diff --git a/mmdet/core/anchor/anchor_generator.py b/mmdet/core/anchor/anchor_generator.py
index ec27c4c02c919af8103440966a69c723291ea427..cd227ad0665ce705a79a3a5328d2fbba2155b114 100644
--- a/mmdet/core/anchor/anchor_generator.py
+++ b/mmdet/core/anchor/anchor_generator.py
@@ -92,6 +92,7 @@ class AnchorGenerator(object):
valid_y[:valid_h] = 1
valid_xx, valid_yy = self._meshgrid(valid_x, valid_y)
valid = valid_xx & valid_yy
- valid = valid[:, None].expand(
- valid.size(0), self.num_base_anchors).contiguous().view(-1)
+ valid = valid[:,
+ None].expand(valid.size(0),
+ self.num_base_anchors).contiguous().view(-1)
return valid
diff --git a/mmdet/core/anchor/anchor_target.py b/mmdet/core/anchor/anchor_target.py
index bba372ffae5d6ffb43bdb21bd76eb3e3e2725f5a..daf43c45e545127e33ee29aeb1c8fea55647513c 100644
--- a/mmdet/core/anchor/anchor_target.py
+++ b/mmdet/core/anchor/anchor_target.py
@@ -159,7 +159,9 @@ def anchor_target_single(flat_anchors,
neg_inds)
-def anchor_inside_flags(flat_anchors, valid_flags, img_shape,
+def anchor_inside_flags(flat_anchors,
+ valid_flags,
+ img_shape,
allowed_border=0):
img_h, img_w = img_shape[:2]
if allowed_border >= 0:
diff --git a/mmdet/core/anchor/guided_anchor_target.py b/mmdet/core/anchor/guided_anchor_target.py
index 21abe5ec508722c13147c9b524fb86cd600a136e..bf43850b6d15689fae7d5a5d900cb9f1a7a61d37 100644
--- a/mmdet/core/anchor/guided_anchor_target.py
+++ b/mmdet/core/anchor/guided_anchor_target.py
@@ -94,12 +94,12 @@ def ga_loc_target(gt_bboxes_list,
# calculate positive (center) regions
ctr_x1, ctr_y1, ctr_x2, ctr_y2 = calc_region(
gt_, r1, featmap_sizes[lvl])
- all_loc_targets[lvl][img_id, 0, ctr_y1:ctr_y2 + 1, ctr_x1:ctr_x2 +
- 1] = 1
- all_loc_weights[lvl][img_id, 0, ignore_y1:ignore_y2 +
- 1, ignore_x1:ignore_x2 + 1] = 0
- all_loc_weights[lvl][img_id, 0, ctr_y1:ctr_y2 + 1, ctr_x1:ctr_x2 +
- 1] = 1
+ all_loc_targets[lvl][img_id, 0, ctr_y1:ctr_y2 + 1,
+ ctr_x1:ctr_x2 + 1] = 1
+ all_loc_weights[lvl][img_id, 0, ignore_y1:ignore_y2 + 1,
+ ignore_x1:ignore_x2 + 1] = 0
+ all_loc_weights[lvl][img_id, 0, ctr_y1:ctr_y2 + 1,
+ ctr_x1:ctr_x2 + 1] = 1
# calculate ignore map on nearby low level feature
if lvl > 0:
d_lvl = lvl - 1
@@ -107,8 +107,8 @@ def ga_loc_target(gt_bboxes_list,
gt_ = gt_bboxes[gt_id, :4] / anchor_strides[d_lvl]
ignore_x1, ignore_y1, ignore_x2, ignore_y2 = calc_region(
gt_, r2, featmap_sizes[d_lvl])
- all_ignore_map[d_lvl][img_id, 0, ignore_y1:ignore_y2 +
- 1, ignore_x1:ignore_x2 + 1] = 1
+ all_ignore_map[d_lvl][img_id, 0, ignore_y1:ignore_y2 + 1,
+ ignore_x1:ignore_x2 + 1] = 1
# calculate ignore map on nearby high level feature
if lvl < num_lvls - 1:
u_lvl = lvl + 1
@@ -116,8 +116,8 @@ def ga_loc_target(gt_bboxes_list,
gt_ = gt_bboxes[gt_id, :4] / anchor_strides[u_lvl]
ignore_x1, ignore_y1, ignore_x2, ignore_y2 = calc_region(
gt_, r2, featmap_sizes[u_lvl])
- all_ignore_map[u_lvl][img_id, 0, ignore_y1:ignore_y2 +
- 1, ignore_x1:ignore_x2 + 1] = 1
+ all_ignore_map[u_lvl][img_id, 0, ignore_y1:ignore_y2 + 1,
+ ignore_x1:ignore_x2 + 1] = 1
for lvl_id in range(num_lvls):
# ignore negative regions w.r.t. ignore map
all_loc_weights[lvl_id][(all_loc_weights[lvl_id] < 0)
diff --git a/mmdet/datasets/pipelines/transforms.py b/mmdet/datasets/pipelines/transforms.py
index e6d3b688d3d40873ceb68f88e5932272e10c8783..760b3b1d1b291435da6f679005701c897a2882b5 100644
--- a/mmdet/datasets/pipelines/transforms.py
+++ b/mmdet/datasets/pipelines/transforms.py
@@ -370,8 +370,8 @@ class RandomCrop(object):
if 'gt_masks' in results:
valid_gt_masks = []
for i in np.where(valid_inds)[0]:
- gt_mask = results['gt_masks'][i][crop_y1:crop_y2, crop_x1:
- crop_x2]
+ gt_mask = results['gt_masks'][i][crop_y1:crop_y2,
+ crop_x1:crop_x2]
valid_gt_masks.append(gt_mask)
results['gt_masks'] = valid_gt_masks
diff --git a/mmdet/models/anchor_heads/anchor_head.py b/mmdet/models/anchor_heads/anchor_head.py
index f4899f9f7926ab5bc992b322872ff35a08d1bc69..83944c88008fdc5a68e1ceda39b50bf4a08b81f6 100644
--- a/mmdet/models/anchor_heads/anchor_head.py
+++ b/mmdet/models/anchor_heads/anchor_head.py
@@ -206,7 +206,11 @@ class AnchorHead(nn.Module):
return dict(loss_cls=losses_cls, loss_bbox=losses_bbox)
@force_fp32(apply_to=('cls_scores', 'bbox_preds'))
- def get_bboxes(self, cls_scores, bbox_preds, img_metas, cfg,
+ def get_bboxes(self,
+ cls_scores,
+ bbox_preds,
+ img_metas,
+ cfg,
rescale=False):
"""
Transform network output for a batch into labeled boxes.
diff --git a/mmdet/models/anchor_heads/guided_anchor_head.py b/mmdet/models/anchor_heads/guided_anchor_head.py
index 9e9282509b6bd04a7061594ff8e2acf7f3bcca69..271a0dc74f38f7b132870bc3ed9b2aeef8dfddd8 100644
--- a/mmdet/models/anchor_heads/guided_anchor_head.py
+++ b/mmdet/models/anchor_heads/guided_anchor_head.py
@@ -94,31 +94,32 @@ class GuidedAnchorHead(AnchorHead):
"""
def __init__(
- self,
- num_classes,
- in_channels,
- feat_channels=256,
- octave_base_scale=8,
- scales_per_octave=3,
- octave_ratios=[0.5, 1.0, 2.0],
- anchor_strides=[4, 8, 16, 32, 64],
- anchor_base_sizes=None,
- anchoring_means=(.0, .0, .0, .0),
- anchoring_stds=(1.0, 1.0, 1.0, 1.0),
- target_means=(.0, .0, .0, .0),
- target_stds=(1.0, 1.0, 1.0, 1.0),
- deformable_groups=4,
- loc_filter_thr=0.01,
- loss_loc=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=1.0),
- loss_shape=dict(type='BoundedIoULoss', beta=0.2, loss_weight=1.0),
- loss_cls=dict(
- type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)):
+ self,
+ num_classes,
+ in_channels,
+ feat_channels=256,
+ octave_base_scale=8,
+ scales_per_octave=3,
+ octave_ratios=[0.5, 1.0, 2.0],
+ anchor_strides=[4, 8, 16, 32, 64],
+ anchor_base_sizes=None,
+ anchoring_means=(.0, .0, .0, .0),
+ anchoring_stds=(1.0, 1.0, 1.0, 1.0),
+ target_means=(.0, .0, .0, .0),
+ target_stds=(1.0, 1.0, 1.0, 1.0),
+ deformable_groups=4,
+ loc_filter_thr=0.01,
+ loss_loc=dict(
+ type='FocalLoss',
+ use_sigmoid=True,
+ gamma=2.0,
+ alpha=0.25,
+ loss_weight=1.0),
+ loss_shape=dict(type='BoundedIoULoss', beta=0.2, loss_weight=1.0),
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
+ loss_weight=1.0)): # yapf: disable
super(AnchorHead, self).__init__()
self.in_channels = in_channels
self.num_classes = num_classes
@@ -209,7 +210,10 @@ class GuidedAnchorHead(AnchorHead):
def forward(self, feats):
return multi_apply(self.forward_single, feats)
- def get_sampled_approxs(self, featmap_sizes, img_metas, cfg,
+ def get_sampled_approxs(self,
+ featmap_sizes,
+ img_metas,
+ cfg,
device='cuda'):
"""Get sampled approxs and inside flags according to feature map sizes.
diff --git a/mmdet/models/detectors/mask_scoring_rcnn.py b/mmdet/models/detectors/mask_scoring_rcnn.py
index 9c16ab14adb5bb5dc32e0dbcf32db47dd28b79bc..f184c453ba2e03e0a9246fb0392ed621116f8b19 100644
--- a/mmdet/models/detectors/mask_scoring_rcnn.py
+++ b/mmdet/models/detectors/mask_scoring_rcnn.py
@@ -152,8 +152,8 @@ class MaskScoringRCNN(TwoStageDetector):
# mask iou head forward and loss
pos_mask_pred = mask_pred[range(mask_pred.size(0)), pos_labels]
mask_iou_pred = self.mask_iou_head(mask_feats, pos_mask_pred)
- pos_mask_iou_pred = mask_iou_pred[range(mask_iou_pred.size(0)
- ), pos_labels]
+ pos_mask_iou_pred = mask_iou_pred[range(mask_iou_pred.size(0)),
+ pos_labels]
mask_iou_targets = self.mask_iou_head.get_target(
sampling_results, gt_masks, pos_mask_pred, mask_targets,
self.train_cfg.rcnn)
@@ -193,8 +193,8 @@ class MaskScoringRCNN(TwoStageDetector):
rescale)
# get mask scores with mask iou head
mask_iou_pred = self.mask_iou_head(
- mask_feats,
- mask_pred[range(det_labels.size(0)), det_labels + 1])
+ mask_feats, mask_pred[range(det_labels.size(0)),
+ det_labels + 1])
mask_scores = self.mask_iou_head.get_mask_scores(
mask_iou_pred, det_bboxes, det_labels)
return segm_result, mask_scores
diff --git a/mmdet/models/mask_heads/maskiou_head.py b/mmdet/models/mask_heads/maskiou_head.py
index 3c923680313215acac2ce19458c5510b60427e45..d509f177f0fc457d043aac59b89e5e7010a13b9e 100644
--- a/mmdet/models/mask_heads/maskiou_head.py
+++ b/mmdet/models/mask_heads/maskiou_head.py
@@ -181,8 +181,8 @@ class MaskIoUHead(nn.Module):
mask_score = bbox_score * mask_iou
"""
inds = range(det_labels.size(0))
- mask_scores = mask_iou_pred[inds, det_labels +
- 1] * det_bboxes[inds, -1]
+ mask_scores = mask_iou_pred[inds, det_labels + 1] * det_bboxes[inds,
+ -1]
mask_scores = mask_scores.cpu().numpy()
det_labels = det_labels.cpu().numpy()
return [
diff --git a/mmdet/models/plugins/generalized_attention.py b/mmdet/models/plugins/generalized_attention.py
index 9517776fe7e9a10b66fbc4db762541dacc96183e..86e5b1e9df5c0df7df79a8a45836f08c4aec1db4 100644
--- a/mmdet/models/plugins/generalized_attention.py
+++ b/mmdet/models/plugins/generalized_attention.py
@@ -120,17 +120,16 @@ class GeneralizedAttention(nn.Module):
(max_len, max_len, max_len_kv, max_len_kv), dtype=np.int)
for iy in range(max_len):
for ix in range(max_len):
- local_constraint_map[iy, ix,
- max((iy - self.spatial_range) //
- self.kv_stride, 0):min(
- (iy + self.spatial_range +
- 1) // self.kv_stride +
- 1, max_len),
- max((ix - self.spatial_range) //
- self.kv_stride, 0):min(
- (ix + self.spatial_range +
- 1) // self.kv_stride +
- 1, max_len)] = 0
+ local_constraint_map[
+ iy, ix,
+ max((iy - self.spatial_range) //
+ self.kv_stride, 0):min((iy + self.spatial_range +
+ 1) // self.kv_stride +
+ 1, max_len),
+ max((ix - self.spatial_range) //
+ self.kv_stride, 0):min((ix + self.spatial_range +
+ 1) // self.kv_stride +
+ 1, max_len)] = 0
self.local_constraint_map = nn.Parameter(
torch.from_numpy(local_constraint_map).byte(),
diff --git a/tests/test_forward.py b/tests/test_forward.py
index 0bec83c73ca0c8fc632b17736572d76d7b3b3864..dede4ce005b25ab149c669c507290243d787751a 100644
--- a/tests/test_forward.py
+++ b/tests/test_forward.py
@@ -168,8 +168,8 @@ def test_retina_ghm_forward():
batch_results.append(result)
-def _demo_mm_inputs(
- input_shape=(1, 3, 300, 300), num_items=None, num_classes=10):
+def _demo_mm_inputs(input_shape=(1, 3, 300, 300),
+ num_items=None, num_classes=10): # yapf: disable
"""
Create a superset of inputs needed to run test or train batches.