.. _sec_anchor:
アンカーボックス
================
物体検出アルゴリズムは通常、
入力画像内の多数の領域をサンプリングし、それらの領域に注目対象の物体が含まれているかを判定し、さらに領域の境界を調整して、物体の
*真のバウンディングボックス* をより正確に予測する。
モデルによって、領域のサンプリング方法は さまざまである。
ここではそのような方法の一つを紹介する。
これは、各ピクセルを中心として、異なるスケールとアスペクト比をもつ複数のバウンディングボックスを生成する。
これらのバウンディングボックスを *アンカーボックス* と呼ぶ。
:numref:`sec_ssd`
では、アンカーボックスに基づく物体検出モデルを設計する。
まず、出力をより簡潔にするために、 表示精度を少し変更しよう。
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
%matplotlib inline
from d2l import torch as d2l
import torch
torch.set_printoptions(2) # 表示精度を簡略化
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
%matplotlib inline
from d2l import mxnet as d2l
from mxnet import gluon, image, np, npx
np.set_printoptions(2) # 表示精度を簡略化
npx.set_np()
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
boxes = Y.reshape(h, w, 5, 4)
boxes[250, 250, 0, :]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
boxes = Y.reshape(h, w, 5, 4)
boxes[250, 250, 0, :]
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def multibox_prior(data, sizes, ratios):
"""Generate anchor boxes with different shapes centered on each pixel."""
in_height, in_width = data.shape[-2:]
device, num_sizes, num_ratios = data.device, len(sizes), len(ratios)
boxes_per_pixel = (num_sizes + num_ratios - 1)
size_tensor = d2l.tensor(sizes, device=device)
ratio_tensor = d2l.tensor(ratios, device=device)
# Offsets are required to move the anchor to the center of a pixel. Since
# a pixel has height=1 and width=1, we choose to offset our centers by 0.5
offset_h, offset_w = 0.5, 0.5
steps_h = 1.0 / in_height # Scaled steps in y axis
steps_w = 1.0 / in_width # Scaled steps in x axis
# Generate all center points for the anchor boxes
center_h = (torch.arange(in_height, device=device) + offset_h) * steps_h
center_w = (torch.arange(in_width, device=device) + offset_w) * steps_w
shift_y, shift_x = torch.meshgrid(center_h, center_w, indexing='ij')
shift_y, shift_x = shift_y.reshape(-1), shift_x.reshape(-1)
# Generate `boxes_per_pixel` number of heights and widths that are later
# used to create anchor box corner coordinates (xmin, xmax, ymin, ymax)
w = torch.cat((size_tensor * torch.sqrt(ratio_tensor[0]),
sizes[0] * torch.sqrt(ratio_tensor[1:])))\
* in_height / in_width # Handle rectangular inputs
h = torch.cat((size_tensor / torch.sqrt(ratio_tensor[0]),
sizes[0] / torch.sqrt(ratio_tensor[1:])))
# Divide by 2 to get half height and half width
anchor_manipulations = torch.stack((-w, -h, w, h)).T.repeat(
in_height * in_width, 1) / 2
# Each center point will have `boxes_per_pixel` number of anchor boxes, so
# generate a grid of all anchor box centers with `boxes_per_pixel` repeats
out_grid = torch.stack([shift_x, shift_y, shift_x, shift_y],
dim=1).repeat_interleave(boxes_per_pixel, dim=0)
output = out_grid + anchor_manipulations
return output.unsqueeze(0)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def multibox_prior(data, sizes, ratios):
"""Generate anchor boxes with different shapes centered on each pixel."""
in_height, in_width = data.shape[-2:]
device, num_sizes, num_ratios = data.ctx, len(sizes), len(ratios)
boxes_per_pixel = (num_sizes + num_ratios - 1)
size_tensor = d2l.tensor(sizes, ctx=device)
ratio_tensor = d2l.tensor(ratios, ctx=device)
# Offsets are required to move the anchor to the center of a pixel. Since
# a pixel has height=1 and width=1, we choose to offset our centers by 0.5
offset_h, offset_w = 0.5, 0.5
steps_h = 1.0 / in_height # Scaled steps in y-axis
steps_w = 1.0 / in_width # Scaled steps in x-axis
# Generate all center points for the anchor boxes
center_h = (d2l.arange(in_height, ctx=device) + offset_h) * steps_h
center_w = (d2l.arange(in_width, ctx=device) + offset_w) * steps_w
shift_x, shift_y = d2l.meshgrid(center_w, center_h)
shift_x, shift_y = shift_x.reshape(-1), shift_y.reshape(-1)
# Generate `boxes_per_pixel` number of heights and widths that are later
# used to create anchor box corner coordinates (xmin, xmax, ymin, ymax)
w = np.concatenate((size_tensor * np.sqrt(ratio_tensor[0]),
sizes[0] * np.sqrt(ratio_tensor[1:]))) \
* in_height / in_width # Handle rectangular inputs
h = np.concatenate((size_tensor / np.sqrt(ratio_tensor[0]),
sizes[0] / np.sqrt(ratio_tensor[1:])))
# Divide by 2 to get half height and half width
anchor_manipulations = np.tile(np.stack((-w, -h, w, h)).T,
(in_height * in_width, 1)) / 2
# Each center point will have `boxes_per_pixel` number of anchor boxes, so
# generate a grid of all anchor box centers with `boxes_per_pixel` repeats
out_grid = d2l.stack([shift_x, shift_y, shift_x, shift_y],
axis=1).repeat(boxes_per_pixel, axis=0)
output = out_grid + anchor_manipulations
return np.expand_dims(output, axis=0)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def show_bboxes(axes, bboxes, labels=None, colors=None):
"""Show bounding boxes."""
def make_list(obj, default_values=None):
if obj is None:
obj = default_values
elif not isinstance(obj, (list, tuple)):
obj = [obj]
return obj
labels = make_list(labels)
colors = make_list(colors, ['b', 'g', 'r', 'm', 'c'])
for i, bbox in enumerate(bboxes):
color = colors[i % len(colors)]
rect = d2l.bbox_to_rect(d2l.numpy(bbox), color)
axes.add_patch(rect)
if labels and len(labels) > i:
text_color = 'k' if color == 'w' else 'w'
axes.text(rect.xy[0], rect.xy[1], labels[i],
va='center', ha='center', fontsize=9, color=text_color,
bbox=dict(facecolor=color, lw=0))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def show_bboxes(axes, bboxes, labels=None, colors=None):
"""Show bounding boxes."""
def make_list(obj, default_values=None):
if obj is None:
obj = default_values
elif not isinstance(obj, (list, tuple)):
obj = [obj]
return obj
labels = make_list(labels)
colors = make_list(colors, ['b', 'g', 'r', 'm', 'c'])
for i, bbox in enumerate(bboxes):
color = colors[i % len(colors)]
rect = d2l.bbox_to_rect(d2l.numpy(bbox), color)
axes.add_patch(rect)
if labels and len(labels) > i:
text_color = 'k' if color == 'w' else 'w'
axes.text(rect.xy[0], rect.xy[1], labels[i],
va='center', ha='center', fontsize=9, color=text_color,
bbox=dict(facecolor=color, lw=0))
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
img = d2l.plt.imread('../img/catdog.jpg')
h, w = img.shape[:2]
print(h, w)
X = torch.rand(size=(1, 3, h, w)) # Construct input data
Y = multibox_prior(X, sizes=[0.75, 0.5, 0.25], ratios=[1, 2, 0.5])
Y.shape
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
561 728
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
torch.Size([1, 2042040, 4])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
img = image.imread('../img/catdog.jpg').asnumpy()
h, w = img.shape[:2]
print(h, w)
X = np.random.uniform(size=(1, 3, h, w)) # Construct input data
Y = multibox_prior(X, sizes=[0.75, 0.5, 0.25], ratios=[1, 2, 0.5])
Y.shape
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
561 728
[07:07:29] ../src/storage/storage.cc:196: Using Pooled (Naive) StorageManager for CPU
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
(1, 2042040, 4)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
d2l.set_figsize()
bbox_scale = d2l.tensor((w, h, w, h))
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, boxes[250, 250, :, :] * bbox_scale,
['s=0.75, r=1', 's=0.5, r=1', 's=0.25, r=1', 's=0.75, r=2',
's=0.75, r=0.5'])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
d2l.set_figsize()
bbox_scale = d2l.tensor((w, h, w, h))
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, boxes[250, 250, :, :] * bbox_scale,
['s=0.75, r=1', 's=0.5, r=1', 's=0.25, r=1', 's=0.75, r=2',
's=0.75, r=0.5'])
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
boxes = Y.reshape(h, w, 5, 4)
boxes[250, 250, 0, :]
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
tensor([0.06, 0.07, 0.63, 0.82])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
boxes = Y.reshape(h, w, 5, 4)
boxes[250, 250, 0, :]
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
array([0.06, 0.07, 0.63, 0.82])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def offset_boxes(anchors, assigned_bb, eps=1e-6):
"""Transform for anchor box offsets."""
c_anc = d2l.box_corner_to_center(anchors)
c_assigned_bb = d2l.box_corner_to_center(assigned_bb)
offset_xy = 10 * (c_assigned_bb[:, :2] - c_anc[:, :2]) / c_anc[:, 2:]
offset_wh = 5 * d2l.log(eps + c_assigned_bb[:, 2:] / c_anc[:, 2:])
offset = d2l.concat([offset_xy, offset_wh], axis=1)
return offset
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def offset_boxes(anchors, assigned_bb, eps=1e-6):
"""Transform for anchor box offsets."""
c_anc = d2l.box_corner_to_center(anchors)
c_assigned_bb = d2l.box_corner_to_center(assigned_bb)
offset_xy = 10 * (c_assigned_bb[:, :2] - c_anc[:, :2]) / c_anc[:, 2:]
offset_wh = 5 * d2l.log(eps + c_assigned_bb[:, 2:] / c_anc[:, 2:])
offset = d2l.concat([offset_xy, offset_wh], axis=1)
return offset
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def show_bboxes(axes, bboxes, labels=None, colors=None):
"""Show bounding boxes."""
def make_list(obj, default_values=None):
if obj is None:
obj = default_values
elif not isinstance(obj, (list, tuple)):
obj = [obj]
return obj
labels = make_list(labels)
colors = make_list(colors, ['b', 'g', 'r', 'm', 'c'])
for i, bbox in enumerate(bboxes):
color = colors[i % len(colors)]
rect = d2l.bbox_to_rect(d2l.numpy(bbox), color)
axes.add_patch(rect)
if labels and len(labels) > i:
text_color = 'k' if color == 'w' else 'w'
axes.text(rect.xy[0], rect.xy[1], labels[i],
va='center', ha='center', fontsize=9, color=text_color,
bbox=dict(facecolor=color, lw=0))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def show_bboxes(axes, bboxes, labels=None, colors=None):
"""Show bounding boxes."""
def make_list(obj, default_values=None):
if obj is None:
obj = default_values
elif not isinstance(obj, (list, tuple)):
obj = [obj]
return obj
labels = make_list(labels)
colors = make_list(colors, ['b', 'g', 'r', 'm', 'c'])
for i, bbox in enumerate(bboxes):
color = colors[i % len(colors)]
rect = d2l.bbox_to_rect(d2l.numpy(bbox), color)
axes.add_patch(rect)
if labels and len(labels) > i:
text_color = 'k' if color == 'w' else 'w'
axes.text(rect.xy[0], rect.xy[1], labels[i],
va='center', ha='center', fontsize=9, color=text_color,
bbox=dict(facecolor=color, lw=0))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
ground_truth = d2l.tensor([[0, 0.1, 0.08, 0.52, 0.92],
[1, 0.55, 0.2, 0.9, 0.88]])
anchors = d2l.tensor([[0, 0.1, 0.2, 0.3], [0.15, 0.2, 0.4, 0.4],
[0.63, 0.05, 0.88, 0.98], [0.66, 0.45, 0.8, 0.8],
[0.57, 0.3, 0.92, 0.9]])
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, ground_truth[:, 1:] * bbox_scale, ['dog', 'cat'], 'k')
show_bboxes(fig.axes, anchors * bbox_scale, ['0', '1', '2', '3', '4']);
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
ground_truth = d2l.tensor([[0, 0.1, 0.08, 0.52, 0.92],
[1, 0.55, 0.2, 0.9, 0.88]])
anchors = d2l.tensor([[0, 0.1, 0.2, 0.3], [0.15, 0.2, 0.4, 0.4],
[0.63, 0.05, 0.88, 0.98], [0.66, 0.45, 0.8, 0.8],
[0.57, 0.3, 0.92, 0.9]])
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, ground_truth[:, 1:] * bbox_scale, ['dog', 'cat'], 'k')
show_bboxes(fig.axes, anchors * bbox_scale, ['0', '1', '2', '3', '4']);
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
d2l.set_figsize()
bbox_scale = d2l.tensor((w, h, w, h))
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, boxes[250, 250, :, :] * bbox_scale,
['s=0.75, r=1', 's=0.5, r=1', 's=0.25, r=1', 's=0.75, r=2',
's=0.75, r=0.5'])
.. figure:: output_anchor_0ce4f6_78_0.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
d2l.set_figsize()
bbox_scale = d2l.tensor((w, h, w, h))
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, boxes[250, 250, :, :] * bbox_scale,
['s=0.75, r=1', 's=0.5, r=1', 's=0.25, r=1', 's=0.75, r=2',
's=0.75, r=0.5'])
.. figure:: output_anchor_0ce4f6_81_0.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
labels[2]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
labels[2]
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def box_iou(boxes1, boxes2):
"""Compute pairwise IoU across two lists of anchor or bounding boxes."""
box_area = lambda boxes: ((boxes[:, 2] - boxes[:, 0]) *
(boxes[:, 3] - boxes[:, 1]))
# Shape of `boxes1`, `boxes2`, `areas1`, `areas2`: (no. of boxes1, 4),
# (no. of boxes2, 4), (no. of boxes1,), (no. of boxes2,)
areas1 = box_area(boxes1)
areas2 = box_area(boxes2)
# Shape of `inter_upperlefts`, `inter_lowerrights`, `inters`: (no. of
# boxes1, no. of boxes2, 2)
inter_upperlefts = torch.max(boxes1[:, None, :2], boxes2[:, :2])
inter_lowerrights = torch.min(boxes1[:, None, 2:], boxes2[:, 2:])
inters = (inter_lowerrights - inter_upperlefts).clamp(min=0)
# Shape of `inter_areas` and `union_areas`: (no. of boxes1, no. of boxes2)
inter_areas = inters[:, :, 0] * inters[:, :, 1]
union_areas = areas1[:, None] + areas2 - inter_areas
return inter_areas / union_areas
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def box_iou(boxes1, boxes2):
"""Compute pairwise IoU across two lists of anchor or bounding boxes."""
box_area = lambda boxes: ((boxes[:, 2] - boxes[:, 0]) *
(boxes[:, 3] - boxes[:, 1]))
# Shape of `boxes1`, `boxes2`, `areas1`, `areas2`: (no. of boxes1, 4),
# (no. of boxes2, 4), (no. of boxes1,), (no. of boxes2,)
areas1 = box_area(boxes1)
areas2 = box_area(boxes2)
# Shape of `inter_upperlefts`, `inter_lowerrights`, `inters`: (no. of
# boxes1, no. of boxes2, 2)
inter_upperlefts = np.maximum(boxes1[:, None, :2], boxes2[:, :2])
inter_lowerrights = np.minimum(boxes1[:, None, 2:], boxes2[:, 2:])
inters = (inter_lowerrights - inter_upperlefts).clip(min=0)
# Shape of `inter_areas` and `union_areas`: (no. of boxes1, no. of boxes2)
inter_areas = inters[:, :, 0] * inters[:, :, 1]
union_areas = areas1[:, None] + areas2 - inter_areas
return inter_areas / union_areas
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
labels[1]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
labels[1]
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def assign_anchor_to_bbox(ground_truth, anchors, device, iou_threshold=0.5):
"""Assign closest ground-truth bounding boxes to anchor boxes."""
num_anchors, num_gt_boxes = anchors.shape[0], ground_truth.shape[0]
# Element x_ij in the i-th row and j-th column is the IoU of the anchor
# box i and the ground-truth bounding box j
jaccard = box_iou(anchors, ground_truth)
# Initialize the tensor to hold the assigned ground-truth bounding box for
# each anchor
anchors_bbox_map = torch.full((num_anchors,), -1, dtype=torch.long,
device=device)
# Assign ground-truth bounding boxes according to the threshold
max_ious, indices = torch.max(jaccard, dim=1)
anc_i = torch.nonzero(max_ious >= iou_threshold).reshape(-1)
box_j = indices[max_ious >= iou_threshold]
anchors_bbox_map[anc_i] = box_j
col_discard = torch.full((num_anchors,), -1)
row_discard = torch.full((num_gt_boxes,), -1)
for _ in range(num_gt_boxes):
max_idx = torch.argmax(jaccard) # Find the largest IoU
box_idx = (max_idx % num_gt_boxes).long()
anc_idx = (max_idx / num_gt_boxes).long()
anchors_bbox_map[anc_idx] = box_idx
jaccard[:, box_idx] = col_discard
jaccard[anc_idx, :] = row_discard
return anchors_bbox_map
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def assign_anchor_to_bbox(ground_truth, anchors, device, iou_threshold=0.5):
"""Assign closest ground-truth bounding boxes to anchor boxes."""
num_anchors, num_gt_boxes = anchors.shape[0], ground_truth.shape[0]
# Element x_ij in the i-th row and j-th column is the IoU of the anchor
# box i and the ground-truth bounding box j
jaccard = box_iou(anchors, ground_truth)
# Initialize the tensor to hold the assigned ground-truth bounding box for
# each anchor
anchors_bbox_map = np.full((num_anchors,), -1, dtype=np.int32, ctx=device)
# Assign ground-truth bounding boxes according to the threshold
max_ious, indices = np.max(jaccard, axis=1), np.argmax(jaccard, axis=1)
anc_i = np.nonzero(max_ious >= iou_threshold)[0]
box_j = indices[max_ious >= iou_threshold]
anchors_bbox_map[anc_i] = box_j
col_discard = np.full((num_anchors,), -1)
row_discard = np.full((num_gt_boxes,), -1)
for _ in range(num_gt_boxes):
max_idx = np.argmax(jaccard) # Find the largest IoU
box_idx = (max_idx % num_gt_boxes).astype('int32')
anc_idx = (max_idx / num_gt_boxes).astype('int32')
anchors_bbox_map[anc_idx] = box_idx
jaccard[:, box_idx] = col_discard
jaccard[anc_idx, :] = row_discard
return anchors_bbox_map
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
labels[0]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
labels[0]
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def offset_boxes(anchors, assigned_bb, eps=1e-6):
"""Transform for anchor box offsets."""
c_anc = d2l.box_corner_to_center(anchors)
c_assigned_bb = d2l.box_corner_to_center(assigned_bb)
offset_xy = 10 * (c_assigned_bb[:, :2] - c_anc[:, :2]) / c_anc[:, 2:]
offset_wh = 5 * d2l.log(eps + c_assigned_bb[:, 2:] / c_anc[:, 2:])
offset = d2l.concat([offset_xy, offset_wh], axis=1)
return offset
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def offset_boxes(anchors, assigned_bb, eps=1e-6):
"""Transform for anchor box offsets."""
c_anc = d2l.box_corner_to_center(anchors)
c_assigned_bb = d2l.box_corner_to_center(assigned_bb)
offset_xy = 10 * (c_assigned_bb[:, :2] - c_anc[:, :2]) / c_anc[:, 2:]
offset_wh = 5 * d2l.log(eps + c_assigned_bb[:, 2:] / c_anc[:, 2:])
offset = d2l.concat([offset_xy, offset_wh], axis=1)
return offset
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def offset_inverse(anchors, offset_preds):
"""Predict bounding boxes based on anchor boxes with predicted offsets."""
anc = d2l.box_corner_to_center(anchors)
pred_bbox_xy = (offset_preds[:, :2] * anc[:, 2:] / 10) + anc[:, :2]
pred_bbox_wh = d2l.exp(offset_preds[:, 2:] / 5) * anc[:, 2:]
pred_bbox = d2l.concat((pred_bbox_xy, pred_bbox_wh), axis=1)
predicted_bbox = d2l.box_center_to_corner(pred_bbox)
return predicted_bbox
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def offset_inverse(anchors, offset_preds):
"""Predict bounding boxes based on anchor boxes with predicted offsets."""
anc = d2l.box_corner_to_center(anchors)
pred_bbox_xy = (offset_preds[:, :2] * anc[:, 2:] / 10) + anc[:, :2]
pred_bbox_wh = d2l.exp(offset_preds[:, 2:] / 5) * anc[:, 2:]
pred_bbox = d2l.concat((pred_bbox_xy, pred_bbox_wh), axis=1)
predicted_bbox = d2l.box_center_to_corner(pred_bbox)
return predicted_bbox
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def multibox_target(anchors, labels):
"""Label anchor boxes using ground-truth bounding boxes."""
batch_size, anchors = labels.shape[0], anchors.squeeze(0)
batch_offset, batch_mask, batch_class_labels = [], [], []
device, num_anchors = anchors.device, anchors.shape[0]
for i in range(batch_size):
label = labels[i, :, :]
anchors_bbox_map = assign_anchor_to_bbox(
label[:, 1:], anchors, device)
bbox_mask = ((anchors_bbox_map >= 0).float().unsqueeze(-1)).repeat(
1, 4)
# Initialize class labels and assigned bounding box coordinates with
# zeros
class_labels = torch.zeros(num_anchors, dtype=torch.long,
device=device)
assigned_bb = torch.zeros((num_anchors, 4), dtype=torch.float32,
device=device)
# Label classes of anchor boxes using their assigned ground-truth
# bounding boxes. If an anchor box is not assigned any, we label its
# class as background (the value remains zero)
indices_true = torch.nonzero(anchors_bbox_map >= 0)
bb_idx = anchors_bbox_map[indices_true]
class_labels[indices_true] = label[bb_idx, 0].long() + 1
assigned_bb[indices_true] = label[bb_idx, 1:]
# Offset transformation
offset = offset_boxes(anchors, assigned_bb) * bbox_mask
batch_offset.append(offset.reshape(-1))
batch_mask.append(bbox_mask.reshape(-1))
batch_class_labels.append(class_labels)
bbox_offset = torch.stack(batch_offset)
bbox_mask = torch.stack(batch_mask)
class_labels = torch.stack(batch_class_labels)
return (bbox_offset, bbox_mask, class_labels)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def multibox_target(anchors, labels):
"""Label anchor boxes using ground-truth bounding boxes."""
batch_size, anchors = labels.shape[0], anchors.squeeze(0)
batch_offset, batch_mask, batch_class_labels = [], [], []
device, num_anchors = anchors.ctx, anchors.shape[0]
for i in range(batch_size):
label = labels[i, :, :]
anchors_bbox_map = assign_anchor_to_bbox(
label[:, 1:], anchors, device)
bbox_mask = np.tile((np.expand_dims((anchors_bbox_map >= 0),
axis=-1)), (1, 4)).astype('int32')
# Initialize class labels and assigned bounding box coordinates with
# zeros
class_labels = d2l.zeros(num_anchors, dtype=np.int32, ctx=device)
assigned_bb = d2l.zeros((num_anchors, 4), dtype=np.float32,
ctx=device)
# Label classes of anchor boxes using their assigned ground-truth
# bounding boxes. If an anchor box is not assigned any, we label its
# class as background (the value remains zero)
indices_true = np.nonzero(anchors_bbox_map >= 0)[0]
bb_idx = anchors_bbox_map[indices_true]
class_labels[indices_true] = label[bb_idx, 0].astype('int32') + 1
assigned_bb[indices_true] = label[bb_idx, 1:]
# Offset transformation
offset = offset_boxes(anchors, assigned_bb) * bbox_mask
batch_offset.append(offset.reshape(-1))
batch_mask.append(bbox_mask.reshape(-1))
batch_class_labels.append(class_labels)
bbox_offset = d2l.stack(batch_offset)
bbox_mask = d2l.stack(batch_mask)
class_labels = d2l.stack(batch_class_labels)
return (bbox_offset, bbox_mask, class_labels)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
anchors = d2l.tensor([[0.1, 0.08, 0.52, 0.92], [0.08, 0.2, 0.56, 0.95],
[0.15, 0.3, 0.62, 0.91], [0.55, 0.2, 0.9, 0.88]])
offset_preds = d2l.tensor([0] * d2l.size(anchors))
cls_probs = d2l.tensor([[0] * 4, # Predicted background likelihood
[0.9, 0.8, 0.7, 0.1], # Predicted dog likelihood
[0.1, 0.2, 0.3, 0.9]]) # Predicted cat likelihood
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
anchors = d2l.tensor([[0.1, 0.08, 0.52, 0.92], [0.08, 0.2, 0.56, 0.95],
[0.15, 0.3, 0.62, 0.91], [0.55, 0.2, 0.9, 0.88]])
offset_preds = d2l.tensor([0] * d2l.size(anchors))
cls_probs = d2l.tensor([[0] * 4, # Predicted background likelihood
[0.9, 0.8, 0.7, 0.1], # Predicted dog likelihood
[0.1, 0.2, 0.3, 0.9]]) # Predicted cat likelihood
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
ground_truth = d2l.tensor([[0, 0.1, 0.08, 0.52, 0.92],
[1, 0.55, 0.2, 0.9, 0.88]])
anchors = d2l.tensor([[0, 0.1, 0.2, 0.3], [0.15, 0.2, 0.4, 0.4],
[0.63, 0.05, 0.88, 0.98], [0.66, 0.45, 0.8, 0.8],
[0.57, 0.3, 0.92, 0.9]])
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, ground_truth[:, 1:] * bbox_scale, ['dog', 'cat'], 'k')
show_bboxes(fig.axes, anchors * bbox_scale, ['0', '1', '2', '3', '4']);
.. figure:: output_anchor_0ce4f6_153_0.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
ground_truth = d2l.tensor([[0, 0.1, 0.08, 0.52, 0.92],
[1, 0.55, 0.2, 0.9, 0.88]])
anchors = d2l.tensor([[0, 0.1, 0.2, 0.3], [0.15, 0.2, 0.4, 0.4],
[0.63, 0.05, 0.88, 0.98], [0.66, 0.45, 0.8, 0.8],
[0.57, 0.3, 0.92, 0.9]])
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, ground_truth[:, 1:] * bbox_scale, ['dog', 'cat'], 'k')
show_bboxes(fig.axes, anchors * bbox_scale, ['0', '1', '2', '3', '4']);
.. figure:: output_anchor_0ce4f6_156_0.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, anchors * bbox_scale,
['dog=0.9', 'dog=0.8', 'dog=0.7', 'cat=0.9'])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, anchors * bbox_scale,
['dog=0.9', 'dog=0.8', 'dog=0.7', 'cat=0.9'])
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
labels = multibox_target(anchors.unsqueeze(dim=0),
ground_truth.unsqueeze(dim=0))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
labels = multibox_target(np.expand_dims(anchors, axis=0),
np.expand_dims(ground_truth, axis=0))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
fig = d2l.plt.imshow(img)
for i in d2l.numpy(output[0]):
if i[0] == -1:
continue
label = ('dog=', 'cat=')[int(i[0])] + str(i[1])
show_bboxes(fig.axes, [d2l.tensor(i[2:]) * bbox_scale], label)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
fig = d2l.plt.imshow(img)
for i in d2l.numpy(output[0]):
if i[0] == -1:
continue
label = ('dog=', 'cat=')[int(i[0])] + str(i[1])
show_bboxes(fig.axes, [d2l.tensor(i[2:]) * bbox_scale], label)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def nms(boxes, scores, iou_threshold):
"""Sort confidence scores of predicted bounding boxes."""
B = torch.argsort(scores, dim=-1, descending=True)
keep = [] # Indices of predicted bounding boxes that will be kept
while B.numel() > 0:
i = B[0]
keep.append(i)
if B.numel() == 1: break
iou = box_iou(boxes[i, :].reshape(-1, 4),
boxes[B[1:], :].reshape(-1, 4)).reshape(-1)
inds = torch.nonzero(iou <= iou_threshold).reshape(-1)
B = B[inds + 1]
return d2l.tensor(keep, device=boxes.device)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def nms(boxes, scores, iou_threshold):
"""Sort confidence scores of predicted bounding boxes."""
B = scores.argsort()[::-1]
keep = [] # Indices of predicted bounding boxes that will be kept
while B.size > 0:
i = B[0]
keep.append(i)
if B.size == 1: break
iou = box_iou(boxes[i, :].reshape(-1, 4),
boxes[B[1:], :].reshape(-1, 4)).reshape(-1)
inds = np.nonzero(iou <= iou_threshold)[0]
B = B[inds + 1]
return np.array(keep, dtype=np.int32, ctx=boxes.ctx)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def multibox_detection(cls_probs, offset_preds, anchors, nms_threshold=0.5,
pos_threshold=0.009999999):
"""Predict bounding boxes using non-maximum suppression."""
device, batch_size = cls_probs.device, cls_probs.shape[0]
anchors = anchors.squeeze(0)
num_classes, num_anchors = cls_probs.shape[1], cls_probs.shape[2]
out = []
for i in range(batch_size):
cls_prob, offset_pred = cls_probs[i], offset_preds[i].reshape(-1, 4)
conf, class_id = torch.max(cls_prob[1:], 0)
predicted_bb = offset_inverse(anchors, offset_pred)
keep = nms(predicted_bb, conf, nms_threshold)
# Find all non-`keep` indices and set the class to background
all_idx = torch.arange(num_anchors, dtype=torch.long, device=device)
combined = torch.cat((keep, all_idx))
uniques, counts = combined.unique(return_counts=True)
non_keep = uniques[counts == 1]
all_id_sorted = torch.cat((keep, non_keep))
class_id[non_keep] = -1
class_id = class_id[all_id_sorted]
conf, predicted_bb = conf[all_id_sorted], predicted_bb[all_id_sorted]
# Here `pos_threshold` is a threshold for positive (non-background)
# predictions
below_min_idx = (conf < pos_threshold)
class_id[below_min_idx] = -1
conf[below_min_idx] = 1 - conf[below_min_idx]
pred_info = torch.cat((class_id.unsqueeze(1),
conf.unsqueeze(1),
predicted_bb), dim=1)
out.append(pred_info)
return d2l.stack(out)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def multibox_detection(cls_probs, offset_preds, anchors, nms_threshold=0.5,
pos_threshold=0.009999999):
"""Predict bounding boxes using non-maximum suppression."""
device, batch_size = cls_probs.ctx, cls_probs.shape[0]
anchors = np.squeeze(anchors, axis=0)
num_classes, num_anchors = cls_probs.shape[1], cls_probs.shape[2]
out = []
for i in range(batch_size):
cls_prob, offset_pred = cls_probs[i], offset_preds[i].reshape(-1, 4)
conf, class_id = np.max(cls_prob[1:], 0), np.argmax(cls_prob[1:], 0)
predicted_bb = offset_inverse(anchors, offset_pred)
keep = nms(predicted_bb, conf, nms_threshold)
# Find all non-`keep` indices and set the class to background
all_idx = np.arange(num_anchors, dtype=np.int32, ctx=device)
combined = d2l.concat((keep, all_idx))
unique, counts = np.unique(combined, return_counts=True)
non_keep = unique[counts == 1]
all_id_sorted = d2l.concat((keep, non_keep))
class_id[non_keep] = -1
class_id = class_id[all_id_sorted].astype('float32')
conf, predicted_bb = conf[all_id_sorted], predicted_bb[all_id_sorted]
# Here `pos_threshold` is a threshold for positive (non-background)
# predictions
below_min_idx = (conf < pos_threshold)
class_id[below_min_idx] = -1
conf[below_min_idx] = 1 - conf[below_min_idx]
pred_info = d2l.concat((np.expand_dims(class_id, axis=1),
np.expand_dims(conf, axis=1),
predicted_bb), axis=1)
out.append(pred_info)
return d2l.stack(out)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
output = multibox_detection(cls_probs.unsqueeze(dim=0),
offset_preds.unsqueeze(dim=0),
anchors.unsqueeze(dim=0),
nms_threshold=0.5)
output
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
tensor([[[ 0.00, 0.90, 0.10, 0.08, 0.52, 0.92],
[ 1.00, 0.90, 0.55, 0.20, 0.90, 0.88],
[-1.00, 0.80, 0.08, 0.20, 0.56, 0.95],
[-1.00, 0.70, 0.15, 0.30, 0.62, 0.91]]])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
output = multibox_detection(np.expand_dims(cls_probs, axis=0),
np.expand_dims(offset_preds, axis=0),
np.expand_dims(anchors, axis=0),
nms_threshold=0.5)
output
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
array([[[ 1. , 0.9 , 0.55, 0.2 , 0.9 , 0.88],
[ 0. , 0.9 , 0.1 , 0.08, 0.52, 0.92],
[-1. , 0.8 , 0.08, 0.2 , 0.56, 0.95],
[-1. , 0.7 , 0.15, 0.3 , 0.62, 0.91]]])
.. raw:: html
.. raw:: html