Python maskrcnn_benchmark.modeling.roi_heads.mask_head.inference.Masker() Examples
The following are 30
code examples of maskrcnn_benchmark.modeling.roi_heads.mask_head.inference.Masker().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
maskrcnn_benchmark.modeling.roi_heads.mask_head.inference
, or try the search function
.
.
Example #1
| Source File: predictor.py From remote_sensing_object_detection_2019 with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #2
| Source File: predictor.py From retinamask with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
checkpointer = DetectronCheckpointer(cfg, self.model)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #3
| Source File: predictor.py From training with Apache License 2.0 | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #4
| Source File: predictor.py From FreeAnchor with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
checkpointer = DetectronCheckpointer(cfg, self.model)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.checkpointer = checkpointer
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
self.CATEGORIES = COCO_CATEGORIES if cfg.DATASETS.TEST[0][:4] == 'coco' else VOC_CATEGORIES
Example #5
| Source File: predictor.py From maskrcnn-benchmark with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
weight_loading = None
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
if weight_loading:
print('Loading weight from {}.'.format(weight_loading))
_ = checkpointer._load_model(torch.load(weight_loading))
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #6
| Source File: predictor.py From HRNet-MaskRCNN-Benchmark with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #7
| Source File: predictor.py From RRPN_pytorch with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #8
| Source File: predictor.py From sampling-free with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.color_list = colormap()
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = torch.tensor(confidence_threshold)
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #9
| Source File: predictor.py From RRPN_pytorch with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #10
| Source File: predictor.py From argoverse_baselinetracker with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #11
| Source File: predictor.py From remote_sensing_object_detection_2019 with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #12
| Source File: predictor.py From remote_sensing_object_detection_2019 with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #13
| Source File: predictor.py From RRPN_pytorch with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #14
| Source File: predictor.py From DetNAS with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
weight_loading = None
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
if weight_loading:
print('Loading weight from {}.'.format(weight_loading))
_ = checkpointer._load_model(torch.load(weight_loading))
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #15
| Source File: predictor.py From DF-Traffic-Sign-Identification with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #16
| Source File: predictor.py From R2CNN.pytorch with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #17
| Source File: predictor.py From Res2Net-maskrcnn with MIT License | 5 votes |
|
def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, self.model, save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2 ** 25 - 1, 2 ** 15 - 1, 2 ** 21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
Example #18
| Source File: coco_eval.py From TinyBenchmark with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
img_info = dataset.get_img_info(image_id)
image_width = img_info["width"]
image_height = img_info["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
Example #19
| Source File: coco_eval.py From DF-Traffic-Sign-Identification with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
img_info = dataset.get_img_info(image_id)
image_width = img_info["width"]
image_height = img_info["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
Example #20
| Source File: coco_eval.py From RRPN_pytorch with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
# TODO replace with get_img_info?
image_width = dataset.coco.imgs[original_id]["width"]
image_height = dataset.coco.imgs[original_id]["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
# inspired from Detectron
Example #21
| Source File: inference.py From maskscoring_rcnn with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset, maskiou_on):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
# TODO replace with get_img_info?
image_width = dataset.coco.imgs[original_id]["width"]
image_height = dataset.coco.imgs[original_id]["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
if maskiou_on:
scores = prediction.get_field("mask_scores").tolist()
else:
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
# inspired from Detectron
Example #22
| Source File: coco_eval.py From NAS-FCOS with BSD 2-Clause "Simplified" License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
img_info = dataset.get_img_info(image_id)
image_width = img_info["width"]
image_height = img_info["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
# inspired from Detectron
Example #23
| Source File: coco_eval.py From Res2Net-maskrcnn with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
img_info = dataset.get_img_info(image_id)
image_width = img_info["width"]
image_height = img_info["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
Example #24
| Source File: coco_eval.py From training with Apache License 2.0 | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
img_info = dataset.get_img_info(image_id)
image_width = img_info["width"]
image_height = img_info["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
Example #25
| Source File: inference.py From retinamask with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
# TODO replace with get_img_info?
image_width = dataset.coco.imgs[original_id]["width"]
image_height = dataset.coco.imgs[original_id]["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
masks = masker(masks, prediction)
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
# inspired from Detectron
Example #26
| Source File: inference.py From FreeAnchor with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
# TODO replace with get_img_info?
image_width = dataset.coco.imgs[original_id]["width"]
image_height = dataset.coco.imgs[original_id]["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
masks = masker(masks, prediction)
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
# inspired from Detectron
Example #27
| Source File: coco_eval.py From maskrcnn-benchmark with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
img_info = dataset.get_img_info(image_id)
image_width = img_info["width"]
image_height = img_info["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
Example #28
| Source File: coco_eval.py From HRNet-MaskRCNN-Benchmark with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
# TODO replace with get_img_info?
image_width = dataset.coco.imgs[original_id]["width"]
image_height = dataset.coco.imgs[original_id]["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
# inspired from Detectron
Example #29
| Source File: coco_eval.py From sampling-free with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
img_info = dataset.get_img_info(image_id)
image_width = img_info["width"]
image_height = img_info["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
Example #30
| Source File: coco_eval.py From remote_sensing_object_detection_2019 with MIT License | 4 votes |
|
def prepare_for_coco_segmentation(predictions, dataset):
import pycocotools.mask as mask_util
import numpy as np
masker = Masker(threshold=0.5, padding=1)
# assert isinstance(dataset, COCODataset)
coco_results = []
for image_id, prediction in tqdm(enumerate(predictions)):
original_id = dataset.id_to_img_map[image_id]
if len(prediction) == 0:
continue
# TODO replace with get_img_info?
image_width = dataset.coco.imgs[original_id]["width"]
image_height = dataset.coco.imgs[original_id]["height"]
prediction = prediction.resize((image_width, image_height))
masks = prediction.get_field("mask")
# t = time.time()
# Masker is necessary only if masks haven't been already resized.
if list(masks.shape[-2:]) != [image_height, image_width]:
masks = masker(masks.expand(1, -1, -1, -1, -1), prediction)
masks = masks[0]
# logger.info('Time mask: {}'.format(time.time() - t))
# prediction = prediction.convert('xywh')
# boxes = prediction.bbox.tolist()
scores = prediction.get_field("scores").tolist()
labels = prediction.get_field("labels").tolist()
# rles = prediction.get_field('mask')
rles = [
mask_util.encode(np.array(mask[0, :, :, np.newaxis], order="F"))[0]
for mask in masks
]
for rle in rles:
rle["counts"] = rle["counts"].decode("utf-8")
mapped_labels = [dataset.contiguous_category_id_to_json_id[i] for i in labels]
coco_results.extend(
[
{
"image_id": original_id,
"category_id": mapped_labels[k],
"segmentation": rle,
"score": scores[k],
}
for k, rle in enumerate(rles)
]
)
return coco_results
# inspired from Detectron
