mmrotate
mmrotate copied to clipboard
open-mmlab
formatting the inference
Prerequisite
- [X] I have searched Issues and Discussions but cannot get the expected help.
- [X] I have read the FAQ documentation but cannot get the expected help.
- [X] The bug has not been fixed in the latest version (master) or latest version (1.x).
Task
I'm using the official example scripts/configs for the officially supported tasks/models/datasets.
Branch
master branch https://github.com/open-mmlab/mmrotate
Environment
Python: 3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0]
CUDA available: True
GPU 0,1,2: NVIDIA RTX A6000
CUDA_HOME: /usr
NVCC: Cuda compilation tools, release 11.6, V11.6.124
GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
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 8.3.2 (built against CUDA 11.5)
- 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
MMCV: 1.7.1
MMCV Compiler: GCC 9.3
MMCV CUDA Compiler: 11.6
MMRotate: 0.3.4+04405ab
Reproduces the problem - code sample
CUDA_VISIBLE_DEVICES=0 python ./tools/test.py redet_re101_39.py /home/ntekay01/mmrotate/work_dirs/redet_101_36/epoch_1800.pth --format-only --eval-options submission_dir=work_dirs/rezult
Reproduces the problem - command or script
CUDA_VISIBLE_DEVICES=0 python ./tools/test.py redet_re101_39.py /home/ntekay01/mmrotate/work_dirs/redet_101_36/epoch_1800.pth --format-only --eval-options submission_dir=work_dirs/rezult
Reproduces the problem - error message
Hi dear contributors and maintainers, thank you so much for your work! we're very grateful.
I am trying to format the prediction results into textual that i can use in my process without going through deployment with torchserve, I wish to keep it at mmrotate level.
used python ./tools/test.py mentioned above and got the error x_y_2 = re.findall(r'\d+', x_y[0]) ; IndexError: list index out of range . After reading similar issues i see they're dealing with splitting problem. whereas i don't, my data is full-sized in training and i do not wish to apply in inference too. Is there way to do that please?
thanks so much in advance @zytx121 @y
Additional information
here's my config file, the paths are correct and the dota.py is modified accordingly
dataset_type = 'DOTADataset'
data_root = '/home/ntekay01/data_obb/obb_dataset_v3_balanced/'
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),
dict(type='RResize', img_scale=(3200, 2400)),
dict(
type='RRandomFlip',
flip_ratio=[0.25, 0.25, 0.25],
direction=['horizontal', 'vertical', 'diagonal'],
version='le135'),
dict(
type='PolyRandomRotate',
rotate_ratio=0.5,
angles_range=180,
auto_bound=False,
rect_classes=[9, 11],
version='le135'),
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'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(3200, 2400),
flip=False,
transforms=[
dict(type='RResize'),
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'])
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=8,
train=dict(
type='DOTADataset',
ann_file='/home/ntekay01/data_obb/obb_dataset_v3_balanced/train/annfiles/',
img_prefix='/home/ntekay01/data_obb/obb_dataset_v3_balanced/train/images/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RResize', img_scale=(3200, 2400)),
dict(
type='RRandomFlip',
flip_ratio=[0.25, 0.25, 0.25],
direction=['horizontal', 'vertical', 'diagonal'],
version='le135'),
dict(
type='PolyRandomRotate',
rotate_ratio=0.5,
angles_range=180,
auto_bound=False,
rect_classes=[9, 11],
version='le135'),
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'])
],
version='le90'),
val=dict(
type='DOTADataset',
ann_file='/home/ntekay01/data_obb/obb_dataset_v3_balanced/valid/annfiles/',
img_prefix='/home/ntekay01/data_obb/obb_dataset_v3_balanced/valid/images/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(3200, 2400),
flip=False,
transforms=[
dict(type='RResize'),
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'])
])
],
version='le135'),
test=dict(
type='DOTADataset',
ann_file='/home/ntekay01/data_obb/obb_dataset_v3_balanced/test/annfiles/',
img_prefix='/home/ntekay01/data_obb/obb_dataset_v3_balanced/test/images/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(3200, 2400),
flip=False,
transforms=[
dict(type='RResize'),
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'])
])
],
version='le90'))
evaluation = dict(interval=100, metric='mAP')
optimizer = dict(type='SGD', lr=0.005, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.3333333333333333,
step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=2000)
checkpoint_config = dict(interval=100)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
angle_version = 'le135'
model = dict(
type='ReDet',
backbone=dict(
type='ReResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
pretrained='work_dirs/pretrain/re_resnet101_v2_c8_batch256-f248cc41.pth'
),
neck=dict(
type='ReFPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RotatedRPNHead',
in_channels=256,
feat_channels=256,
version='le90',
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='SmoothL1Loss', beta=0.1111111111111111, loss_weight=1.0)),
roi_head=dict(
type='RoITransRoIHead',
version='le90',
num_stages=2,
stage_loss_weights=[1, 1],
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]),
dict(
type='RotatedSingleRoIExtractor',
roi_layer=dict(
type='RiRoIAlignRotated',
out_size=7,
num_samples=2,
num_orientations=8,
clockwise=True),
out_channels=256,
featmap_strides=[4, 8, 16, 32])
],
bbox_head=[
dict(
type='RotatedShared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=36,
bbox_coder=dict(
type='DeltaXYWHAHBBoxCoder',
angle_range='le90',
norm_factor=2,
edge_swap=True,
target_means=[0.0, 0.0, 0.0, 0.0, 0.0],
target_stds=[0.1, 0.1, 0.2, 0.2, 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='RotatedShared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=36,
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
angle_range='le90',
norm_factor=None,
edge_swap=True,
proj_xy=True,
target_means=[0.0, 0.0, 0.0, 0.0, 0.0],
target_stds=[0.05, 0.05, 0.1, 0.1, 0.5]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, 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,
gpu_assign_thr=200),
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_pre=2000,
max_per_img=2000,
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=False,
ignore_iof_thr=-1,
iou_calculator=dict(type='BboxOverlaps2D')),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1,
iou_calculator=dict(type='RBboxOverlaps2D')),
sampler=dict(
type='RRandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)
]),
test_cfg=dict(
rpn=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
nms_pre=2000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(iou_thr=0.1),
max_per_img=2000)))
work_dir = './work_dirs/redet_101_36'
auto_resume = False
gpu_ids = range(0, 1)
Did you solve this problem? I've encountered a similar issue these past two days. I initially split the dataset and then used a command to generate the results for the test set for submission.
The command I used:
CUDA_LAUNCH_BLOCKING=1 CUDA_VISIBLE_DEVICES=1 python ./tools/test.py /mnt/sda/zxh/code/mmrotate/configs/oriented_reppoints/oriented_reppoints_r50_fpn_40e_dota_ms_le135.py /mnt/sda/zxh/code/mmrotate/ckpt/oriented_reppoints_r50_fpn_40e_dota_ms_le135-bb0323fd.pth --format-only --eval-options submission_dir=work_dirs/Task1_results_20240703
However, I encountered the same issue when using the resultmerge function of the dotadevkit package later on. I think the problem might be with the output format. Below is part of the content from my output:
P1870 0.09854765981435776 377.27 5178.65 674.38 5202.58 652.82 5470.35 355.70 5446.42
P1870 0.07365919649600983 460.82 1777.70 732.45 1765.00 736.17 1844.41 464.53 1857.11
I believe the output format should be something like P1870__1024__0, but I don't know how to fix it.
