OpenMMLab AI实战营 第七课笔记
OpenMMLab AI实战营 第七课笔记
import os
import numpy as np
from PIL import Image
import os.path as osp
from tqdm import tqdm
import mmcv
import mmengine
import matplotlib.pyplot as plt
%matplotlib inline
# 数据集图片和标注路径
data_root = 'data/koto/'
img_dir = 'imgs'
ann_dir = 'annos'
# 类别和对应的颜色
classes = ('bg', 'person')
palette = [[0, 0, 0],[255, 255, 255]]
# palette = [[128, 128, 128], [129, 127, 38], [120, 69, 125], [53, 125, 34],
# [0, 11, 123], [118, 20, 12], [122, 81, 25], [241, 134, 51]]
Image.open('data/koto/imgs/00001-125.jpg')
Image.open('data/koto/annos/00001-125.png')
import matplotlib.patches as mpatches
img = Image.open('data/koto/annos/00001-125.png')
plt.figure(figsize=(8, 6))
im = plt.imshow(np.array(img.convert('RGB')))
# 图例小块
patches = [mpatches.Patch(color=np.array(palette[i])/255., label=classes[i]) for i in range(2)]
# 图例
plt.legend(handles=patches, bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0., fontsize='large')
plt.show()
from mmseg.registry import DATASETS
from mmseg.datasets import BaseSegDataset
@DATASETS.register_module()
class StanfordBackgroundDataset(BaseSegDataset):
METAINFO = dict(classes = classes, palette = palette)
def __init__(self, **kwargs):
super().__init__(img_suffix='.jpg', seg_map_suffix='.png', **kwargs)
# 下载 config 文件 和 预训练模型checkpoint权重文件
!mim download mmsegmentation --config pspnet_r50-d8_4xb2-40k_cityscapes-512x1024 --dest .
processing pspnet_r50-d8_4xb2-40k_cityscapes-512x1024...
[32mpspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth exists in /home/linxu/Desktop/OpenMMLab-Space/mmsegmentation[0m
[32mSuccessfully dumped pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py to /home/linxu/Desktop/OpenMMLab-Space/mmsegmentation[0m
from mmengine import Config
cfg = Config.fromfile('configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py')
cfg.norm_cfg = dict(type='BN', requires_grad=True) # 只使用GPU时，BN取代SyncBN
cfg.crop_size = (256, 256)
cfg.model.data_preprocessor.size = cfg.crop_size
cfg.model.backbone.norm_cfg = cfg.norm_cfg
cfg.model.decode_head.norm_cfg = cfg.norm_cfg
cfg.model.auxiliary_head.norm_cfg = cfg.norm_cfg
# modify num classes of the model in decode/auxiliary head
cfg.model.decode_head.num_classes = 2
cfg.model.auxiliary_head.num_classes = 8
# 修改数据集的 type 和 root
cfg.dataset_type = 'StanfordBackgroundDataset'
cfg.data_root = data_root
cfg.train_dataloader.batch_size = 8
cfg.train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(type='RandomResize', scale=(320, 240), ratio_range=(0.5, 2.0), keep_ratio=True),
dict(type='RandomCrop', crop_size=cfg.crop_size, cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PackSegInputs')
]
cfg.test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(320, 240), keep_ratio=True),
# add loading annotation after ``Resize`` because ground truth
# does not need to do resize data transform
dict(type='LoadAnnotations'),
dict(type='PackSegInputs')
]
cfg.train_dataloader.dataset.type = cfg.dataset_type
cfg.train_dataloader.dataset.data_root = cfg.data_root
cfg.train_dataloader.dataset.data_prefix = dict(img_path=img_dir, seg_map_path=ann_dir)
cfg.train_dataloader.dataset.pipeline = cfg.train_pipeline
cfg.train_dataloader.dataset.ann_file = 'data/koto/train_list.txt'
cfg.val_dataloader.dataset.type = cfg.dataset_type
cfg.val_dataloader.dataset.data_root = cfg.data_root
cfg.val_dataloader.dataset.data_prefix = dict(img_path=img_dir, seg_map_path=ann_dir)
cfg.val_dataloader.dataset.pipeline = cfg.test_pipeline
cfg.val_dataloader.dataset.ann_file = 'data/koto/valid_list.txtt'
cfg.test_dataloader = cfg.val_dataloader
# 载入预训练模型权重
cfg.load_from = 'pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth'
# 工作目录
cfg.work_dir = './work_dirs/tutorial'
# 训练迭代次数
cfg.train_cfg.max_iters = 800
# 评估模型间隔
cfg.train_cfg.val_interval = 400
# 日志记录间隔
cfg.default_hooks.logger.interval = 100
# 模型权重保存间隔
cfg.default_hooks.checkpoint.interval = 400
# 随机数种子
cfg['randomness'] = dict(seed=0)
print(cfg.pretty_text)
norm_cfg = dict(type='BN', requires_grad=True)
data_preprocessor = dict(
type='SegDataPreProcessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_val=0,
seg_pad_val=255,
size=(512, 1024))
model = dict(
type='EncoderDecoder',
data_preprocessor=dict(
type='SegDataPreProcessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_val=0,
seg_pad_val=255,
size=(256, 256)),
pretrained='open-mmlab://resnet50_v1c',
backbone=dict(
type='ResNetV1c',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
dilations=(1, 1, 2, 4),
strides=(1, 2, 1, 1),
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=False,
style='pytorch',
contract_dilation=True),
decode_head=dict(
type='PSPHead',
in_channels=2048,
in_index=3,
channels=512,
pool_scales=(1, 2, 3, 6),
dropout_ratio=0.1,
num_classes=2,
norm_cfg=dict(type='BN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
auxiliary_head=dict(
type='FCNHead',
in_channels=1024,
in_index=2,
channels=256,
num_convs=1,
concat_input=False,
dropout_ratio=0.1,
num_classes=8,
norm_cfg=dict(type='BN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
train_cfg=dict(),
test_cfg=dict(mode='whole'))
dataset_type = 'StanfordBackgroundDataset'
data_root = 'data/koto/'
crop_size = (256, 256)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(
type='RandomResize',
scale=(320, 240),
ratio_range=(0.5, 2.0),
keep_ratio=True),
dict(type='RandomCrop', crop_size=(256, 256), cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PackSegInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(320, 240), keep_ratio=True),
dict(type='LoadAnnotations'),
dict(type='PackSegInputs')
]
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
tta_pipeline = [
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
dict(
type='TestTimeAug',
transforms=[[{
'type': 'Resize',
'scale_factor': 0.5,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 0.75,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 1.0,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 1.25,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 1.5,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 1.75,
'keep_ratio': True
}],
[{
'type': 'RandomFlip',
'prob': 0.0,
'direction': 'horizontal'
}, {
'type': 'RandomFlip',
'prob': 1.0,
'direction': 'horizontal'
}], [{
'type': 'LoadAnnotations'
}], [{
'type': 'PackSegInputs'
}]])
]
train_dataloader = dict(
batch_size=8,
num_workers=2,
persistent_workers=True,
sampler=dict(type='InfiniteSampler', shuffle=True),
dataset=dict(
type='StanfordBackgroundDataset',
data_root='data/koto/',
data_prefix=dict(img_path='imgs', seg_map_path='annos'),
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(
type='RandomResize',
scale=(320, 240),
ratio_range=(0.5, 2.0),
keep_ratio=True),
dict(type='RandomCrop', crop_size=(256, 256), cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PackSegInputs')
],
ann_file='data/koto/train_list.txt'))
val_dataloader = dict(
batch_size=1,
num_workers=4,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='StanfordBackgroundDataset',
data_root='data/koto/',
data_prefix=dict(img_path='imgs', seg_map_path='annos'),
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(320, 240), keep_ratio=True),
dict(type='LoadAnnotations'),
dict(type='PackSegInputs')
],
ann_file='data/koto/valid_list.txtt'))
test_dataloader = dict(
batch_size=1,
num_workers=4,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='StanfordBackgroundDataset',
data_root='data/koto/',
data_prefix=dict(img_path='imgs', seg_map_path='annos'),
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(320, 240), keep_ratio=True),
dict(type='LoadAnnotations'),
dict(type='PackSegInputs')
],
ann_file='data/koto/valid_list.txtt'))
val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
test_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
default_scope = 'mmseg'
env_cfg = dict(
cudnn_benchmark=True,
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
dist_cfg=dict(backend='nccl'))
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
type='SegLocalVisualizer',
vis_backends=[dict(type='LocalVisBackend')],
name='visualizer')
log_processor = dict(by_epoch=False)
log_level = 'INFO'
load_from = 'pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth'
resume = False
tta_model = dict(type='SegTTAModel')
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005),
clip_grad=None)
param_scheduler = [
dict(
type='PolyLR',
eta_min=0.0001,
power=0.9,
begin=0,
end=40000,
by_epoch=False)
]
train_cfg = dict(type='IterBasedTrainLoop', max_iters=800, val_interval=400)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=100, log_metric_by_epoch=False),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=400),
sampler_seed=dict(type='DistSamplerSeedHook'),
visualization=dict(type='SegVisualizationHook'))
work_dir = './work_dirs/tutorial'
randomness = dict(seed=0)
from mmengine.runner import Runner
from mmseg.utils import register_all_modules
# register all modules in mmseg into the registries
# do not init the default scope here because it will be init in the runner
register_all_modules(init_default_scope=False)
runner = Runner.from_cfg(cfg)
02/11 22:55:46 - mmengine - [4m[97mINFO[0m -
------------------------------------------------------------
System environment:
sys.platform: linux
Python: 3.8.16 (default, Jan 17 2023, 23:13:24) [GCC 11.2.0]
CUDA available: True
numpy_random_seed: 0
GPU 0: NVIDIA GeForce RTX 3060 Laptop GPU
CUDA_HOME: /usr/local/cuda-11.6
NVCC: Cuda compilation tools, release 11.6, V11.6.124
GCC: gcc (Uos 8.3.0.3-3+rebuild) 8.3.0
PyTorch: 1.13.1+cu116
PyTorch compiling details: PyTorch built with:
- GCC 9.3
- C++ Version: 201402
- Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 11.6
- NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
- CuDNN 8.6 (built against CUDA 11.8)
- Built with CuDNN 8.3.2
- Magma 2.6.1
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,
TorchVision: 0.14.1+cu116
OpenCV: 4.7.0
MMEngine: 0.5.0
Runtime environment:
cudnn_benchmark: True
mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
dist_cfg: {'backend': 'nccl'}
seed: 0
Distributed launcher: none
Distributed training: False
GPU number: 1
------------------------------------------------------------
02/11 22:55:46 - mmengine - [4m[97mINFO[0m - Config:
norm_cfg = dict(type='BN', requires_grad=True)
data_preprocessor = dict(
type='SegDataPreProcessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_val=0,
seg_pad_val=255,
size=(512, 1024))
model = dict(
type='EncoderDecoder',
data_preprocessor=dict(
type='SegDataPreProcessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_val=0,
seg_pad_val=255,
size=(256, 256)),
pretrained='open-mmlab://resnet50_v1c',
backbone=dict(
type='ResNetV1c',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
dilations=(1, 1, 2, 4),
strides=(1, 2, 1, 1),
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=False,
style='pytorch',
contract_dilation=True),
decode_head=dict(
type='PSPHead',
in_channels=2048,
in_index=3,
channels=512,
pool_scales=(1, 2, 3, 6),
dropout_ratio=0.1,
num_classes=2,
norm_cfg=dict(type='BN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
auxiliary_head=dict(
type='FCNHead',
in_channels=1024,
in_index=2,
channels=256,
num_convs=1,
concat_input=False,
dropout_ratio=0.1,
num_classes=8,
norm_cfg=dict(type='BN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
train_cfg=dict(),
test_cfg=dict(mode='whole'))
dataset_type = 'StanfordBackgroundDataset'
data_root = 'data/koto/'
crop_size = (256, 256)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(
type='RandomResize',
scale=(320, 240),
ratio_range=(0.5, 2.0),
keep_ratio=True),
dict(type='RandomCrop', crop_size=(256, 256), cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PackSegInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(320, 240), keep_ratio=True),
dict(type='LoadAnnotations'),
dict(type='PackSegInputs')
]
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
tta_pipeline = [
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
dict(
type='TestTimeAug',
transforms=[[{
'type': 'Resize',
'scale_factor': 0.5,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 0.75,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 1.0,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 1.25,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 1.5,
'keep_ratio': True
}, {
'type': 'Resize',
'scale_factor': 1.75,
'keep_ratio': True
}],
[{
'type': 'RandomFlip',
'prob': 0.0,
'direction': 'horizontal'
}, {
'type': 'RandomFlip',
'prob': 1.0,
'direction': 'horizontal'
}], [{
'type': 'LoadAnnotations'
}], [{
'type': 'PackSegInputs'
}]])
]
train_dataloader = dict(
batch_size=8,
num_workers=2,
persistent_workers=True,
sampler=dict(type='InfiniteSampler', shuffle=True),
dataset=dict(
type='StanfordBackgroundDataset',
data_root='data/koto/',
data_prefix=dict(img_path='imgs', seg_map_path='annos'),
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations'),
dict(
type='RandomResize',
scale=(320, 240),
ratio_range=(0.5, 2.0),
keep_ratio=True),
dict(type='RandomCrop', crop_size=(256, 256), cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PackSegInputs')
],
ann_file='data/koto/train_list.txt'))
val_dataloader = dict(
batch_size=1,
num_workers=4,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='StanfordBackgroundDataset',
data_root='data/koto/',
data_prefix=dict(img_path='imgs', seg_map_path='annos'),
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(320, 240), keep_ratio=True),
dict(type='LoadAnnotations'),
dict(type='PackSegInputs')
],
ann_file='data/koto/valid_list.txtt'))
test_dataloader = dict(
batch_size=1,
num_workers=4,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='StanfordBackgroundDataset',
data_root='data/koto/',
data_prefix=dict(img_path='imgs', seg_map_path='annos'),
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='Resize', scale=(320, 240), keep_ratio=True),
dict(type='LoadAnnotations'),
dict(type='PackSegInputs')
],
ann_file='data/koto/valid_list.txtt'))
val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
test_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
default_scope = 'mmseg'
env_cfg = dict(
cudnn_benchmark=True,
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
dist_cfg=dict(backend='nccl'))
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
type='SegLocalVisualizer',
vis_backends=[dict(type='LocalVisBackend')],
name='visualizer')
log_processor = dict(by_epoch=False)
log_level = 'INFO'
load_from = 'pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth'
resume = False
tta_model = dict(type='SegTTAModel')
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005),
clip_grad=None)
param_scheduler = [
dict(
type='PolyLR',
eta_min=0.0001,
power=0.9,
begin=0,
end=40000,
by_epoch=False)
]
train_cfg = dict(type='IterBasedTrainLoop', max_iters=800, val_interval=400)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=100, log_metric_by_epoch=False),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=400),
sampler_seed=dict(type='DistSamplerSeedHook'),
visualization=dict(type='SegVisualizationHook'))
work_dir = './work_dirs/tutorial'
randomness = dict(seed=0)
02/11 22:55:46 - mmengine - [5m[4m[33mWARNING[0m - The "visualizer" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:46 - mmengine - [5m[4m[33mWARNING[0m - The "vis_backend" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:47 - mmengine - [5m[4m[33mWARNING[0m - The "model" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
/home/linxu/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/backbones/resnet.py:431: UserWarning: DeprecationWarning: pretrained is a deprecated, please use "init_cfg" instead
warnings.warn('DeprecationWarning: pretrained is a deprecated, '
/home/linxu/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/decode_heads/decode_head.py:120: UserWarning: For binary segmentation, we suggest using`out_channels = 1` to define the outputchannels of segmentor, and use `threshold`to convert `seg_logits` into a predictionapplying a threshold
warnings.warn('For binary segmentation, we suggest using'
/home/linxu/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/builder.py:36: UserWarning: ``build_loss`` would be deprecated soon, please use ``mmseg.registry.MODELS.build()``
warnings.warn('``build_loss`` would be deprecated soon, please use '
/home/linxu/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/losses/cross_entropy_loss.py:235: UserWarning: Default ``avg_non_ignore`` is False, if you would like to ignore the certain label and average loss over non-ignore labels, which is the same with PyTorch official cross_entropy, set ``avg_non_ignore=True``.
warnings.warn(
02/11 22:55:48 - mmengine - [4m[97mINFO[0m - Distributed training is not used, all SyncBatchNorm (SyncBN) layers in the model will be automatically reverted to BatchNormXd layers if they are used.
02/11 22:55:48 - mmengine - [5m[4m[33mWARNING[0m - The "hook" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:48 - mmengine - [4m[97mINFO[0m - Hooks will be executed in the following order:
before_run:
(VERY_HIGH ) RuntimeInfoHook
(BELOW_NORMAL) LoggerHook
--------------------
before_train:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(VERY_LOW ) CheckpointHook
--------------------
before_train_epoch:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(NORMAL ) DistSamplerSeedHook
--------------------
before_train_iter:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
--------------------
after_train_iter:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(NORMAL ) SegVisualizationHook
(BELOW_NORMAL) LoggerHook
(LOW ) ParamSchedulerHook
(VERY_LOW ) CheckpointHook
--------------------
after_train_epoch:
(NORMAL ) IterTimerHook
(LOW ) ParamSchedulerHook
(VERY_LOW ) CheckpointHook
--------------------
before_val_epoch:
(NORMAL ) IterTimerHook
--------------------
before_val_iter:
(NORMAL ) IterTimerHook
--------------------
after_val_iter:
(NORMAL ) IterTimerHook
(NORMAL ) SegVisualizationHook
(BELOW_NORMAL) LoggerHook
--------------------
after_val_epoch:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(BELOW_NORMAL) LoggerHook
(LOW ) ParamSchedulerHook
(VERY_LOW ) CheckpointHook
--------------------
before_test_epoch:
(NORMAL ) IterTimerHook
--------------------
before_test_iter:
(NORMAL ) IterTimerHook
--------------------
after_test_iter:
(NORMAL ) IterTimerHook
(NORMAL ) SegVisualizationHook
(BELOW_NORMAL) LoggerHook
--------------------
after_test_epoch:
(VERY_HIGH ) RuntimeInfoHook
(NORMAL ) IterTimerHook
(BELOW_NORMAL) LoggerHook
--------------------
after_run:
(BELOW_NORMAL) LoggerHook
--------------------
/home/linxu/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/engine/hooks/visualization_hook.py:61: UserWarning: The draw is False, it means that the hook for visualization will not take effect. The results will NOT be visualized or stored.
warnings.warn('The draw is False, it means that the '
runner.train()
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "loop" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "dataset" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "transform" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "data sampler" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "optimizer wrapper constructor" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "optimizer" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "optim_wrapper" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "parameter scheduler" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "metric" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
/home/linxu/anaconda3/envs/mmlab2/lib/python3.8/site-packages/mmengine/evaluator/metric.py:47: UserWarning: The prefix is not set in metric class IoUMetric.
warnings.warn('The prefix is not set in metric class '
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The "weight initializer" registry in mmseg did not set import location. Fallback to call `mmseg.utils.register_all_modules` instead.
02/11 22:55:54 - mmengine - [4m[97mINFO[0m - load model from: open-mmlab://resnet50_v1c
02/11 22:55:54 - mmengine - [4m[97mINFO[0m - Loads checkpoint by openmmlab backend from path: open-mmlab://resnet50_v1c
02/11 22:55:54 - mmengine - [5m[4m[33mWARNING[0m - The model and loaded state dict do not match exactly
unexpected key in source state_dict: fc.weight, fc.bias
Loads checkpoint by local backend from path: pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth
The model and loaded state dict do not match exactly
size mismatch for decode_head.conv_seg.weight: copying a param with shape torch.Size([19, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([2, 512, 1, 1]).
size mismatch for decode_head.conv_seg.bias: copying a param with shape torch.Size([19]) from checkpoint, the shape in current model is torch.Size([2]).
size mismatch for auxiliary_head.conv_seg.weight: copying a param with shape torch.Size([19, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([8, 256, 1, 1]).
size mismatch for auxiliary_head.conv_seg.bias: copying a param with shape torch.Size([19]) from checkpoint, the shape in current model is torch.Size([8]).
02/11 22:55:55 - mmengine - [4m[97mINFO[0m - Load checkpoint from pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth
02/11 22:55:55 - mmengine - [4m[97mINFO[0m - Checkpoints will be saved to /home/linxu/Desktop/OpenMMLab-Space/mmsegmentation/work_dirs/tutorial.
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
Cell In[14], line 1
----> 1 runner.train()
File ~/anaconda3/envs/mmlab2/lib/python3.8/site-packages/mmengine/runner/runner.py:1686, in Runner.train(self)
1680 # Initiate inner count of `optim_wrapper`.
1681 self.optim_wrapper.initialize_count_status(
1682 self.model,
1683 self._train_loop.iter, # type: ignore
1684 self._train_loop.max_iters) # type: ignore
-> 1686 model = self.train_loop.run() # type: ignore
1687 self.call_hook('after_run')
1688 return model
File ~/anaconda3/envs/mmlab2/lib/python3.8/site-packages/mmengine/runner/loops.py:264, in IterBasedTrainLoop.run(self)
261 self.runner.model.train()
263 data_batch = next(self.dataloader_iterator)
--> 264 self.run_iter(data_batch)
266 self._decide_current_val_interval()
267 if (self.runner.val_loop is not None
268 and self._iter >= self.val_begin
269 and self._iter % self.val_interval == 0):
File ~/anaconda3/envs/mmlab2/lib/python3.8/site-packages/mmengine/runner/loops.py:287, in IterBasedTrainLoop.run_iter(self, data_batch)
282 self.runner.call_hook(
283 'before_train_iter', batch_idx=self._iter, data_batch=data_batch)
284 # Enable gradient accumulation mode and avoid unnecessary gradient
285 # synchronization during gradient accumulation process.
286 # outputs should be a dict of loss.
--> 287 outputs = self.runner.model.train_step(
288 data_batch, optim_wrapper=self.runner.optim_wrapper)
290 self.runner.call_hook(
291 'after_train_iter',
292 batch_idx=self._iter,
293 data_batch=data_batch,
294 outputs=outputs)
295 self._iter += 1
File ~/anaconda3/envs/mmlab2/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py:114, in BaseModel.train_step(self, data, optim_wrapper)
112 with optim_wrapper.optim_context(self):
113 data = self.data_preprocessor(data, True)
--> 114 losses = self._run_forward(data, mode='loss') # type: ignore
115 parsed_losses, log_vars = self.parse_losses(losses) # type: ignore
116 optim_wrapper.update_params(parsed_losses)
File ~/anaconda3/envs/mmlab2/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py:326, in BaseModel._run_forward(self, data, mode)
316 """Unpacks data for :meth:`forward`
317
318 Args:
(...)
323 dict or list: Results of training or testing mode.
324 """
325 if isinstance(data, dict):
--> 326 results = self(**data, mode=mode)
327 elif isinstance(data, (list, tuple)):
328 results = self(*data, mode=mode)
File ~/anaconda3/envs/mmlab2/lib/python3.8/site-packages/torch/nn/modules/module.py:1194, in Module._call_impl(self, *input, **kwargs)
1190 # If we don't have any hooks, we want to skip the rest of the logic in
1191 # this function, and just call forward.
1192 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1193 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1194 return forward_call(*input, **kwargs)
1195 # Do not call functions when jit is used
1196 full_backward_hooks, non_full_backward_hooks = [], []
File ~/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/segmentors/base.py:94, in BaseSegmentor.forward(self, inputs, data_samples, mode)
64 """The unified entry for a forward process in both training and test.
65
66 The method should accept three modes: "tensor", "predict" and "loss":
(...)
91 - If ``mode="loss"``, return a dict of tensor.
92 """
93 if mode == 'loss':
---> 94 return self.loss(inputs, data_samples)
95 elif mode == 'predict':
96 return self.predict(inputs, data_samples)
File ~/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py:176, in EncoderDecoder.loss(self, inputs, data_samples)
172 x = self.extract_feat(inputs)
174 losses = dict()
--> 176 loss_decode = self._decode_head_forward_train(x, data_samples)
177 losses.update(loss_decode)
179 if self.with_auxiliary_head:
File ~/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py:137, in EncoderDecoder._decode_head_forward_train(self, inputs, data_samples)
134 """Run forward function and calculate loss for decode head in
135 training."""
136 losses = dict()
--> 137 loss_decode = self.decode_head.loss(inputs, data_samples,
138 self.train_cfg)
140 losses.update(add_prefix(loss_decode, 'decode'))
141 return losses
File ~/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/decode_heads/decode_head.py:262, in BaseDecodeHead.loss(self, inputs, batch_data_samples, train_cfg)
249 """Forward function for training.
250
251 Args:
(...)
259 dict[str, Tensor]: a dictionary of loss components
260 """
261 seg_logits = self.forward(inputs)
--> 262 losses = self.loss_by_feat(seg_logits, batch_data_samples)
263 return losses
File ~/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/decode_heads/decode_head.py:336, in BaseDecodeHead.loss_by_feat(self, seg_logits, batch_data_samples)
329 else:
330 loss[loss_decode.loss_name] += loss_decode(
331 seg_logits,
332 seg_label,
333 weight=seg_weight,
334 ignore_index=self.ignore_index)
--> 336 loss['acc_seg'] = accuracy(
337 seg_logits, seg_label, ignore_index=self.ignore_index)
338 return loss
File ~/Desktop/OpenMMLab-Space/mmsegmentation/mmseg/models/losses/accuracy.py:49, in accuracy(pred, target, topk, thresh, ignore_index)
47 correct = correct & (pred_value > thresh).t()
48 if ignore_index is not None:
---> 49 correct = correct[:, target != ignore_index]
50 res = []
51 eps = torch.finfo(torch.float32).eps
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
OpenMMLab AI实战营 第七课笔记的更多相关文章
- 华为云 AI 实战营计划，带你迈上 AI 之路
当今,AI的开发人才需求呈现极大的供需不平衡.所有开发者都关心,要如何从一名开发者晋升为AI开发者?AI开发能力,是主要的进入障碍.不用慌,华为云推出了 <华为云ModelArts-Lab AI ...
- Elasticsearch7.X 入门学习第七课笔记-----Mapping多字段与自定义Analyzer
原文:Elasticsearch7.X 入门学习第七课笔记-----Mapping多字段与自定义Analyzer 版权声明:本文为博主原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处 ...
- 红帽学习笔记[RHCSA] 第七课[网络配置相关]
第七课[网络配置相关] 在Vmware中添加网卡 编辑 -> 编辑虚拟网络 -> 添加网络->随便选择一个如VMnet2-> 选择仅主机模式 -> 勾掉使用本地DHCP服 ...
- 小马哥的 Java 项目实战营学习笔记（1）
小马哥的 Java 项目实战营 小马哥的 Java 项目实战营 第二节:数据存储之 JDBC JDBC 核心 API 数据源 接口 - javax.sql.DataSource获取方式 1.普通对象初 ...
- Elasticsearch7.X 入门学习第三课笔记----search api学习（URI Search）
原文:Elasticsearch7.X 入门学习第三课笔记----search api学习(URI Search) 版权声明:本文为博主原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出 ...
- 清华大学ucore操作系统课笔记
操作系统 清华大学ucore操作系统课笔记 全文思维导图 1. 操作系统概述 1.1 什么是操作系统? 操作系统的定义 没有公认的精确定义 一个控制程序 一个系统软件 控制程序执行过程,防止错误和计算 ...
- Kali Linux Web 渗透测试视频教程— 第七课 OpenVas
Kali Linux Web 渗透测试视频教程— 第七课 OpenVas 文/玄魂 视频教程地址:http://edu.51cto.com/course/course_id-1887.html 目录 ...
- NeHe OpenGL教程 第七课：光照和键盘
转自[翻译]NeHe OpenGL 教程 前言 声明,此 NeHe OpenGL教程系列文章由51博客yarin翻译(2010-08-19),本博客为转载并稍加整理与修改.对NeHe的OpenGL管线 ...
- Udacity调试课笔记之断言异常
Udacity调试课笔记之断言异常 这一单元的内容不是很多,如Zeller教授所说,就是如何写.检查断言,并如何使用工具实现自动推导出断言的条件. 现在,多数的编程语言,尤其是高级编程语言都会有内置的 ...
- 菜农群课笔记之ICP与ISP----20110412(整理版)
耗时一上午时间对HOT大叔昨晚的群课内容进行温故并整理,现将其上传,若想看直播可到下面链接处下载:http://bbs.21ic.com/icview-229746-1-1.html 成 ...
随机推荐
- Oracle 11.2 RAC 删除节点
软硬件环境:与上一篇文章一致: 一般对 CRS 层面数据结构做重要操作之前一定要先备份 OCR [root@vastdata4 ~]# ocrconfig -manualbackup vastdat ...
- AI五子棋_10 更多的算法探索
AI五子棋 第十步 恭喜你到达第十步! 你已经完成了一个AI的设计,下面就需要发动你的智慧让你的机器大脑变得更聪明了! 我们的征途是星辰大海! 更多资料可以参考这个列表 https://gomocup ...
- 搞清楚这个老六的真面目！逐层‘剥开’人工智能中的卷积神经网络（CNN）
第三章:超越基础--图像中的特征检测 上一篇<揭开计算机视觉的神秘面纱,原来机器是这样"看图"的!> 本篇序言:上一篇我们实现并训练了一个神经网络,成功让计算机&quo ...
- 用ffmpeg压缩视频、提高声音、加水印 命令记录
ffmpeg -i in.mp4 -i LOGOW.png -filter_complex overlay=W-w:56 -c:v libx264 -x264-params "crf=35& ...
- 在react中使用阿里图标库
参考教程:https://blog.csdn.net/qq_41977441/article/details/110352463 阿里图标库:https://www.iconfont.cn/ 成果展示 ...
- 2个月搞定计算机二级C语言——真题（9）解析
1. 前言 本篇我们讲解2个月搞定计算机二级C语言--真题9 2. 程序填空题 2.1 题目要求 2.2 提供的代码 #include <stdio.h> double f1(double ...
- 3.14 深度剖析Linux硬链接和软链接，直击它们的本质！
建立硬链接和软链接非常简单,那这两种链接有什么区别?它们都有什么作用?这才是链接文件最不容易理解的地方,我们分别来讲讲. ln创建硬链接 我们再来建立一个硬链接文件,然后看看这两个文件的特点. [ro ...
- 研发LLM模型，如何用数值表示人类自然语言？
上一篇:<人工智能--自然语言处理简介> 序言:人工智能大语言模型(LLM)如何理解人类的自然语言?这个过程的核心在于将文本转化为计算机能处理的数值形式,经过计算,最终达到对语言的理解.起 ...
- 2. jenkins的安装
Docker方式: 如果在安装社区推荐插件时报错,网络延迟,则建议采用官方yum安装 遇到一个问题:公司局域网openstack虚拟机安装时,修改了镜像仍报错,但是自己电脑vmware虚拟机正常,暂时 ...
- 批量归一化（BN, Batch Normalization）
现在的神经网络通常都特别深,在输出层向输入层传播导数的过程中,梯度很容易被激活函数或是权重以指数级的规模缩小或放大,从而产生"梯度消失"或"梯度爆炸"的现象,造 ...