Closed 1wang11lijian1 closed 4 weeks ago
Can you describe the multi-task training in more detail? What tasks are you training?
Can you share your config where the dataset(s) are defined?
Hello is this, I have written a PYQT5 training interface, for different target detection tasks training, training script is as follows:
# Train
# load config
cfg = Config.fromfile(param_config)
cfg.work_dir = param_save_dir
# build the runner from config
if 'runner_type' not in cfg:
# build the default runner
runner = Runner.from_cfg(cfg)
else:
# build customized runner from the registry
# if 'runner_type' is set in the cfg
runner = RUNNERS.build(cfg)
# start training
runner.train()
The profile here will vary depending on my different data sets, i.e. for different target detection tasks.
auto_scale_lr = dict(base_batch_size=64, enable=False)
backend_args = None
classes = ('Particle', )
data_preprocessor = dict(
bgr_to_rgb=True,
mean=[
0,
0,
0,
],
pad_size_divisor=32,
std=[
255.0,
255.0,
255.0,
],
type='DetDataPreprocessor')
data_root = 'D:/训练数据/'
dataset_type = 'CocoDataset'
default_hooks = dict(
checkpoint=dict(interval=10, type='CheckpointHook'),
logger=dict(interval=10, type='LoggerHook'),
param_scheduler=dict(type='ParamSchedulerHook'),
sampler_seed=dict(type='DistSamplerSeedHook'),
timer=dict(type='IterTimerHook'),
visualization=dict(type='DetVisualizationHook'))
default_scope = 'mmdet'
env_cfg = dict(
cudnn_benchmark=False,
dist_cfg=dict(backend='nccl'),
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
images_suffix = '.bmp'
load_from = None
log_level = 'INFO'
log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50)
model = dict(
backbone=dict(
depth=53,
init_cfg=dict(checkpoint='open-mmlab://darknet53', type='Pretrained'),
out_indices=(
3,
4,
5,
),
type='Darknet'),
bbox_head=dict(
anchor_generator=dict(
base_sizes=[
[
(
116,
90,
),
(
156,
198,
),
(
373,
326,
),
],
[
(
30,
61,
),
(
62,
45,
),
(
59,
119,
),
],
[
(
10,
13,
),
(
16,
30,
),
(
33,
23,
),
],
],
strides=[
32,
16,
8,
],
type='YOLOAnchorGenerator'),
bbox_coder=dict(type='YOLOBBoxCoder'),
featmap_strides=[
32,
16,
8,
],
in_channels=[
512,
256,
128,
],
loss_cls=dict(
loss_weight=1.0,
reduction='sum',
type='CrossEntropyLoss',
use_sigmoid=True),
loss_conf=dict(
loss_weight=1.0,
reduction='sum',
type='CrossEntropyLoss',
use_sigmoid=True),
loss_wh=dict(loss_weight=2.0, reduction='sum', type='MSELoss'),
loss_xy=dict(
loss_weight=2.0,
reduction='sum',
type='CrossEntropyLoss',
use_sigmoid=True),
num_classes=1,
out_channels=[
1024,
512,
256,
],
type='YOLOV3Head'),
data_preprocessor=dict(
bgr_to_rgb=True,
mean=[
0,
0,
0,
],
pad_size_divisor=32,
std=[
255.0,
255.0,
255.0,
],
type='DetDataPreprocessor'),
neck=dict(
in_channels=[
1024,
512,
256,
],
num_scales=3,
out_channels=[
512,
256,
128,
],
type='YOLOV3Neck'),
test_cfg=dict(
conf_thr=0.005,
max_per_img=100,
min_bbox_size=0,
nms=dict(iou_threshold=0.45, type='nms'),
nms_pre=1000,
score_thr=0.05),
train_cfg=dict(
assigner=dict(
min_pos_iou=0,
neg_iou_thr=0.5,
pos_iou_thr=0.5,
type='GridAssigner')),
type='YOLOV3')
optim_wrapper = dict(
clip_grad=dict(max_norm=35, norm_type=2),
optimizer=dict(lr=0.0001, momentum=0.9, type='SGD', weight_decay=0.0005),
type='OptimWrapper')
palette = [
[
128,
64,
128,
],
]
param_scheduler = [
dict(begin=0, by_epoch=False, end=2000, start_factor=0.1, type='LinearLR'),
dict(
by_epoch=True, gamma=0.1, milestones=[
218,
246,
], type='MultiStepLR'),
]
resume = False
resume_from = None
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
batch_size=1,
dataset=dict(
ann_file=
'E:\\Work\\Projects_test\\Keyboard_Object/data/data_coco/coco/annotations/instances_val2017.json',
backend_args=None,
data_prefix=dict(
img=
'E:\\Work\\Projects_test\\Keyboard_Object/data/data_coco/coco/images/'
),
data_root='data/coco/',
pipeline=[
dict(backend_args=None, type='LoadImageFromFile'),
dict(keep_ratio=True, scale=(
448,
448,
), type='Resize'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
meta_keys=(
'img_id',
'img_path',
'ori_shape',
'img_shape',
'scale_factor',
),
type='PackDetInputs'),
],
test_mode=True,
type='CocoDataset'),
drop_last=False,
num_workers=2,
persistent_workers=True,
sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
ann_file=
'E:\\Work\\Projects_test\\Keyboard_Object/data/data_coco/coco/annotations/instances_val2017.json',
backend_args=None,
metric='bbox',
type='CocoMetric')
test_pipeline = [
dict(backend_args=None, type='LoadImageFromFile'),
dict(keep_ratio=True, scale=(
448,
448,
), type='Resize'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
meta_keys=(
'img_id',
'img_path',
'ori_shape',
'img_shape',
'scale_factor',
),
type='PackDetInputs'),
]
train_cfg = dict(max_epochs=273, type='EpochBasedTrainLoop', val_interval=7)
train_dataloader = dict(
batch_sampler=dict(type='AspectRatioBatchSampler'),
batch_size=2,
dataset=dict(
ann_file=
'E:\\Work\\Projects_test\\Keyboard_Object/data/data_coco/coco/annotations/instances_train2017.json',
backend_args=None,
data_prefix=dict(
img=
'E:\\Work\\Projects_test\\Keyboard_Object/data/data_coco/coco/images/'
),
data_root='data/coco/',
filter_cfg=dict(filter_empty_gt=True, min_size=32),
pipeline=[
dict(backend_args=None, type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
mean=[
0,
0,
0,
],
ratio_range=(
1,
2,
),
to_rgb=True,
type='Expand'),
dict(
min_crop_size=0.3,
min_ious=(
0.4,
0.5,
0.6,
0.7,
0.8,
0.9,
),
type='MinIoURandomCrop'),
dict(
keep_ratio=True,
scale=[
(
448,
448,
),
(
448,
448,
),
],
type='RandomResize'),
dict(prob=0.5, type='RandomFlip'),
dict(type='PhotoMetricDistortion'),
dict(type='PackDetInputs'),
],
type='CocoDataset'),
num_workers=2,
persistent_workers=True,
sampler=dict(shuffle=True, type='DefaultSampler'))
train_pipeline = [
dict(backend_args=None, type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(mean=[
0,
0,
0,
], ratio_range=(
1,
2,
), to_rgb=True, type='Expand'),
dict(
min_crop_size=0.3,
min_ious=(
0.4,
0.5,
0.6,
0.7,
0.8,
0.9,
),
type='MinIoURandomCrop'),
dict(
keep_ratio=True,
scale=[
(
448,
448,
),
(
448,
448,
),
],
type='RandomResize'),
dict(prob=0.5, type='RandomFlip'),
dict(type='PhotoMetricDistortion'),
dict(type='PackDetInputs'),
]
val_cfg = dict(type='ValLoop')
val_dataloader = dict(
batch_size=1,
dataset=dict(
ann_file=
'E:\\Work\\Projects_test\\Keyboard_Object/data/data_coco/coco/annotations/instances_val2017.json',
backend_args=None,
data_prefix=dict(
img=
'E:\\Work\\Projects_test\\Keyboard_Object/data/data_coco/coco/images/'
),
data_root='data/coco/',
pipeline=[
dict(backend_args=None, type='LoadImageFromFile'),
dict(keep_ratio=True, scale=(
448,
448,
), type='Resize'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
meta_keys=(
'img_id',
'img_path',
'ori_shape',
'img_shape',
'scale_factor',
),
type='PackDetInputs'),
],
test_mode=True,
type='CocoDataset'),
drop_last=False,
num_workers=2,
persistent_workers=True,
sampler=dict(shuffle=False, type='DefaultSampler'))
val_evaluator = dict(
ann_file=
'E:\\Work\\Projects_test\\Keyboard_Object/data/data_coco/coco/annotations/instances_val2017.json',
backend_args=None,
metric='bbox',
type='CocoMetric')
vis_backends = [
dict(type='LocalVisBackend'),
]
visualizer = dict(
name='visualizer',
type='DetLocalVisualizer',
vis_backends=[
dict(type='LocalVisBackend'),
])
The first task starts without a problem, and the second task keeps getting errors like this: ValueError: need at least one array to concatenate. So I would like to ask you, how does this category information keep up to date during the interface multi-task training run? What I tried before didn't seem to work. Can you help me with this question?
Okay, it's settled.
modify main function in tools/train.py
:
from mmdet.datasets.coco import CocoDataset
CocoDataset.METAINFO = {'classes':('fire',),'palette':[(220, 20, 60), ]}
Hello developers, I have a scene here encountered a problem, I very much hope that you can provide solutions or solutions, I through the python interface training of different detection tasks, the first task can be started smoothly, the second task will always report errors, the error is as follows: ValueError: need at least one array to concatenate. So I looked for the reasons myself, probably because of these two things:
\mmdet\datasets\coco.py
did not update the class and palette information in time.\mmdet\evaluation\functional\class_names.py
coco_classes()
does not return updated class information.So I would like to ask you, how does this category information keep up to date during the interface multi-task training run? What I tried before didn't seem to work.
Here's what I tried to fix
\mmdet\datasets\coco.py
, the file Objectdataset_config.yaml changes category and color palette information every time you change a different task:Here's what I tried to fix
\mmdet\evaluation\functional\class_names.py
coco_classes()
: