant_model,
train_dataset,
val_dataset=val_dataset,
optimizer=cfg.optimizer,
save_dir=args.save_dir,
iters=cfg.iters,
batch_size=cfg.batch_size,
resume_model=None,
save_interval=args.save_interval,
log_iters=args.log_iters,
num_workers=args.num_workers,
use_vdl=args.use_vdl,
losses=losses,
keep_checkpoint_max=args.keep_checkpoint_max)
def __init__(self, layers=200, scales=4, width=26, pretrained=False):
super(Res2Net200_vd_26w_4s_ssld, self).__init__()
self.layers = layers
self.pretrained = pretrained
self.scales = scales
self.width = width
basic_width = self.width * self.scales
supported_layers = [50, 101, 152, 200]
assert layers in supported_layers, \
"supported layers are {} but input layer is {}".format(
supported_layers, layers)
if layers == 50:
depth = [3, 4, 6, 3]
elif layers == 101:
depth = [3, 4, 23, 3]
elif layers == 152:
depth = [3, 8, 36, 3]
elif layers == 200:
depth = [3, 12, 48, 3]
num_channels = [64, 256, 512, 1024]
num_channels2 = [256, 512, 1024, 2048]
num_filters = [basic_width * t for t in [1, 2, 4, 8]]
self.conv1_1 = ConvBNLayer(num_channels=3,
num_filters=32,
filter_size=3,
stride=2,
act='relu',
name="conv1_1")
self.conv1_2 = ConvBNLayer(num_channels=32,
num_filters=32,
filter_size=3,
stride=1,
act='relu',
name="conv1_2")
self.conv1_3 = ConvBNLayer(num_channels=32,
num_filters=64,
filter_size=3,
stride=1,
act='relu',
name="conv1_3")
self.pool2d_max = MaxPool2D(kernel_size=3, stride=2, padding=1)
self.block_list = []
for block in range(len(depth)):
shortcut = False
for i in range(depth[block]):
if layers in [101, 152, 200] and block == 2:
if i == 0:
conv_name = "res" + str(block + 2) + "a"
else:
conv_name = "res" + str(block + 2) + "b" + str(i)
else:
conv_name = "res" + str(block + 2) + chr(97 + i)
bottleneck_block = self.add_sublayer(
'bb_%d_%d' % (block, i),
BottleneckBlock(num_channels1=num_channels[block]
if i == 0 else num_channels2[block],
num_channels2=num_channels2[block],
num_filters=num_filters[block],
stride=2 if i == 0 and block != 0 else 1,
scales=scales,
shortcut=shortcut,
if_first=block == i == 0,
name=conv_name))
self.block_list.append(bottleneck_block)
shortcut = True
if pretrained:
utils.load_entire_model(
self,
'https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net200_vd_26w_4s_pretrained.pdparams'
)