From 97d08556373c0bc98badf4f2b17a114d97a70124 Mon Sep 17 00:00:00 2001
From: Jiangmiao Pang <pangjiangmiao@gmail.com>
Date: Mon, 20 May 2019 21:10:48 +0800
Subject: [PATCH] Reformat use yapf 0.27.0 & Add yapf style file (#672)
* Reformat use yapf 0.27.0
* Add yapf style file
---
.style.yapf | 4 +++
...ascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py | 4 +--
.../cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py | 4 +--
.../dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py | 4 +--
.../faster_rcnn_mdconv_c3-c5_r50_fpn_1x.py | 4 +--
.../dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x.py | 4 +--
configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py | 4 +--
mmdet/apis/inference.py | 3 +-
mmdet/apis/train.py | 4 +--
mmdet/core/bbox/assign_sampling.py | 6 ++--
mmdet/core/evaluation/mean_ap.py | 4 +--
mmdet/core/post_processing/bbox_nms.py | 5 ++-
mmdet/datasets/extra_aug.py | 4 +--
mmdet/datasets/loader/__init__.py | 4 +--
mmdet/datasets/loader/build_loader.py | 22 ++++++-------
mmdet/datasets/loader/sampler.py | 4 +--
mmdet/datasets/transforms.py | 4 +--
mmdet/models/anchor_heads/anchor_head.py | 5 +--
mmdet/models/backbones/resnet.py | 7 +----
mmdet/models/bbox_heads/convfc_bbox_head.py | 8 ++---
mmdet/models/detectors/cascade_rcnn.py | 18 ++++++-----
mmdet/models/detectors/htc.py | 18 ++++++-----
mmdet/models/detectors/test_mixins.py | 4 +--
mmdet/models/mask_heads/fcn_mask_head.py | 14 ++++-----
.../models/mask_heads/fused_semantic_head.py | 5 +--
mmdet/models/registry.py | 5 +--
mmdet/models/utils/conv_module.py | 19 ++++++------
mmdet/models/utils/norm.py | 1 -
mmdet/ops/dcn/setup.py | 6 ++--
tools/analyze_logs.py | 4 +--
tools/test.py | 31 +++++++++----------
tools/train.py | 3 +-
32 files changed, 108 insertions(+), 128 deletions(-)
create mode 100644 .style.yapf
diff --git a/.style.yapf b/.style.yapf
new file mode 100644
index 0000000..286a3f1
--- /dev/null
+++ b/.style.yapf
@@ -0,0 +1,4 @@
+[style]
+BASED_ON_STYLE = pep8
+BLANK_LINE_BEFORE_NESTED_CLASS_OR_DEF = true
+SPLIT_BEFORE_EXPRESSION_AFTER_OPENING_PAREN = true
diff --git a/configs/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py b/configs/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
index afd3183..711231e 100644
--- a/configs/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/cascade_mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
@@ -11,9 +11,7 @@ model = dict(
frozen_stages=1,
style='pytorch',
dcn=dict(
- modulated=False,
- deformable_groups=1,
- fallback_on_stride=False),
+ modulated=False, deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
diff --git a/configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py b/configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py
index 19f281f..cc00d91 100644
--- a/configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/cascade_rcnn_dconv_c3-c5_r50_fpn_1x.py
@@ -11,9 +11,7 @@ model = dict(
frozen_stages=1,
style='pytorch',
dcn=dict(
- modulated=False,
- deformable_groups=1,
- fallback_on_stride=False),
+ modulated=False, deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
diff --git a/configs/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py b/configs/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py
index 5d24d81..5e47eae 100644
--- a/configs/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/faster_rcnn_dconv_c3-c5_r50_fpn_1x.py
@@ -10,9 +10,7 @@ model = dict(
frozen_stages=1,
style='pytorch',
dcn=dict(
- modulated=False,
- deformable_groups=1,
- fallback_on_stride=False),
+ modulated=False, deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
diff --git a/configs/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x.py b/configs/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x.py
index 10279ac..73dc579 100644
--- a/configs/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/faster_rcnn_mdconv_c3-c5_r50_fpn_1x.py
@@ -10,9 +10,7 @@ model = dict(
frozen_stages=1,
style='pytorch',
dcn=dict(
- modulated=True,
- deformable_groups=1,
- fallback_on_stride=False),
+ modulated=True, deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
diff --git a/configs/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x.py b/configs/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
index 3325943..8135f09 100644
--- a/configs/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
+++ b/configs/dcn/mask_rcnn_dconv_c3-c5_r50_fpn_1x.py
@@ -10,9 +10,7 @@ model = dict(
frozen_stages=1,
style='pytorch',
dcn=dict(
- modulated=False,
- deformable_groups=1,
- fallback_on_stride=False),
+ modulated=False, deformable_groups=1, fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
diff --git a/configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py b/configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py
index ef63583..396993f 100644
--- a/configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py
+++ b/configs/gn+ws/faster_rcnn_r50_fpn_gn_ws_1x.py
@@ -99,9 +99,7 @@ test_cfg = dict(
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
- score_thr=0.05,
- nms=dict(type='nms', iou_thr=0.5),
- max_per_img=100))
+ score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
diff --git a/mmdet/apis/inference.py b/mmdet/apis/inference.py
index d2f455e..222fc83 100644
--- a/mmdet/apis/inference.py
+++ b/mmdet/apis/inference.py
@@ -124,8 +124,7 @@ def show_result(img, result, class_names, score_thr=0.3, out_file=None):
segms = mmcv.concat_list(segm_result)
inds = np.where(bboxes[:, -1] > score_thr)[0]
for i in inds:
- color_mask = np.random.randint(
- 0, 256, (1, 3), dtype=np.uint8)
+ color_mask = np.random.randint(0, 256, (1, 3), dtype=np.uint8)
mask = maskUtils.decode(segms[i]).astype(np.bool)
img[mask] = img[mask] * 0.5 + color_mask * 0.5
# draw bounding boxes
diff --git a/mmdet/apis/train.py b/mmdet/apis/train.py
index 6732664..44ec2cc 100644
--- a/mmdet/apis/train.py
+++ b/mmdet/apis/train.py
@@ -91,8 +91,8 @@ def build_optimizer(model, optimizer_cfg):
paramwise_options = optimizer_cfg.pop('paramwise_options', None)
# if no paramwise option is specified, just use the global setting
if paramwise_options is None:
- return obj_from_dict(optimizer_cfg, torch.optim,
- dict(params=model.parameters()))
+ return obj_from_dict(
+ optimizer_cfg, torch.optim, dict(params=model.parameters()))
else:
assert isinstance(paramwise_options, dict)
# get base lr and weight decay
diff --git a/mmdet/core/bbox/assign_sampling.py b/mmdet/core/bbox/assign_sampling.py
index 70d9fdf..4267174 100644
--- a/mmdet/core/bbox/assign_sampling.py
+++ b/mmdet/core/bbox/assign_sampling.py
@@ -7,8 +7,7 @@ def build_assigner(cfg, **kwargs):
if isinstance(cfg, assigners.BaseAssigner):
return cfg
elif isinstance(cfg, dict):
- return mmcv.runner.obj_from_dict(
- cfg, assigners, default_args=kwargs)
+ return mmcv.runner.obj_from_dict(cfg, assigners, default_args=kwargs)
else:
raise TypeError('Invalid type {} for building a sampler'.format(
type(cfg)))
@@ -18,8 +17,7 @@ def build_sampler(cfg, **kwargs):
if isinstance(cfg, samplers.BaseSampler):
return cfg
elif isinstance(cfg, dict):
- return mmcv.runner.obj_from_dict(
- cfg, samplers, default_args=kwargs)
+ return mmcv.runner.obj_from_dict(cfg, samplers, default_args=kwargs)
else:
raise TypeError('Invalid type {} for building a sampler'.format(
type(cfg)))
diff --git a/mmdet/core/evaluation/mean_ap.py b/mmdet/core/evaluation/mean_ap.py
index d69eda7..8f0474a 100644
--- a/mmdet/core/evaluation/mean_ap.py
+++ b/mmdet/core/evaluation/mean_ap.py
@@ -261,8 +261,8 @@ def eval_map(det_results,
cls_dets, cls_gts, cls_gt_ignore = get_cls_results(
det_results, gt_bboxes, gt_labels, gt_ignore, i)
# calculate tp and fp for each image
- tpfp_func = (tpfp_imagenet
- if dataset in ['det', 'vid'] else tpfp_default)
+ tpfp_func = (
+ tpfp_imagenet if dataset in ['det', 'vid'] else tpfp_default)
tpfp = [
tpfp_func(cls_dets[j], cls_gts[j], cls_gt_ignore[j], iou_thr,
area_ranges) for j in range(len(cls_dets))
diff --git a/mmdet/core/post_processing/bbox_nms.py b/mmdet/core/post_processing/bbox_nms.py
index 01beecd..cb3fe21 100644
--- a/mmdet/core/post_processing/bbox_nms.py
+++ b/mmdet/core/post_processing/bbox_nms.py
@@ -45,9 +45,8 @@ def multiclass_nms(multi_bboxes,
_scores *= score_factors[cls_inds]
cls_dets = torch.cat([_bboxes, _scores[:, None]], dim=1)
cls_dets, _ = nms_op(cls_dets, **nms_cfg_)
- cls_labels = multi_bboxes.new_full((cls_dets.shape[0], ),
- i - 1,
- dtype=torch.long)
+ cls_labels = multi_bboxes.new_full(
+ (cls_dets.shape[0], ), i - 1, dtype=torch.long)
bboxes.append(cls_dets)
labels.append(cls_labels)
if bboxes:
diff --git a/mmdet/datasets/extra_aug.py b/mmdet/datasets/extra_aug.py
index c9e0734..a9f4f44 100644
--- a/mmdet/datasets/extra_aug.py
+++ b/mmdet/datasets/extra_aug.py
@@ -91,9 +91,7 @@ class Expand(object):
class RandomCrop(object):
- def __init__(self,
- min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
- min_crop_size=0.3):
+ def __init__(self, min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3):
# 1: return ori img
self.sample_mode = (1, *min_ious, 0)
self.min_crop_size = min_crop_size
diff --git a/mmdet/datasets/loader/__init__.py b/mmdet/datasets/loader/__init__.py
index a3d4fdd..1f23fa4 100644
--- a/mmdet/datasets/loader/__init__.py
+++ b/mmdet/datasets/loader/__init__.py
@@ -1,6 +1,4 @@
from .build_loader import build_dataloader
from .sampler import GroupSampler, DistributedGroupSampler
-__all__ = [
- 'GroupSampler', 'DistributedGroupSampler', 'build_dataloader'
-]
+__all__ = ['GroupSampler', 'DistributedGroupSampler', 'build_dataloader']
diff --git a/mmdet/datasets/loader/build_loader.py b/mmdet/datasets/loader/build_loader.py
index 248f8f8..8759b06 100644
--- a/mmdet/datasets/loader/build_loader.py
+++ b/mmdet/datasets/loader/build_loader.py
@@ -25,10 +25,8 @@ def build_dataloader(dataset,
sampler = DistributedGroupSampler(dataset, imgs_per_gpu,
world_size, rank)
else:
- sampler = DistributedSampler(dataset,
- world_size,
- rank,
- shuffle=False)
+ sampler = DistributedSampler(
+ dataset, world_size, rank, shuffle=False)
batch_size = imgs_per_gpu
num_workers = workers_per_gpu
else:
@@ -36,13 +34,13 @@ def build_dataloader(dataset,
batch_size = num_gpus * imgs_per_gpu
num_workers = num_gpus * workers_per_gpu
- data_loader = DataLoader(dataset,
- batch_size=batch_size,
- sampler=sampler,
- num_workers=num_workers,
- collate_fn=partial(collate,
- samples_per_gpu=imgs_per_gpu),
- pin_memory=False,
- **kwargs)
+ data_loader = DataLoader(
+ dataset,
+ batch_size=batch_size,
+ sampler=sampler,
+ num_workers=num_workers,
+ collate_fn=partial(collate, samples_per_gpu=imgs_per_gpu),
+ pin_memory=False,
+ **kwargs)
return data_loader
diff --git a/mmdet/datasets/loader/sampler.py b/mmdet/datasets/loader/sampler.py
index d2eef23..1e454b7 100644
--- a/mmdet/datasets/loader/sampler.py
+++ b/mmdet/datasets/loader/sampler.py
@@ -139,8 +139,8 @@ class DistributedGroupSampler(Sampler):
indices = [
indices[j] for i in list(
- torch.randperm(len(indices) // self.samples_per_gpu,
- generator=g))
+ torch.randperm(
+ len(indices) // self.samples_per_gpu, generator=g))
for j in range(i * self.samples_per_gpu, (i + 1) *
self.samples_per_gpu)
]
diff --git a/mmdet/datasets/transforms.py b/mmdet/datasets/transforms.py
index df36590..ff575db 100644
--- a/mmdet/datasets/transforms.py
+++ b/mmdet/datasets/transforms.py
@@ -34,8 +34,8 @@ class ImageTransform(object):
else:
img, w_scale, h_scale = mmcv.imresize(
img, scale, return_scale=True)
- scale_factor = np.array([w_scale, h_scale, w_scale, h_scale],
- dtype=np.float32)
+ scale_factor = np.array(
+ [w_scale, h_scale, w_scale, h_scale], dtype=np.float32)
img_shape = img.shape
img = mmcv.imnormalize(img, self.mean, self.std, self.to_rgb)
if flip:
diff --git a/mmdet/models/anchor_heads/anchor_head.py b/mmdet/models/anchor_heads/anchor_head.py
index 54096a4..881415b 100644
--- a/mmdet/models/anchor_heads/anchor_head.py
+++ b/mmdet/models/anchor_heads/anchor_head.py
@@ -196,8 +196,9 @@ class AnchorHead(nn.Module):
return None
(labels_list, label_weights_list, bbox_targets_list, bbox_weights_list,
num_total_pos, num_total_neg) = cls_reg_targets
- num_total_samples = (num_total_pos if self.cls_focal_loss else
- num_total_pos + num_total_neg)
+ num_total_samples = (
+ num_total_pos
+ if self.cls_focal_loss else num_total_pos + num_total_neg)
losses_cls, losses_reg = multi_apply(
self.loss_single,
cls_scores,
diff --git a/mmdet/models/backbones/resnet.py b/mmdet/models/backbones/resnet.py
index 564b565..d1db1dd 100644
--- a/mmdet/models/backbones/resnet.py
+++ b/mmdet/models/backbones/resnet.py
@@ -43,12 +43,7 @@ class BasicBlock(nn.Module):
bias=False)
self.add_module(self.norm1_name, norm1)
self.conv2 = build_conv_layer(
- conv_cfg,
- planes,
- planes,
- 3,
- padding=1,
- bias=False)
+ conv_cfg, planes, planes, 3, padding=1, bias=False)
self.add_module(self.norm2_name, norm2)
self.relu = nn.ReLU(inplace=True)
diff --git a/mmdet/models/bbox_heads/convfc_bbox_head.py b/mmdet/models/bbox_heads/convfc_bbox_head.py
index c0e7154..2ce687e 100644
--- a/mmdet/models/bbox_heads/convfc_bbox_head.py
+++ b/mmdet/models/bbox_heads/convfc_bbox_head.py
@@ -94,8 +94,8 @@ class ConvFCBBoxHead(BBoxHead):
branch_convs = nn.ModuleList()
if num_branch_convs > 0:
for i in range(num_branch_convs):
- conv_in_channels = (last_layer_dim
- if i == 0 else self.conv_out_channels)
+ conv_in_channels = (
+ last_layer_dim if i == 0 else self.conv_out_channels)
branch_convs.append(
ConvModule(
conv_in_channels,
@@ -114,8 +114,8 @@ class ConvFCBBoxHead(BBoxHead):
or self.num_shared_fcs == 0) and not self.with_avg_pool:
last_layer_dim *= (self.roi_feat_size * self.roi_feat_size)
for i in range(num_branch_fcs):
- fc_in_channels = (last_layer_dim
- if i == 0 else self.fc_out_channels)
+ fc_in_channels = (
+ last_layer_dim if i == 0 else self.fc_out_channels)
branch_fcs.append(
nn.Linear(fc_in_channels, self.fc_out_channels))
last_layer_dim = self.fc_out_channels
diff --git a/mmdet/models/detectors/cascade_rcnn.py b/mmdet/models/detectors/cascade_rcnn.py
index 6eb83e8..f0564c9 100644
--- a/mmdet/models/detectors/cascade_rcnn.py
+++ b/mmdet/models/detectors/cascade_rcnn.py
@@ -186,8 +186,8 @@ class CascadeRCNN(BaseDetector, RPNTestMixin):
gt_labels, rcnn_train_cfg)
loss_bbox = bbox_head.loss(cls_score, bbox_pred, *bbox_targets)
for name, value in loss_bbox.items():
- losses['s{}.{}'.format(
- i, name)] = (value * lw if 'loss' in name else value)
+ losses['s{}.{}'.format(i, name)] = (
+ value * lw if 'loss' in name else value)
# mask head forward and loss
if self.with_mask:
@@ -224,8 +224,8 @@ class CascadeRCNN(BaseDetector, RPNTestMixin):
[res.pos_gt_labels for res in sampling_results])
loss_mask = mask_head.loss(mask_pred, mask_targets, pos_labels)
for name, value in loss_mask.items():
- losses['s{}.{}'.format(
- i, name)] = (value * lw if 'loss' in name else value)
+ losses['s{}.{}'.format(i, name)] = (
+ value * lw if 'loss' in name else value)
# refine bboxes
if i < self.num_stages - 1:
@@ -286,8 +286,9 @@ class CascadeRCNN(BaseDetector, RPNTestMixin):
[] for _ in range(mask_head.num_classes - 1)
]
else:
- _bboxes = (det_bboxes[:, :4] * scale_factor
- if rescale else det_bboxes)
+ _bboxes = (
+ det_bboxes[:, :4] * scale_factor
+ if rescale else det_bboxes)
mask_rois = bbox2roi([_bboxes])
mask_feats = mask_roi_extractor(
x[:len(mask_roi_extractor.featmap_strides)],
@@ -324,8 +325,9 @@ class CascadeRCNN(BaseDetector, RPNTestMixin):
[] for _ in range(self.mask_head[-1].num_classes - 1)
]
else:
- _bboxes = (det_bboxes[:, :4] * scale_factor
- if rescale else det_bboxes)
+ _bboxes = (
+ det_bboxes[:, :4] * scale_factor
+ if rescale else det_bboxes)
mask_rois = bbox2roi([_bboxes])
aug_masks = []
for i in range(self.num_stages):
diff --git a/mmdet/models/detectors/htc.py b/mmdet/models/detectors/htc.py
index b7ac7ae..0384aa9 100644
--- a/mmdet/models/detectors/htc.py
+++ b/mmdet/models/detectors/htc.py
@@ -224,8 +224,8 @@ class HybridTaskCascade(CascadeRCNN):
roi_labels = bbox_targets[0]
for name, value in loss_bbox.items():
- losses['s{}.{}'.format(
- i, name)] = (value * lw if 'loss' in name else value)
+ losses['s{}.{}'.format(i, name)] = (
+ value * lw if 'loss' in name else value)
# mask head forward and loss
if self.with_mask:
@@ -253,8 +253,8 @@ class HybridTaskCascade(CascadeRCNN):
gt_masks, rcnn_train_cfg,
semantic_feat)
for name, value in loss_mask.items():
- losses['s{}.{}'.format(
- i, name)] = (value * lw if 'loss' in name else value)
+ losses['s{}.{}'.format(i, name)] = (
+ value * lw if 'loss' in name else value)
# refine bboxes (same as Cascade R-CNN)
if i < self.num_stages - 1 and not self.interleaved:
@@ -312,8 +312,9 @@ class HybridTaskCascade(CascadeRCNN):
[] for _ in range(mask_head.num_classes - 1)
]
else:
- _bboxes = (det_bboxes[:, :4] * scale_factor
- if rescale else det_bboxes)
+ _bboxes = (
+ det_bboxes[:, :4] * scale_factor
+ if rescale else det_bboxes)
mask_pred = self._mask_forward_test(
i, x, _bboxes, semantic_feat=semantic_feat)
segm_result = mask_head.get_seg_masks(
@@ -345,8 +346,9 @@ class HybridTaskCascade(CascadeRCNN):
[] for _ in range(self.mask_head[-1].num_classes - 1)
]
else:
- _bboxes = (det_bboxes[:, :4] * scale_factor
- if rescale else det_bboxes)
+ _bboxes = (
+ det_bboxes[:, :4] * scale_factor
+ if rescale else det_bboxes)
mask_rois = bbox2roi([_bboxes])
aug_masks = []
diff --git a/mmdet/models/detectors/test_mixins.py b/mmdet/models/detectors/test_mixins.py
index 709ee39..b64f2cd 100644
--- a/mmdet/models/detectors/test_mixins.py
+++ b/mmdet/models/detectors/test_mixins.py
@@ -105,8 +105,8 @@ class MaskTestMixin(object):
else:
# if det_bboxes is rescaled to the original image size, we need to
# rescale it back to the testing scale to obtain RoIs.
- _bboxes = (det_bboxes[:, :4] * scale_factor
- if rescale else det_bboxes)
+ _bboxes = (
+ det_bboxes[:, :4] * scale_factor if rescale else det_bboxes)
mask_rois = bbox2roi([_bboxes])
mask_feats = self.mask_roi_extractor(
x[:len(self.mask_roi_extractor.featmap_strides)], mask_rois)
diff --git a/mmdet/models/mask_heads/fcn_mask_head.py b/mmdet/models/mask_heads/fcn_mask_head.py
index 9274e7c..0a5054c 100644
--- a/mmdet/models/mask_heads/fcn_mask_head.py
+++ b/mmdet/models/mask_heads/fcn_mask_head.py
@@ -43,8 +43,8 @@ class FCNMaskHead(nn.Module):
self.convs = nn.ModuleList()
for i in range(self.num_convs):
- in_channels = (self.in_channels
- if i == 0 else self.conv_out_channels)
+ in_channels = (
+ self.in_channels if i == 0 else self.conv_out_channels)
padding = (self.conv_kernel_size - 1) // 2
self.convs.append(
ConvModule(
@@ -54,8 +54,8 @@ class FCNMaskHead(nn.Module):
padding=padding,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg))
- upsample_in_channels = (self.conv_out_channels
- if self.num_convs > 0 else in_channels)
+ upsample_in_channels = (
+ self.conv_out_channels if self.num_convs > 0 else in_channels)
if self.upsample_method is None:
self.upsample = None
elif self.upsample_method == 'deconv':
@@ -69,9 +69,9 @@ class FCNMaskHead(nn.Module):
scale_factor=self.upsample_ratio, mode=self.upsample_method)
out_channels = 1 if self.class_agnostic else self.num_classes
- logits_in_channel = (self.conv_out_channels
- if self.upsample_method == 'deconv' else
- upsample_in_channels)
+ logits_in_channel = (
+ self.conv_out_channels
+ if self.upsample_method == 'deconv' else upsample_in_channels)
self.conv_logits = nn.Conv2d(logits_in_channel, out_channels, 1)
self.relu = nn.ReLU(inplace=True)
self.debug_imgs = None
diff --git a/mmdet/models/mask_heads/fused_semantic_head.py b/mmdet/models/mask_heads/fused_semantic_head.py
index 12b8302..6107423 100644
--- a/mmdet/models/mask_heads/fused_semantic_head.py
+++ b/mmdet/models/mask_heads/fused_semantic_head.py
@@ -85,10 +85,7 @@ class FusedSemanticHead(nn.Module):
for i, feat in enumerate(feats):
if i != self.fusion_level:
feat = F.interpolate(
- feat,
- size=fused_size,
- mode='bilinear',
- align_corners=True)
+ feat, size=fused_size, mode='bilinear', align_corners=True)
x += self.lateral_convs[i](feat)
for i in range(self.num_convs):
diff --git a/mmdet/models/registry.py b/mmdet/models/registry.py
index fc14bc1..d5f8e67 100644
--- a/mmdet/models/registry.py
+++ b/mmdet/models/registry.py
@@ -22,8 +22,9 @@ class Registry(object):
module (:obj:`nn.Module`): Module to be registered.
"""
if not issubclass(module_class, nn.Module):
- raise TypeError('module must be a child of nn.Module, but got {}'.
- format(module_class))
+ raise TypeError(
+ 'module must be a child of nn.Module, but got {}'.format(
+ module_class))
module_name = module_class.__name__
if module_name in self._module_dict:
raise KeyError('{} is already registered in {}'.format(
diff --git a/mmdet/models/utils/conv_module.py b/mmdet/models/utils/conv_module.py
index 329b235..623d691 100644
--- a/mmdet/models/utils/conv_module.py
+++ b/mmdet/models/utils/conv_module.py
@@ -98,15 +98,16 @@ class ConvModule(nn.Module):
warnings.warn('ConvModule has norm and bias at the same time')
# build convolution layer
- self.conv = build_conv_layer(conv_cfg,
- in_channels,
- out_channels,
- kernel_size,
- stride=stride,
- padding=padding,
- dilation=dilation,
- groups=groups,
- bias=bias)
+ self.conv = build_conv_layer(
+ conv_cfg,
+ in_channels,
+ out_channels,
+ kernel_size,
+ stride=stride,
+ padding=padding,
+ dilation=dilation,
+ groups=groups,
+ bias=bias)
# export the attributes of self.conv to a higher level for convenience
self.in_channels = self.conv.in_channels
self.out_channels = self.conv.out_channels
diff --git a/mmdet/models/utils/norm.py b/mmdet/models/utils/norm.py
index a912a19..d5687cb 100644
--- a/mmdet/models/utils/norm.py
+++ b/mmdet/models/utils/norm.py
@@ -1,6 +1,5 @@
import torch.nn as nn
-
norm_cfg = {
# format: layer_type: (abbreviation, module)
'BN': ('bn', nn.BatchNorm2d),
diff --git a/mmdet/ops/dcn/setup.py b/mmdet/ops/dcn/setup.py
index 020d5ed..9638018 100644
--- a/mmdet/ops/dcn/setup.py
+++ b/mmdet/ops/dcn/setup.py
@@ -8,8 +8,8 @@ setup(
'src/deform_conv_cuda.cpp',
'src/deform_conv_cuda_kernel.cu',
]),
- CUDAExtension('deform_pool_cuda', [
- 'src/deform_pool_cuda.cpp', 'src/deform_pool_cuda_kernel.cu'
- ]),
+ CUDAExtension(
+ 'deform_pool_cuda',
+ ['src/deform_pool_cuda.cpp', 'src/deform_pool_cuda_kernel.cu']),
],
cmdclass={'build_ext': BuildExtension})
diff --git a/tools/analyze_logs.py b/tools/analyze_logs.py
index b56f3de..c9f603f 100644
--- a/tools/analyze_logs.py
+++ b/tools/analyze_logs.py
@@ -51,8 +51,8 @@ def plot_curve(log_dicts, args):
for j, metric in enumerate(metrics):
print('plot curve of {}, metric is {}'.format(
args.json_logs[i], metric))
- assert metric in log_dict[
- epochs[0]], '{} does not contain metric {}'.format(
+ assert metric in log_dict[epochs[
+ 0]], '{} does not contain metric {}'.format(
args.json_logs[i], metric)
if 'mAP' in metric:
diff --git a/tools/test.py b/tools/test.py
index dc94b6d..9719f45 100644
--- a/tools/test.py
+++ b/tools/test.py
@@ -63,15 +63,12 @@ def collect_results(result_part, size, tmpdir=None):
if tmpdir is None:
MAX_LEN = 512
# 32 is whitespace
- dir_tensor = torch.full((MAX_LEN, ),
- 32,
- dtype=torch.uint8,
- device='cuda')
+ dir_tensor = torch.full(
+ (MAX_LEN, ), 32, dtype=torch.uint8, device='cuda')
if rank == 0:
tmpdir = tempfile.mkdtemp()
- tmpdir = torch.tensor(bytearray(tmpdir.encode()),
- dtype=torch.uint8,
- device='cuda')
+ tmpdir = torch.tensor(
+ bytearray(tmpdir.encode()), dtype=torch.uint8, device='cuda')
dir_tensor[:len(tmpdir)] = tmpdir
dist.broadcast(dir_tensor, 0)
tmpdir = dir_tensor.cpu().numpy().tobytes().decode().rstrip()
@@ -113,10 +110,11 @@ def parse_args():
help='eval types')
parser.add_argument('--show', action='store_true', help='show results')
parser.add_argument('--tmpdir', help='tmp dir for writing some results')
- parser.add_argument('--launcher',
- choices=['none', 'pytorch', 'slurm', 'mpi'],
- default='none',
- help='job launcher')
+ parser.add_argument(
+ '--launcher',
+ choices=['none', 'pytorch', 'slurm', 'mpi'],
+ default='none',
+ help='job launcher')
parser.add_argument('--local_rank', type=int, default=0)
args = parser.parse_args()
return args
@@ -145,11 +143,12 @@ def main():
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
dataset = get_dataset(cfg.data.test)
- data_loader = build_dataloader(dataset,
- imgs_per_gpu=1,
- workers_per_gpu=cfg.data.workers_per_gpu,
- dist=distributed,
- shuffle=False)
+ data_loader = build_dataloader(
+ dataset,
+ imgs_per_gpu=1,
+ workers_per_gpu=cfg.data.workers_per_gpu,
+ dist=distributed,
+ shuffle=False)
# build the model and load checkpoint
model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
diff --git a/tools/train.py b/tools/train.py
index 97a253f..3e06d6f 100644
--- a/tools/train.py
+++ b/tools/train.py
@@ -77,7 +77,8 @@ def main():
# save mmdet version, config file content and class names in
# checkpoints as meta data
cfg.checkpoint_config.meta = dict(
- mmdet_version=__version__, config=cfg.text,
+ mmdet_version=__version__,
+ config=cfg.text,
classes=train_dataset.CLASSES)
# add an attribute for visualization convenience
model.CLASSES = train_dataset.CLASSES
--
GitLab