【目标检测】swin-transformer的模型推理
文章目录
- 1. 源代码
- 2. 相关文件
- 3. 代码
-
- 3.1 infer
- 3.2 mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco
1. 源代码
https://github.com/SwinTransformer/Swin-Transformer-Object-Detection
2. 相关文件
3. 代码
3.1 infer
from mmdet.apis import init_detector, inference_detector, show_result_pyplot
# import mmcv
import numpy as np
import cv2
import random
def InferResult(img, config_file, checkpoint_file, classes, model):
result = inference_detector(model, img)
if isinstance(result, tuple):
bbox_result, segm_result = result
if isinstance(segm_result, tuple):
segm_result = segm_result[0] # ms rcnn
else:
bbox_result, segm_result = result, None
bboxes = np.vstack(bbox_result)
labels = [
np.full(bbox.shape[0], i, dtype=np.int32)
for i, bbox in enumerate(bbox_result)
]
labels = np.concatenate(labels)
assert bboxes.shape[1] == 5
scores = bboxes[:, -1]
inds = scores > 0.3
bboxes = bboxes[inds, :]
labels = labels[inds]
# print(bboxes[:, :4])
# print(bboxes[:, -1:])
img, result_label = draw(img, bboxes, classes, labels)
return img, result_label
def plot_one_box(x, img, label=None, color=None, line_thickness=None):
# Plots one bounding box on image img
tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness
color = color or [random.randint(0, 255) for _ in range(3)]
c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
if label:
tf = max(tl - 1, 1) # font thickness
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled
cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)
# show the results
def draw(img, bboxes, classes, labels):
img = cv2.imread(img)
colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(classes))]
result_label = []
for i in range(bboxes.shape[0]):
xyxy = bboxes[i, :4]
conf = bboxes[i, -1:]
label = '%s %.2f' % (classes[labels[i]], conf)
label = '%s' % (classes[labels[i]])
result_label.append(label)
plot_one_box(xyxy, img, label=label, color=colors[0], line_thickness=1)
result_label = list(set(result_label))
cv2.imshow('test', img)
cv2.waitKey()
return img, result_label
if __name__ == '__main__':
img = '2.jpg'
# img = cv2.imread('./2.jpg')
config_file = 'mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco.py'
checkpoint_file = 'epoch_100.pth'
classes = ['The color of silica gel is abnormal', 'The color of silica gel is normal', 'The door is open', 'The door is close', 'breakage', 'dirt', 'rust', 'foreign object', 'oil leakage', 'animal', 'hat', 'person']
model = init_detector(config_file, checkpoint_file, device='cuda:0')
img, result_label = InferResult(img, config_file, checkpoint_file, classes, model)
3.2 mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco
model = dict(
type='MaskRCNN',
pretrained=None,
backbone=dict(
type='SwinTransformer',
embed_dim=96,
depths=[2, 2, 6, 2],
num_heads=[3, 6, 12, 24],
window_size=7,
mlp_ratio=4.0,
qkv_bias=True,
qk_scale=None,
drop_rate=0.0,
attn_drop_rate=0.0,
drop_path_rate=0.1,
ape=False,
patch_norm=True,
out_indices=(0, 1, 2, 3),
use_checkpoint=False),
neck=dict(
type='FPN',
in_channels=[96, 192, 384, 768],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=12,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=12,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
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=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=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,
match_low_quality=True,
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)),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='AutoAugment',
policies=[[{
'type':
'Resize',
'img_scale': [(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
'multiscale_mode':
'value',
'keep_ratio':
True
}],
[{
'type': 'Resize',
'img_scale': [(400, 1333), (500, 1333), (600, 1333)],
'multiscale_mode': 'value',
'keep_ratio': True
}, {
'type': 'RandomCrop',
'crop_type': 'absolute_range',
'crop_size': (384, 600),
'allow_negative_crop': True
}, {
'type':
'Resize',
'img_scale': [(480, 1333), (512, 1333), (544, 1333),
(576, 1333), (608, 1333), (640, 1333),
(672, 1333), (704, 1333), (736, 1333),
(768, 1333), (800, 1333)],
'multiscale_mode':
'value',
'override':
True,
'keep_ratio':
True
}]]),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=3,
workers_per_gpu=0,
train=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_train2017.json',
img_prefix='data/coco/train2017/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='AutoAugment',
policies=[[{
'type':
'Resize',
'img_scale': [(480, 1333), (512, 1333), (544, 1333),
(576, 1333), (608, 1333), (640, 1333),
(672, 1333), (704, 1333), (736, 1333),
(768, 1333), (800, 1333)],
'multiscale_mode':
'value',
'keep_ratio':
True
}],
[{
'type': 'Resize',
'img_scale': [(400, 1333), (500, 1333),
(600, 1333)],
'multiscale_mode': 'value',
'keep_ratio': True
}, {
'type': 'RandomCrop',
'crop_type': 'absolute_range',
'crop_size': (384, 600),
'allow_negative_crop': True
}, {
'type':
'Resize',
'img_scale': [(480, 1333), (512, 1333),
(544, 1333), (576, 1333),
(608, 1333), (640, 1333),
(672, 1333), (704, 1333),
(736, 1333), (768, 1333),
(800, 1333)],
'multiscale_mode':
'value',
'override':
True,
'keep_ratio':
True
}]]),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'])
]),
val=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_val2017.json',
img_prefix='data/coco/val2017/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_test2017.json',
img_prefix='data/coco/val2017/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(
type='AdamW',
lr=0.0001,
betas=(0.9, 0.999),
weight_decay=0.05,
paramwise_cfg=dict(
custom_keys=dict(
absolute_pos_embed=dict(decay_mult=0.0),
relative_position_bias_table=dict(decay_mult=0.0),
norm=dict(decay_mult=0.0))))
optimizer_config = dict(
grad_clip=None,
type='DistOptimizerHook',
update_interval=1,
coalesce=True,
bucket_size_mb=-1,
use_fp16=True)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[8, 11])
runner = dict(type='EpochBasedRunnerAmp', max_epochs=100)
checkpoint_config = dict(interval=2)
log_config = dict(interval=10, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = 'mask_rcnn_swin_12.pth'
resume_from = None
workflow = [('train', 1)]
fp16 = None
work_dir = './work_dirs\mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco'
gpu_ids = range(0, 1)