Comments (2)
@Chen823 Please refer to GETTING_STARTED.md for details.
from solo.
@Chen823 Please refer to GETTING_STARTED.md for details.
@WXinlong thanks for your prompt reply, i get it.
but now i am in another confuze :
i trained custom COCO data set with ./tools/dist_train.shconfigs/solo/decoupled_solo_light_dcn_r50_fpn_8gpu_3x.py 4
and successfully got weights files like this ,
“”“”
2020-04-29 11:42:54,670 - mmdet - INFO - Distributed training: True
2020-04-29 11:42:54,670 - mmdet - INFO - MMDetection Version: 1.0.0+d5398a0
2020-04-29 11:42:54,671 - mmdet - INFO - Config:
model settings
model = dict(
type='SOLO',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3), # C2, C3, C4, C5
frozen_stages=1,
style='pytorch',
dcn=dict(
type='DCN',
deformable_groups=1,
fallback_on_stride=False),
stage_with_dcn=(False, True, True, True)),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=0,
num_outs=5),
bbox_head=dict(
type='DecoupledSOLOLightHead',
num_classes=2, # 1+1
in_channels=256,
stacked_convs=4,
use_dcn_in_tower=True,
type_dcn='DCN',
seg_feat_channels=256,
strides=[8, 8, 16, 32, 32],
scale_ranges=((1, 64), (32, 128), (64, 256), (128, 512), (256, 2048)),
sigma=0.2,
num_grids=[40, 36, 24, 16, 12],
cate_down_pos=0,
loss_ins=dict(
type='DiceLoss',
use_sigmoid=True,
loss_weight=3.0),
loss_cate=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
))
training and testing settings
train_cfg = dict()
test_cfg = dict(
nms_pre=500,
score_thr=0.1,
mask_thr=0.5,
update_thr=0.05,
kernel='gaussian', # gaussian/linear
sigma=2.0,
max_per_img=100)
dataset settings
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='Resize',
img_scale=[(852, 512), (852, 480), (852, 448),
(852, 416), (852, 384), (852, 352)],
multiscale_mode='value',
keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(852, 512),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'test2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
# img_prefix=data_root + 'val2017/',
img_prefix=data_root + 'test2017/',
pipeline=test_pipeline))
optimizer
optimizer = dict(type='SGD', lr=0.01, 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=[27, 33])
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 = 80
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/decoupled_solo_light_dcn_release_r50_fpn_8gpu_3x'
load_from = None
resume_from = None
workflow = [('train', 1)]
2020-04-29 11:42:55,303 - mmdet - INFO - load model from: torchvision://resnet50
2020-04-29 11:42:59,583 - mmdet - WARNING - The model and loaded state dict do not match exactly
unexpected key in source state_dict: fc.weight, fc.bias
missing keys in source state_dict: layer2.0.conv2.conv_offset.weight, layer2.0.conv2.conv_offset.bias, layer2.1.conv2.conv_offset.weight, layer2.1.conv2.conv_offset.bias, layer2.2.conv2.conv_offset.weight, layer2.2.conv2.conv_offset.bias, layer2.3.conv2.conv_offset.weight, layer2.3.conv2.conv_offset.bias, layer3.0.conv2.conv_offset.weight, layer3.0.conv2.conv_offset.bias, layer3.1.conv2.conv_offset.weight, layer3.1.conv2.conv_offset.bias, layer3.2.conv2.conv_offset.weight, layer3.2.conv2.conv_offset.bias, layer3.3.conv2.conv_offset.weight, layer3.3.conv2.conv_offset.bias, layer3.4.conv2.conv_offset.weight, layer3.4.conv2.conv_offset.bias, layer3.5.conv2.conv_offset.weight, layer3.5.conv2.conv_offset.bias, layer4.0.conv2.conv_offset.weight, layer4.0.conv2.conv_offset.bias, layer4.1.conv2.conv_offset.weight, layer4.1.conv2.conv_offset.bias, layer4.2.conv2.conv_offset.weight, layer4.2.conv2.conv_offset.bias
2020-04-29 11:42:59,827 - mmdet - INFO - Start running, host: adt@adt-SA5212M5, work_dir: /home/adt/Documents/alg/big-xing/SOLO/work_dirs/decoupled_solo_light_dcn_release_r50_fpn_8gpu_3x
2020-04-29 11:42:59,828 - mmdet - INFO - workflow: [('train', 1)], max: 80 epochs
“”“”
after that, i wanna test and visualize my result with
"""
./tools/dist_test.sh configs/solo/decoupled_solo_light_dcn_r50_fpn_8gpu_3x.py ./work_dirs/decoupled_solo_light_dcn_release_r50_fpn_8gpu_3x/epoch_80.pth 4 --show --out results_solo.pkl --eval segm
"""
and
"""
python tools/test_ins_vis.py configs/solo/decoupled_solo_light_dcn_r50_fpn_8gpu_3x.py ./work_dirs/decoupled_solo_light_dcn_release_r50_fpn_8gpu_3x/latest.pth --show --save_dir work_dirs/vis_solo
"""
, test result is :
"""
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
loading annotations into memory...
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
Done (t=0.00s)
creating index...
index created!
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
[ ] 0/2, elapsed: 0s, ETA:/home/adt/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/functional.py:2539: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 3/2, 1.8 task/s, elapsed: 2s, ETA: [>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 4/2, 2.4 task/s, elapsed: 2s, ETA: 0s/home/adt/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/functional.py:2539: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
/home/adt/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/functional.py:2539: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
/home/adt/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/functional.py:2539: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
writing results to results_solo.pkl
Starting evaluate segm
result file is:results_solo.pkl.segm.json
Loading and preparing results...
Traceback (most recent call last):
File "./tools/test_ins.py", line 257, in
main()
File "./tools/test_ins.py", line 235, in main
coco_eval(result_files, eval_types, dataset.coco)
File "/home/adt/Documents/alg/big-xing/SOLO/mmdet/core/evaluation/coco_utils.py", line 42, in coco_eval
coco_dets = coco.loadRes(result_file)
File "/home/adt/anaconda3/envs/pytorch/lib/python3.6/site-packages/pycocotools/coco.py", line 326, in loadRes
if 'caption' in anns[0]:
IndexError: list index out of range
Traceback (most recent call last):
File "/home/adt/anaconda3/envs/pytorch/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/adt/anaconda3/envs/pytorch/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/adt/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/distributed/launch.py", line 235, in
main()
File "/home/adt/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/distributed/launch.py", line 231, in main
cmd=process.args)
subprocess.CalledProcessError: Command '['/home/adt/anaconda3/envs/pytorch/bin/python', '-u', './tools/test_ins.py', '--local_rank=0', 'configs/solo/decoupled_solo_light_dcn_r50_fpn_8gpu_3x.py', './work_dirs/decoupled_solo_light_dcn_release_r50_fpn_8gpu_3x/epoch_80.pth', '--launcher', 'pytorch', '--show', '--out', 'results_solo.pkl', '--eval', 'segm']' returned non-zero exit status 1.
"""
meanwhile, visualize result is :
there is no result images generated in "./word_dirs/vis_solo".
could u give me some further advises to this problem? thank u.
from solo.
Related Issues (20)
- How to run video on inference_demo.py ??
- How to test the calculation amount (Flops) of solov2? Thank you~
- Win10 Installation Tutorial HOT 1
- Change Maximum allowed Pytorch Version to 10.1
- About training configuration of SOLOv2 on LVIS dataset
- TypeError: SOLOv2: __init__() got an unexpected keyword argument 'mask_feat_head' HOT 2
- dynamic conv
- SOLOv2 get segmentation mask and classes
- ImportError: cannot import name 'coco_eval' from 'mmdet.core'
- Relu inplace ops making issues HOT 1
- About dataset's picture size problem
- 如何看评价结果
- Welcome update to OpenMMLab 2.0
- How can I improve AP accuracy on my dataset
- I have a bug when I launch train.py
- I don't succeeds to install solov2 with anaconda on windows 10
- Unable to evaluate bbox HOT 1
- TypeError: impad() takes 1 positional argument but 2 positional arguments (and 1 keyword-only argument) were given HOT 1
- installation made easy
- What does this code snippet in solo_head.py mean? I'm so confused.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from solo.