From 7ae953332a061d0f82528048a798e4e0db663761 Mon Sep 17 00:00:00 2001
From: nikhil_rayaprolu <nikhil684@gmail.com>
Date: Sun, 9 Feb 2020 15:31:56 +0530
Subject: [PATCH] changes for aicrowd
---
configs/htc_r50.py | 317 ++++++++++++++++++++++
mmdet/datasets/custom.py | 5 +-
mmdet/models/losses/cross_entropy_loss.py | 3 +
tools/analyze_logs.py | 29 +-
tools/dist_train.sh | 2 +-
5 files changed, 339 insertions(+), 17 deletions(-)
create mode 100644 configs/htc_r50.py
diff --git a/configs/htc_r50.py b/configs/htc_r50.py
new file mode 100644
index 0000000..f065170
--- /dev/null
+++ b/configs/htc_r50.py
@@ -0,0 +1,317 @@
+# model settings
+model = dict(
+ type='HybridTaskCascade',
+ num_stages=3,
+ pretrained='torchvision://resnet50',
+ interleaved=True,
+ mask_info_flow=True,
+ backbone=dict(
+ type='ResNet',
+ depth=50,
+ num_stages=4,
+ out_indices=(0, 1, 2, 3),
+ frozen_stages=1,
+ style='pytorch'),
+ neck=dict(
+ type='FPN',
+ in_channels=[256, 512, 1024, 2048],
+ out_channels=256,
+ num_outs=5),
+ rpn_head=dict(
+ type='RPNHead',
+ in_channels=256,
+ feat_channels=256,
+ anchor_scales=[8],
+ anchor_ratios=[0.5, 1.0, 2.0],
+ anchor_strides=[4, 8, 16, 32, 64],
+ target_means=[.0, .0, .0, .0],
+ target_stds=[1.0, 1.0, 1.0, 1.0],
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+ bbox_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ bbox_head=[
+ dict(
+ type='SharedFCBBoxHead',
+ num_fcs=2,
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=62,
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.1, 0.1, 0.2, 0.2],
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
+ dict(
+ type='SharedFCBBoxHead',
+ num_fcs=2,
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=62,
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.05, 0.05, 0.1, 0.1],
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
+ dict(
+ type='SharedFCBBoxHead',
+ num_fcs=2,
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=62,
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.033, 0.033, 0.067, 0.067],
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
+ ],
+ mask_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ mask_head=dict(
+ type='HTCMaskHead',
+ num_convs=4,
+ in_channels=256,
+ conv_out_channels=256,
+ num_classes=62,
+ loss_mask=dict(
+ type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)),
+ )
+# model training and testing settings
+train_cfg = dict(
+ rpn=dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False),
+ allowed_border=0,
+ pos_weight=-1,
+ debug=False),
+ rpn_proposal=dict(
+ nms_across_levels=False,
+ nms_pre=2000,
+ nms_post=2000,
+ max_num=2000,
+ nms_thr=0.7,
+ min_bbox_size=0),
+ rcnn=[
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.6,
+ neg_iou_thr=0.6,
+ min_pos_iou=0.6,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.7,
+ min_pos_iou=0.7,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False)
+ ],
+ stage_loss_weights=[1, 0.5, 0.25])
+test_cfg = dict(
+ rpn=dict(
+ nms_across_levels=False,
+ nms_pre=1000,
+ nms_post=1000,
+ max_num=1000,
+ nms_thr=0.7,
+ min_bbox_size=0),
+ rcnn=dict(
+ score_thr=0.001,
+ nms=dict(type='soft_nms', iou_thr=0.3),
+ max_per_img=10,
+ mask_thr_binary=0.5),
+ keep_all_stages=False)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = '/ssd_scratch/cvit/mmdetection/data/'
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+albu_train_transforms = [
+ dict(
+ type='ShiftScaleRotate',
+ shift_limit=0.0625,
+ scale_limit=0.0,
+ rotate_limit=0,
+ interpolation=1,
+ p=0.5),
+ dict(
+ type='RandomBrightnessContrast',
+ brightness_limit=[0.1, 0.3],
+ contrast_limit=[0.1, 0.3],
+ p=0.2),
+ dict(
+ type='OneOf',
+ transforms=[
+ dict(
+ type='RGBShift',
+ r_shift_limit=10,
+ g_shift_limit=10,
+ b_shift_limit=10,
+ p=1.0),
+ dict(
+ type='HueSaturationValue',
+ hue_shift_limit=20,
+ sat_shift_limit=30,
+ val_shift_limit=20,
+ p=1.0)
+ ],
+ p=0.1),
+ dict(type='JpegCompression', quality_lower=85, quality_upper=95, p=0.2),
+ dict(type='ChannelShuffle', p=0.1),
+ dict(
+ type='OneOf',
+ transforms=[
+ dict(type='Blur', blur_limit=3, p=1.0),
+ dict(type='MedianBlur', blur_limit=3, p=1.0)
+ ],
+ p=0.1),
+]
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='LoadAnnotations', with_bbox=True, with_mask=True),
+ dict(type='Resize', img_scale=(800, 800), keep_ratio=True),
+ dict(type='Pad', size_divisor=32),
+ dict(
+ type='Albu',
+ transforms=albu_train_transforms,
+ bbox_params=dict(
+ type='BboxParams',
+ format='pascal_voc',
+ label_fields=['gt_labels'],
+ min_visibility=0.0,
+ filter_lost_elements=True),
+ keymap={
+ 'img': 'image',
+ 'gt_masks': 'masks',
+ 'gt_bboxes': 'bboxes'
+ },
+ update_pad_shape=False,
+ skip_img_without_anno=True),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='DefaultFormatBundle'),
+ dict(
+ type='Collect',
+ keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'],
+ meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
+ 'pad_shape', 'scale_factor'))
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(
+ type='MultiScaleFlipAug',
+ img_scale=(800, 800),
+ flip=True,
+ transforms=[
+ dict(type='Resize', keep_ratio=True),
+ dict(type='RandomFlip', flip_ratio=0.5),
+ dict(type='Normalize', **img_norm_cfg),
+ dict(type='Pad', size_divisor=32),
+ dict(type='ImageToTensor', keys=['img']),
+ dict(type='Collect', keys=['img']),
+ ])
+]
+data = dict(
+ imgs_per_gpu=4,
+ workers_per_gpu=0,
+ train=dict(
+ type=dataset_type,
+ ann_file=data_root + 'train/annotations.json',
+ img_prefix=data_root + 'train/images',
+ pipeline=train_pipeline),
+ val=dict(
+ type=dataset_type,
+ ann_file=data_root + 'val/annotations.json',
+ img_prefix=data_root + 'val/images',
+ pipeline=test_pipeline),
+ test=dict(
+ type=dataset_type,
+ ann_file=data_root + 'val/annotations.json',
+ img_prefix=data_root + 'val/images',
+ pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+ policy='step',
+ warmup='linear',
+ warmup_iters=500,
+ warmup_ratio=1.0 / 3,
+ step=[17, 24])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+ interval=50,
+ hooks=[
+ dict(type='TextLoggerHook'),
+ # dict(type='TensorboardLoggerHook')
+ ])
+# yapf:enable
+# runtime settings
+total_epochs = 30
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/htc_r50_fpn'
+load_from = '/ssd_scratch/cvit/mmdetection/htc_r50_fpn_20e_20190408-c03b7015.pth'
+resume_from = None
+workflow = [('train', 1)]
\ No newline at end of file
diff --git a/mmdet/datasets/custom.py b/mmdet/datasets/custom.py
index 935b39d..5bdfeea 100644
--- a/mmdet/datasets/custom.py
+++ b/mmdet/datasets/custom.py
@@ -141,7 +141,10 @@ class CustomDataset(Dataset):
if self.proposals is not None:
results['proposals'] = self.proposals[idx]
self.pre_pipeline(results)
- return self.pipeline(results)
+ try:
+ return self.pipeline(results)
+ except:
+ return None
def prepare_test_img(self, idx):
img_info = self.img_infos[idx]
diff --git a/mmdet/models/losses/cross_entropy_loss.py b/mmdet/models/losses/cross_entropy_loss.py
index dd9d477..53c9da3 100644
--- a/mmdet/models/losses/cross_entropy_loss.py
+++ b/mmdet/models/losses/cross_entropy_loss.py
@@ -8,6 +8,9 @@ from .utils import weight_reduce_loss
def cross_entropy(pred, label, weight=None, reduction='mean', avg_factor=None):
# element-wise losses
+# print(pred.shape, label.shape)
+# torch.set_printoptions(profile="full")
+# print(label)
loss = F.cross_entropy(pred, label, reduction='none')
# apply weights and do the reduction
diff --git a/tools/analyze_logs.py b/tools/analyze_logs.py
index 2810c98..0d54e64 100644
--- a/tools/analyze_logs.py
+++ b/tools/analyze_logs.py
@@ -32,28 +32,27 @@ def cal_train_time(log_dicts, args):
def plot_curve(log_dicts, args):
- if args.backend is not None:
- plt.switch_backend(args.backend)
- sns.set_style(args.style)
+ if args['backend'] is not None:
+ plt.switch_backend(args['backend'])
# if legend is None, use {filename}_{key} as legend
- legend = args.legend
+ legend = args['legend']
if legend is None:
legend = []
- for json_log in args.json_logs:
- for metric in args.keys:
+ for json_log in args['json_logs']:
+ for metric in args['keys']:
legend.append('{}_{}'.format(json_log, metric))
- assert len(legend) == (len(args.json_logs) * len(args.keys))
- metrics = args.keys
+ assert len(legend) == (len(args['json_logs']) * len(args['keys']))
+ metrics = args['keys']
num_metrics = len(metrics)
for i, log_dict in enumerate(log_dicts):
epochs = list(log_dict.keys())
for j, metric in enumerate(metrics):
print('plot curve of {}, metric is {}'.format(
- args.json_logs[i], metric))
+ args['json_logs'][i], metric))
if metric not in log_dict[epochs[0]]:
raise KeyError('{} does not contain metric {}'.format(
- args.json_logs[i], metric))
+ args['json_logs'][i], metric))
if 'mAP' in metric:
xs = np.arange(1, max(epochs) + 1)
@@ -81,13 +80,13 @@ def plot_curve(log_dicts, args):
plt.plot(
xs, ys, label=legend[i * num_metrics + j], linewidth=0.5)
plt.legend()
- if args.title is not None:
- plt.title(args.title)
- if args.out is None:
+ if args['title'] is not None:
+ plt.title(args['title'])
+ if args['out'] is None:
plt.show()
else:
- print('save curve to: {}'.format(args.out))
- plt.savefig(args.out)
+ print('save curve to: {}'.format(args['out']))
+ plt.savefig(args['out'])
plt.cla()
diff --git a/tools/dist_train.sh b/tools/dist_train.sh
index 3b3b580..4e6911d 100755
--- a/tools/dist_train.sh
+++ b/tools/dist_train.sh
@@ -6,5 +6,5 @@ CONFIG=$1
GPUS=$2
PORT=${PORT:-29500}
-$PYTHON -m torch.distributed.launch --nproc_per_node=$GPUS --master_port=$PORT \
+$PYTHON -W ignore::UserWarning -m torch.distributed.launch --nproc_per_node=$GPUS --master_port=$PORT \
$(dirname "$0")/train.py $CONFIG --launcher pytorch ${@:3}
--
GitLab