Python to_mask 예제들

예제 #1

파일: train_mask_rcnn_coco.py 프로젝트: zzzzlalala/gluon-cv

ax = fig.add_subplot(1, 1, 1)
ax = viz.plot_bbox(train_image,
                   bboxes,
                   labels=cids,
                   class_names=train_dataset.classes,
                   ax=ax)
plt.show()

##############################################################################
# To actually see the object segmentation, we need to convert polygons to masks
import numpy as np
from gluoncv.data.transforms import mask as tmask

width, height = train_image.shape[1], train_image.shape[0]
train_masks = np.stack(
    [tmask.to_mask(polys, (width, height)) for polys in train_segm])
plt_image = viz.plot_mask(train_image, train_masks)

##############################################################################
# Now plot the image with boxes, labels and masks
fig = plt.figure(figsize=(10, 10))
ax = fig.add_subplot(1, 1, 1)
ax = viz.plot_bbox(plt_image,
                   bboxes,
                   labels=cids,
                   class_names=train_dataset.classes,
                   ax=ax)
plt.show()

##############################################################################
# Data transforms, i.e. decoding and transformation, are identical to Faster R-CNN

예제 #2

파일: train_mask_rcnn_coco.py 프로젝트: xiayongtao/gluon-cv

##############################################################################
# Plot the image with boxes and labels:
from matplotlib import pyplot as plt
from gluoncv.utils import viz

fig = plt.figure(figsize=(10, 10))
ax = fig.add_subplot(1, 1, 1)
ax = viz.plot_bbox(train_image, bboxes, labels=cids, class_names=train_dataset.classes, ax=ax)
plt.show()

##############################################################################
# To actually see the object segmentation, we need to convert polygons to masks
import numpy as np
from gluoncv.data.transforms import mask as tmask
width, height = train_image.shape[1], train_image.shape[0]
train_masks = np.stack([tmask.to_mask(polys, (width, height)) for polys in train_segm])
plt_image = viz.plot_mask(train_image, train_masks)

##############################################################################
# Now plot the image with boxes, labels and masks
fig = plt.figure(figsize=(10, 10))
ax = fig.add_subplot(1, 1, 1)
ax = viz.plot_bbox(plt_image, bboxes, labels=cids, class_names=train_dataset.classes, ax=ax)
plt.show()

##############################################################################
# Data transforms, i.e. decoding and transformation, are identical to Faster R-CNN
# with the exception of segmentation polygons as an additional input.
# :py:class:`gluoncv.data.transforms.presets.rcnn.MaskRCNNDefaultTrainTransform`
# converts the segmentation polygons to binary segmentation mask.
# :py:class:`gluoncv.data.transforms.presets.rcnn.MaskRCNNDefaultValTransform`