i have the DCNv2，but it's always error

[wangyunlong1111]

(CenterTrack) I:\uc\CenterTrack-master\src>python demo.py tracking,ddd --load_model ../models/nuScenes_3Dtracking.pth --dataset nuscenes --pre_hm --track_thresh 0.1 --demo ../videos/nuscenes_mini.mp4 --test_focal_length 633
import DCN failed
Import DCN failed
import DCN failed
import DCN failed
E:\Anaconda3\envs\CenterTrack\lib\site-packages\sklearn\utils\linear_assignment_.py:22: FutureWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead.
FutureWarning)
Running tracking
Using tracking threshold for out threshold! 0.1
Fix size testing.
training chunk_sizes: [32]
input h w: 448 800
heads {'hm': 10, 'reg': 2, 'wh': 2, 'tracking': 2, 'dep': 1, 'rot': 8, 'dim': 3, 'amodel_offset': 2}
weights {'hm': 1, 'reg': 1, 'wh': 0.1, 'tracking': 1, 'dep': 1, 'rot': 1, 'dim': 1, 'amodel_offset': 1}
head conv {'hm': [256], 'reg': [256], 'wh': [256], 'tracking': [256], 'dep': [256], 'rot': [256], 'dim': [256], 'amodel_offset': [256]}
Creating model...
Using node type: (<class 'model.networks.dla.DeformConv'>, <class 'model.networks.dla.DeformConv'>)
Warning: No ImageNet pretrain!!
Traceback (most recent call last):
File "demo.py", line 128, in
demo(opt)
File "demo.py", line 24, in demo
detector = Detector(opt)
File "I:\uc\CenterTrack-master\src\lib\detector.py", line 33, in init
opt.arch, opt.heads, opt.head_conv, opt=opt)
File "I:\uc\CenterTrack-master\src\lib\model\model.py", line 28, in create_model
model = model_class(num_layers, heads=head, head_convs=head_conv, opt=opt)
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 612, in init
node_type=self.node_type)
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 565, in init
node_type=node_type))
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 527, in init
proj = node_type[0](c, o)
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 514, in init
self.conv = DCN(chi, cho, kernel_size=(3,3), stride=1, padding=1, dilation=1, deformable_groups=1)
TypeError: 'NoneType' object is not callable

(CenterTrack) I:\uc\CenterTrack-master\src>python demo.py tracking,ddd --load_model ../models/nuScenes_3Dtracking.pth --dataset nuscenes --pre_hm --track_thresh 0.1 --demo ../videos/nuscenes_mini.mp4 --test_focal_length 633
import DCN failed
Import DCN failed
import DCN failed
import DCN failed
E:\Anaconda3\envs\CenterTrack\lib\site-packages\sklearn\utils\linear_assignment_.py:22: FutureWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead.
FutureWarning)
Running tracking
Using tracking threshold for out threshold! 0.1
Fix size testing.
training chunk_sizes: [32]
input h w: 448 800
heads {'hm': 10, 'reg': 2, 'wh': 2, 'tracking': 2, 'dep': 1, 'rot': 8, 'dim': 3, 'amodel_offset': 2}
weights {'hm': 1, 'reg': 1, 'wh': 0.1, 'tracking': 1, 'dep': 1, 'rot': 1, 'dim': 1, 'amodel_offset': 1}
head conv {'hm': [256], 'reg': [256], 'wh': [256], 'tracking': [256], 'dep': [256], 'rot': [256], 'dim': [256], 'amodel_offset': [256]}
Creating model...
Using node type: (<class 'model.networks.dla.DeformConv'>, <class 'model.networks.dla.DeformConv'>)
Warning: No ImageNet pretrain!!
Traceback (most recent call last):
File "demo.py", line 128, in
demo(opt)
File "demo.py", line 24, in demo
detector = Detector(opt)
File "I:\uc\CenterTrack-master\src\lib\detector.py", line 33, in init
opt.arch, opt.heads, opt.head_conv, opt=opt)
File "I:\uc\CenterTrack-master\src\lib\model\model.py", line 28, in create_model
model = model_class(num_layers, heads=head, head_convs=head_conv, opt=opt)
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 612, in init
node_type=self.node_type)
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 565, in init
node_type=node_type))
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 527, in init
proj = node_type[0](c, o)
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 514, in init
self.conv = DCN(chi, cho, kernel_size=(3,3), stride=1, padding=1, dilation=1, deformable_groups=1)
TypeError: 'NoneType' object is not callable

(CenterTrack) I:\uc\CenterTrack-master\src>python demo.py tracking,ddd --load_model ../models/nuScenes_3Dtracking.pth --dataset nuscenes --pre_hm --track_thresh 0.1 --demo ../videos/nuscenes_mini.mp4 --test_focal_length 633
import DCN failed
Import DCN failed
import DCN failed
import DCN failed
E:\Anaconda3\envs\CenterTrack\lib\site-packages\sklearn\utils\linear_assignment_.py:22: FutureWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead.
FutureWarning)
Running tracking
Using tracking threshold for out threshold! 0.1
Fix size testing.
training chunk_sizes: [32]
input h w: 448 800
heads {'hm': 10, 'reg': 2, 'wh': 2, 'tracking': 2, 'dep': 1, 'rot': 8, 'dim': 3, 'amodel_offset': 2}
weights {'hm': 1, 'reg': 1, 'wh': 0.1, 'tracking': 1, 'dep': 1, 'rot': 1, 'dim': 1, 'amodel_offset': 1}
head conv {'hm': [256], 'reg': [256], 'wh': [256], 'tracking': [256], 'dep': [256], 'rot': [256], 'dim': [256], 'amodel_offset': [256]}
Creating model...
Using node type: (<class 'model.networks.dla.DeformConv'>, <class 'model.networks.dla.DeformConv'>)
Warning: No ImageNet pretrain!!
Traceback (most recent call last):
File "demo.py", line 128, in
demo(opt)
File "demo.py", line 24, in demo
detector = Detector(opt)
File "I:\uc\CenterTrack-master\src\lib\detector.py", line 33, in init
opt.arch, opt.heads, opt.head_conv, opt=opt)
File "I:\uc\CenterTrack-master\src\lib\model\model.py", line 28, in create_model
model = model_class(num_layers, heads=head, head_convs=head_conv, opt=opt)
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 612, in init
node_type=self.node_type)
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 565, in init
node_type=node_type))
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 527, in init
proj = node_type[0](c, o)
File "I:\uc\CenterTrack-master\src\lib\model\networks\dla.py", line 514, in init
self.conv = DCN(chi, cho, kernel_size=(3,3), stride=1, padding=1, dilation=1, deformable_groups=1)
TypeError: 'NoneType' object is not callable

(CenterTrack) I:\uc\CenterTrack-master\src>python demo.py tracking,ddd --load_model ../models/nuScenes_3Dtracking.pth --dataset nuscenes --pre_hm --track_thresh 0.1 --demo ../videos/nuscenes_mini.mp4 --test_focal_length 633
i

[yktangac]

I solved it but can u tell me which Pytorch version you're using.
In case with this error messages, I presume that you're not using Charles Shang's DCNv2 and you've successfully compiled the DCNv2, right?

The solution is simple since Matthew's DCNv2 has nested.
You have to modified the backbone python like dla.py
Go to $CenterTrack_Root/src/lib/model/network/
just add few lines of code to fix it:

import sys
sys.path.append("path/to/center-tracker/CenterTrack/src/lib/model/networks/DCNv2")
try:
    from .DCNv2.DCN.dcn_v2 import DCN
except:
    print('import DCN failed')
    DCN = None

[fabrizioschiano]

Hi @yktangac , i guess the only lines to add are:

import sys
sys.path.append("path/to/center-tracker/CenterTrack/src/lib/model/networks/DCNv2")

correct?

Anyway, i tried it and it did not solve the problem for me.

[touranisatyajit]

Hi @wangyunlong1111. I also faced this problem with Python 3.6. When I shifted to Python 3.8, the error got resolved after incorporating @yktangac's solution

[yktangac]

Hi @yktangac , i guess the only lines to add are:

import sys
sys.path.append("path/to/center-tracker/CenterTrack/src/lib/model/networks/DCNv2")

correct?

Anyway, i tried it and it did not solve the problem for me.

Well, you don't actually need that line: sys.path.append("path/to/center-tracker/CenterTrack/src/lib/model/networks/DCNv2") . What I modified are in dla.py, dlaup.py, msraup.py, and resdcn.py

Matthew's DNCv2 is compatible with Pytorch versions from 1.6-1.8. If you install this DCNv2, just do the following in the above mentioned python files.

import sys
try:
    #from .DCNv2.DCN.dcn_v2 import DCN <--- this is for Charles Shang's DCNv2
    from DCN.dcn_v2 import DCN <--- if you're using Pytorch 1.6+

except:
    print('import DCN failed')
    DCN = None

Hope it helps!

[Pamulapati13]

Hi @yktangac ,

Hi @yktangac , i guess the only lines to add are:

import sys
sys.path.append("path/to/center-tracker/CenterTrack/src/lib/model/networks/DCNv2")

correct?
Anyway, i tried it and it did not solve the problem for me.

Well, you don't actually need that line: sys.path.append("path/to/center-tracker/CenterTrack/src/lib/model/networks/DCNv2") . What I modified are in dla.py, dlaup.py, msraup.py, and resdcn.py

Matthew's DNCv2 is compatible with Pytorch versions from 1.6-1.8. If you install this DCNv2, just do the following in the above mentioned python files.

import sys
try:
    #from .DCNv2.DCN.dcn_v2 import DCN <--- this is for Charles Shang's DCNv2
    from DCN.dcn_v2 import DCN <--- if you're using Pytorch 1.6+

except:
    print('import DCN failed')
    DCN = None

Hope it helps!

This helped to solve the issue. Thank you!

[philgineer]

Using DCNv2_newest instead of given DCNv2 worked for me.
You don't need to change any codes in CenterTrack with this way.

• cd CenterTrack/src/lib/model/networks/
• git clone https://codechina.csdn.net/mirrors/jinfagang/DCNv2_latest.git
• cd DCNv2_latest
• vim make.sh
  • remove sudo to prevent install out of current environment.
  • sudo python3 setup.py build develop -> python3 setup.py build develop
• ./make.sh

[daipeizhe]

@philgineer

Using DCNv2_newest instead of given DCNv2 worked for me. You don't need to change any codes in CenterTrack with this way.

• cd CenterTrack/src/lib/model/networks/

• git clone https://codechina.csdn.net/mirrors/jinfagang/DCNv2_latest.git

• cd DCNv2_latest

• vim make.sh

  • remove sudo to prevent install out of current environment.
  • sudo python3 setup.py build develop -> python3 setup.py build develop

• ./make.sh

thanks!!!

[123454xiao]

I used the torch1.10.1, so I choose the version of CDNv2 is torch1.9,and I have the same issue .

like this
import DCN failed
Import DCN failed
import DCN failed
import DCN failed
Running tracking
Using tracking threshold for out threshold! 0.3
Fix size testing.
training chunk_sizes: [16, 16]
input h w: 544 960
heads {'hm': 1, 'reg': 2, 'wh': 2, 'tracking': 2, 'ltrb_amodal': 4}
weights {'hm': 1, 'reg': 1, 'wh': 0.1, 'tracking': 1, 'ltrb_amodal': 0.1}
head conv {'hm': [256], 'reg': [256], 'wh': [256], 'tracking': [256], 'ltrb_amodal': [256]}
Namespace(K=100, add_05=False, amodel_offset_weight=1, arch='dla_34', aug_rot=0, backbone='dla34', batch_size=32, chunk_sizes=[16, 16], custom_dataset_ann_path='../data/mot17/annotations/train_half.json', custom_dataset_img_path='../data/mot17/train/', data_dir='/data/xiaoyuting/CenterTrack/src/lib/../../data', dataset='custom', dataset_version='', debug=0, debug_dir='/data/xiaoyuting/CenterTrack/src/lib/../../exp/tracking/mot17_half_sc/debug', debugger_theme='white', demo='', dense_reg=1, dep_weight=1, depth_scale=1, dim_weight=1, dla_node='dcn', down_ratio=4, efficient_level=0, eval_val=False, exp_dir='/data/xiaoyuting/CenterTrack/src/lib/../../exp/tracking', exp_id='mot17_half_sc', fix_res=True, fix_short=-1, flip=0.5, flip_test=False, fp_disturb=0.1, gpus=[0, 1], gpus_str='0,1', head_conv={'hm': [256], 'reg': [256], 'wh': [256], 'tracking': [256], 'ltrb_amodal': [256]}, head_kernel=3, heads={'hm': 1, 'reg': 2, 'wh': 2, 'tracking': 2, 'ltrb_amodal': 4}, hm_disturb=0.05, hm_hp_weight=1, hm_weight=1, hp_weight=1, hungarian=False, ignore_loaded_cats=[], input_h=544, input_res=960, input_w=960, keep_res=False, kitti_split='3dop', load_model='', load_results='', lost_disturb=0.4, lr=0.000125, lr_step=[60], ltrb=False, ltrb_amodal=True, ltrb_amodal_weight=0.1, ltrb_weight=0.1, map_argoverse_id=False, master_batch_size=16, max_age=-1, max_frame_dist=3, model_output_list=False, msra_outchannel=256, neck='dlaup', new_thresh=0.3, nms=False, no_color_aug=False, no_pause=False, no_pre_img=False, non_block_test=False, not_cuda_benchmark=False, not_idaup=False, not_max_crop=False, not_prefetch_test=False, not_rand_crop=False, not_set_cuda_env=False, not_show_bbox=False, not_show_number=False, not_show_txt=False, num_classes=1, num_epochs=70, num_head_conv=1, num_iters=-1, num_layers=101, num_stacks=1, num_workers=4, nuscenes_att=False, nuscenes_att_weight=1, off_weight=1, only_show_dots=False, optim='adam', out_thresh=0.3, output_h=136, output_res=240, output_w=240, pad=31, pre_hm=True, pre_img=True, pre_thresh=0.3, print_iter=0, prior_bias=-4.6, public_det=False, qualitative=False, reg_loss='l1', reset_hm=False, resize_video=False, resume=False, reuse_hm=False, root_dir='/data/xiaoyuting/CenterTrack/src/lib/../..', rot_weight=1, rotate=0, same_aug_pre=True, save_all=False, save_dir='/data/xiaoyuting/CenterTrack/src/lib/../../exp/tracking/mot17_half_sc', save_framerate=30, save_img_suffix='', save_imgs=[], save_point=[90], save_results=False, save_video=False, scale=0, seed=317, shift=0, show_trace=False, show_track_color=False, skip_first=-1, tango_color=False, task='tracking', test=False, test_dataset='custom', test_focal_length=-1, test_scales=[1.0], track_thresh=0.3, tracking=True, tracking_weight=1, trainval=False, transpose_video=False, use_kpt_center=False, use_loaded_results=False, val_intervals=10000, velocity=False, velocity_weight=1, video_h=512, video_w=512, vis_gt_bev='', vis_thresh=0.3, weights={'hm': 1, 'reg': 1, 'wh': 0.1, 'tracking': 1, 'ltrb_amodal': 0.1}, wh_weight=0.1, zero_pre_hm=False, zero_tracking=False)
fatal: not a git repository (or any of the parent directories): .git
Traceback (most recent call last):
File "main.py", line 101, in
main(opt)
File "main.py", line 37, in main
logger = Logger(opt)
File "/data/xiaoyuting/CenterTrack/src/lib/logger.py", line 33, in init
subprocess.check_output(["git", "describe"])))
File "/home/xiaoyuting/.conda/envs/centertrack/lib/python3.8/subprocess.py", line 411, in check_output
return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
File "/home/xiaoyuting/.conda/envs/centertrack/lib/python3.8/subprocess.py", line 512, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['git', 'describe']' returned non-zero exit status 128.

[shuyu888]

RuntimeError: Error compiling objects for extension

[bryanbocao]

Try using Docker:
https://github.com/bryanbocao/CenterTrack/blob/master/readme/Docker.md
#290

Run CenterTrack using Docker

DCNv2 Compilation Issue Fixed

docker pull bryanbocao/centertrack
docker run -d --ipc=host --shm-size=16384m -it -v /:/share --gpus all --network=bridge bryanbocao/centertrack /bin/bash
docker ps -a

Check <CONTAINER_ID>:

CONTAINER ID   IMAGE                    COMMAND                  CREATED          STATUS                       PORTS                NAMES
89bb79551ccb   bryanbocao/centertrack   "/usr/local/bin/nvid…"   49 seconds ago   Up 38 seconds                6006/tcp, 8888/tcp   competent_northcutt

docker exec -it <CONTAINE_ID> /bin/bash

docker exec -it 89bb79551ccb /bin/bash

Inside the container:

cd /root/CenterTrack/src/lib/model/networks/DCNv2
python3 setup.py build develop
cd /root/CenterTrack/src/
python3 demo.py tracking,ddd --load_model ../models/nuScenes_3Dtracking.pth --dataset nuscenes --pre_hm --track_thresh 0.1 --demo ../videos/nuscenes_mini.mp4 --test_focal_length 633

The DCNv2 is built from MatthewHowe_DCNv2. Thanks MatthewHowe for the contribution.
Then you should be able to see the results.

Go to /share to transfer data between the container and your root system.