def __init__(self, option, model_type, dataset, modules):
# call the initialization method of UnetBasedModel
UnetBasedModel.__init__(self, option, model_type, dataset, modules)
self._num_classes = dataset.num_classes
self._weight_classes = dataset.weight_classes
self._use_category = getattr(option, "use_category", False)
if self._use_category:
if not dataset.class_to_segments:
raise ValueError(
"The dataset needs to specify a class_to_segments property when using category information for segmentation"
)
self._num_categories = len(dataset.class_to_segments.keys())
log.info("Using category information for the predictions with %i categories", self._num_categories)
else:
self._num_categories = 0
# Last MLP
last_mlp_opt = option.mlp_cls
self.FC_layer = Seq()
last_mlp_opt.nn[0] += self._num_categories
for i in range(1, len(last_mlp_opt.nn)):
self.FC_layer.append(Conv1D(last_mlp_opt.nn[i - 1], last_mlp_opt.nn[i], bn=True, bias=False))
if last_mlp_opt.dropout:
self.FC_layer.append(torch.nn.Dropout(p=last_mlp_opt.dropout))
self.FC_layer.append(Conv1D(last_mlp_opt.nn[-1], self._num_classes, activation=None, bias=True, bn=False))
self.loss_names = ["loss_seg"]
self.visual_names = ["data_visual"]
def __init__(self, option, model_type, dataset, modules):
# call the initialization method of UnetBasedModel
UnetBasedModel.__init__(self, option, model_type, dataset, modules)
# Last MLP
self.mode = option.loss_mode
self.normalize_feature = option.normalize_feature
self.out_channels = option.out_channels
self.loss_names = ["loss_reg", "loss"]
self.metric_loss_module, self.miner_module = UnetBasedModel.get_metric_loss_and_miner(
getattr(option, "metric_loss", None),
getattr(option, "miner", None))
last_mlp_opt = option.mlp_cls
self.FC_layer = Seq()
last_mlp_opt.nn[0]
for i in range(1, len(last_mlp_opt.nn)):
self.FC_layer.append(
Conv1D(last_mlp_opt.nn[i - 1],
last_mlp_opt.nn[i],
bn=True,
bias=False))
if last_mlp_opt.dropout:
self.FC_layer.append(torch.nn.Dropout(p=last_mlp_opt.dropout))
self.FC_layer.append(
Conv1D(last_mlp_opt.nn[-1],
self.out_channels,
activation=None,
bias=True,
bn=False))
def set_last_mlp(self, last_mlp_opt):
self.FC_layer = Seq()
for i in range(1, len(last_mlp_opt.nn)):
self.FC_layer.append(
Conv1D(last_mlp_opt.nn[i - 1],
last_mlp_opt.nn[i],
bn=True,
bias=False))
def __init__(self, model_config, model_type, dataset, modules, *args, **kwargs):
super(RSConvBase, self).__init__(model_config, model_type, dataset, modules)
default_output_nc = kwargs.get("default_output_nc", 384)
self._has_mlp_head = False
self._output_nc = default_output_nc
if "output_nc" in kwargs:
self._has_mlp_head = True
self._output_nc = kwargs["output_nc"]
self.mlp = Seq()
self.mlp.append(Conv1D(default_output_nc, self._output_nc, bn=True, bias=False))
def __init__(self, option, model_type, dataset, modules):
BackboneBasedModel.__init__(self, option, model_type, dataset, modules)
# Last MLP
last_mlp_opt = option.mlp_cls
self._dim_output = last_mlp_opt.nn[-1]
self.FC_layer = Seq()
for i in range(1, len(last_mlp_opt.nn)):
self.FC_layer.append(Conv1D(last_mlp_opt.nn[i - 1], last_mlp_opt.nn[i], bn=True, bias=False))
self.loss_names = ["loss_patch_desc"]
def __init__(self, params):
super().__init__()
self._params = params
self._build_backbone()
self._model["classifier"] = Seq()
self._model["classifier"].append(
Conv1D(self._model_opt.output_nc,
self._params.data.number,
activation=None,
bias=True,
bn=False))
print(self._model)
def __init__(self, params, num_classes):
super(Net, self).__init__()
self._model = nn.ModuleDict()
self._model[
"backbone"], self._model_opt, self._backbone_name = self.build_backbone(
params)
self._model["classifier"] = Seq()
self._model["classifier"].append(
Conv1D(self._model_opt.output_nc,
num_classes,
activation=None,
bias=True,
bn=False))
def __init__(self, model_config, model_type, dataset, modules, *args, **kwargs):
super(BasePointnet2, self).__init__(model_config, model_type, dataset, modules)
try:
default_output_nc = extract_output_nc(model_config)
except:
default_output_nc = -1
log.warning("Could not resolve number of output channels")
self._has_mlp_head = False
self._output_nc = default_output_nc
if "output_nc" in kwargs:
self._has_mlp_head = True
self._output_nc = kwargs["output_nc"]
self.mlp = Seq()
self.mlp.append(Conv1D(default_output_nc, self._output_nc, bn=True, bias=False))
def __init__(self, option, model_type, dataset, modules):
# Pointnet++ is UnetBased model, call init method of unet model
UnetBasedModel.__init__(self, option, model_type, dataset, modules)
self._num_classes = dataset.num_classes
self._weight_classes = dataset.weight_classes
self._use_category = getattr(option, "use_category", False)
if self._use_category:
if not dataset.class_to_segments:
raise ValueError("Dataset does not specify needed "
"class_to_segments property")
self._num_categories = len(dataset.class_to_segments.keys())
log.info(f"Using category information for "
f"the predictions with ${self._num_categories}")
else:
self._num_categories = 0
log.info(f"Category information is not going to be used")
# ---------------------------------------------------
# Specification of last MLP based on
# mlp_cls opt in "mypointnet2" in "pointnet2.yaml"
last_mlp_opt = copy.deepcopy(option.mlp_cls)
# A sequential container. Modules will be added to
# it in the order they are passed in the constructor
# (Torch classic method)
self.FC_layer = Seq()
last_mlp_opt.nn[0] += self._num_categories
# Adding layers specified in pointnet2.yaml - mlp_cls
for i in range(1, len(last_mlp_opt.nn)):
self.FC_layer.append(
Conv1D(last_mlp_opt.nn[i - 1],
last_mlp_opt.nn[i],
bn=True,
bias=False))
# Specify dropout of last FC layer (mlp_cls)
if last_mlp_opt.dropout:
self.FC_layer.append(torch.nn.Dropout(p=last_mlp_opt.dropout))
self.FC_layer.append(
Conv1D(last_mlp_opt.nn[-1],
self._num_classes,
activation=None,
bias=True,
bn=False))
# -------------------------------------------------------------------
# Name specs.
self.loss_names = ["loss_seg"]
self.visual_names = ["data_visual"]
self.input = None
self.labels = None
self.batch_idx = None
self.category = None
self.loss_seg = None
self.data_visual = None