def forward(self, batched_inputs):
"""
Args:
batched_inputs: a list, batched outputs of :class:`DatasetMapper` .
Each item in the list contains the inputs for one image.
For now, each item in the list is a dict that contains:
* image: Tensor, image in (C, H, W) format.
* instances (optional): groundtruth :class:`Instances`
* proposals (optional): :class:`Instances`, precomputed proposals.
Other information that's included in the original dicts, such as:
* "height", "width" (int): the output resolution of the model, used in inference.
See :meth:`postprocess` for details.
Returns:
list[dict]:
Each dict is the output for one input image.
The dict contains one key "instances" whose value is a :class:`Instances`.
The :class:`Instances` object has the following keys:
"pred_boxes", "pred_classes", "scores", "pred_masks", "pred_keypoints"
"""
if not self.training:
return self.inference(batched_inputs)
images = self.preprocess_image(batched_inputs)
if "instances" in batched_inputs[0]:
gt_instances = [x["instances"].to(self.device) for x in batched_inputs]
elif "targets" in batched_inputs[0]:
log_first_n(
logging.WARN, "'targets' in the model inputs is now renamed to 'instances'!", n=10
)
gt_instances = [x["targets"].to(self.device) for x in batched_inputs]
else:
gt_instances = None
features = self.backbone(images.tensor)
if self.proposal_generator:
proposals, proposal_losses = self.proposal_generator(images, features, gt_instances)
else:
assert "proposals" in batched_inputs[0]
proposals = [x["proposals"].to(self.device) for x in batched_inputs]
proposal_losses = {}
_, detector_losses = self.roi_heads(images, features, proposals, gt_instances)
if self.vis_period > 0:
storage = get_event_storage()
if storage.iter % self.vis_period == 0:
self.visualize_training(batched_inputs, proposals)
losses = {}
losses.update(detector_losses)
losses.update(proposal_losses)
return losses
def __getattr__(self, key):
if key in self._RENAMED:
log_first_n(
logging.WARNING,
"Metadata '{}' was renamed to '{}'!".format(key, self._RENAMED[key]),
n=10,
)
return getattr(self, self._RENAMED[key])
raise AttributeError(
"Attribute '{}' does not exist in the metadata of '{}'. Available keys are {}.".format(
key, self.name, str(self.__dict__.keys())
)
)
def forward(self, batched_inputs):
"""
Args:
Same as in :class:`GeneralizedRCNN.forward`
Returns:
list[dict]:
Each dict is the output for one input image.
The dict contains one key "proposals" whose value is a
:class:`Instances` with keys "proposal_boxes" and "objectness_logits".
"""
images = [x["image"].to(self.device) for x in batched_inputs]
images = [self.normalizer(x) for x in images]
images = ImageList.from_tensors(images,
self.backbone.size_divisibility)
features = self.backbone(images.tensor)
if "instances" in batched_inputs[0]:
gt_instances = [
x["instances"].to(self.device) for x in batched_inputs
]
elif "targets" in batched_inputs[0]:
log_first_n(
logging.WARN,
"'targets' in the model inputs is now renamed to 'instances'!",
n=10)
gt_instances = [
x["targets"].to(self.device) for x in batched_inputs
]
else:
gt_instances = None
proposals, proposal_losses = self.proposal_generator(
images, features, gt_instances)
# In training, the proposals are not useful at all but we generate them anyway.
# This makes RPN-only models about 5% slower.
if self.training:
return proposal_losses
processed_results = []
for results_per_image, input_per_image, image_size in zip(
proposals, batched_inputs, images.image_sizes):
height = input_per_image.get("height", image_size[0])
width = input_per_image.get("width", image_size[1])
r = detector_postprocess(results_per_image, height, width)
processed_results.append({"proposals": r})
return processed_results
def __setattr__(self, key, val):
if key in self._RENAMED:
log_first_n(
logging.WARNING,
"Metadata '{}' was renamed to '{}'!".format(key, self._RENAMED[key]),
n=10,
)
setattr(self, self._RENAMED[key], val)
# Ensure that metadata of the same name stays consistent
try:
oldval = getattr(self, key)
assert oldval == val, (
"Attribute '{}' in the metadata of '{}' cannot be set "
"to a different value!\n{} != {}".format(key, self.name, oldval, val)
)
except AttributeError:
super().__setattr__(key, val)
def print_instances_class_histogram(dataset_dicts, class_names):
"""
Args:
dataset_dicts (list[dict]): list of dataset dicts.
class_names (list[str]): list of class names (zero-indexed).
"""
num_classes = len(class_names)
hist_bins = np.arange(num_classes + 1)
histogram = np.zeros((num_classes, ), dtype=np.int)
for entry in dataset_dicts:
annos = entry["annotations"]
classes = [x["category_id"] for x in annos if not x.get("iscrowd", 0)]
histogram += np.histogram(classes, bins=hist_bins)[0]
N_COLS = min(6, len(class_names) * 2)
def short_name(x):
# make long class names shorter. useful for lvis
if len(x) > 13:
return x[:11] + ".."
return x
data = list(
itertools.chain(
*[[short_name(class_names[i]), int(v)]
for i, v in enumerate(histogram)]))
total_num_instances = sum(data[1::2])
data.extend([None] * (N_COLS - (len(data) % N_COLS)))
if num_classes > 1:
data.extend(["total", total_num_instances])
data = itertools.zip_longest(*[data[i::N_COLS] for i in range(N_COLS)])
table = tabulate(
data,
headers=["category", "#instances"] * (N_COLS // 2),
tablefmt="pipe",
numalign="left",
stralign="center",
)
log_first_n(
logging.INFO,
"Distribution of instances among all {} categories:\n".format(
num_classes) + colored(table, "cyan"),
key="message",
)
def forward(self, batched_inputs):
"""
Args:
batched_inputs: a list, batched outputs of :class:`DetectionTransform` .
Each item in the list contains the inputs for one image.
For now, each item in the list is a dict that contains:
image: Tensor, image in (C, H, W) format.
instances: Instances
Other information that's included in the original dicts, such as:
"height", "width" (int): the output resolution of the model, used in inference.
See :meth:`postprocess` for details.
Returns:
losses (dict[str: Tensor]): mapping from a named loss to a tensor
storing the loss. Used during training only.
"""
images = self.preprocess_image(batched_inputs)
if "instances" in batched_inputs[0]:
gt_instances = [
x["instances"].to(self.device) for x in batched_inputs
]
elif "targets" in batched_inputs[0]:
log_first_n(
logging.WARN,
"'targets' in the model inputs is now renamed to 'instances'!",
n=10)
gt_instances = [
x["targets"].to(self.device) for x in batched_inputs
]
else:
gt_instances = None
features = self.backbone(images.tensor)
features = [features[f] for f in self.in_features]
# apply the TensorMask head
pred_logits, pred_deltas, pred_masks = self.head(features)
# generate anchors based on features, is it image specific?
anchors, unit_lengths, indexes = self.anchor_generator(features)
if self.training:
# get ground truths for class labels and box targets, it will label each anchor
gt_class_info, gt_delta_info, gt_mask_info, num_fg = self.get_ground_truth(
anchors, unit_lengths, indexes, gt_instances)
# compute the loss
return self.losses(
gt_class_info,
gt_delta_info,
gt_mask_info,
num_fg,
pred_logits,
pred_deltas,
pred_masks,
)
else:
# do inference to get the output
results = self.inference(pred_logits, pred_deltas, pred_masks,
anchors, indexes, images)
processed_results = []
for results_im, input_im, image_size in zip(
results, batched_inputs, images.image_sizes):
height = input_im.get("height", image_size[0])
width = input_im.get("width", image_size[1])
# this is to do post-processing with the image size
result_box, result_mask = results_im
r = _postprocess(result_box, result_mask, height, width)
processed_results.append({"instances": r})
return processed_results
def forward(self, batched_inputs):
"""
Args:
batched_inputs: a list, batched outputs of :class:`DatasetMapper` .
Each item in the list contains the inputs for one image.
For now, each item in the list is a dict that contains:
* image: Tensor, image in (C, H, W) format.
* instances: Instances
Other information that's included in the original dicts, such as:
* "height", "width" (int): the output resolution of the model, used in inference.
See :meth:`postprocess` for details.
Returns:
dict[str: Tensor]:
mapping from a named loss to a tensor storing the loss. Used during training only.
"""
images = self.preprocess_image(batched_inputs)
if "instances" in batched_inputs[0]:
gt_instances = [
x["instances"].to(self.device) for x in batched_inputs
]
elif "targets" in batched_inputs[0]:
log_first_n(
logging.WARN,
"'targets' in the model inputs is now renamed to 'instances'!",
n=10)
gt_instances = [
x["targets"].to(self.device) for x in batched_inputs
]
else:
gt_instances = None
features = self.backbone(images.tensor)
features = [features[f] for f in self.in_features]
box_cls, box_delta = self.head(features)
anchors = self.anchor_generator(features)
if self.training:
gt_classes, gt_anchors_reg_deltas = self.get_ground_truth(
anchors, gt_instances)
losses = self.losses(gt_classes, gt_anchors_reg_deltas, box_cls,
box_delta)
if self.vis_period > 0:
storage = get_event_storage()
if storage.iter % self.vis_period == 0:
results = self.inference(box_cls, box_delta, anchors,
images.image_sizes)
self.visualize_training(batched_inputs, results)
return losses
else:
results = self.inference(box_cls, box_delta, anchors,
images.image_sizes)
processed_results = []
for results_per_image, input_per_image, image_size in zip(
results, batched_inputs, images.image_sizes):
height = input_per_image.get("height", image_size[0])
width = input_per_image.get("width", image_size[1])
r = detector_postprocess(results_per_image, height, width)
processed_results.append({"instances": r})
return processed_results