mvig-sjtu / alphapose Goto Github PK
View Code? Open in Web Editor NEWReal-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Home Page: http://mvig.org/research/alphapose.html
License: Other
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Home Page: http://mvig.org/research/alphapose.html
License: Other
I met such a problem:
50%|█████████████████████████████████████████████████████████████████████████████████████████ | 2/4 [00:03<00:03, 1.75s/it]
Traceback (most recent call last):
File "demo-alpha-pose.py", line 176, in
num_boxes=demo(sess, net, im_name, xminarr,yminarr,xmaxarr,ymaxarr,results,score_file,index_file,num_boxes,inputpath, mode)
File "demo-alpha-pose.py", line 67, in demo
scores, boxes = im_detect(sess, net, im)
File "/home/yinruiying/Desktop/ring/env/AlphaPose/human-detection/tools/../lib/model/test.py", line 91, in im_detect
blobs, im_scales = _get_blobs(im,scale)
File "/home/yinruiying/Desktop/ring/env/AlphaPose/human-detection/tools/../lib/model/test.py", line 63, in _get_blobs
blobs['data'], im_scale_factors = _get_image_blob(im,scale)
File "/home/yinruiying/Desktop/ring/env/AlphaPose/human-detection/tools/../lib/model/test.py", line 35, in _get_image_blob
im_orig = im.astype(np.float32, copy=True)
AttributeError: 'NoneType' object has no attribute 'astype'
pose estimation with RMPE...
/home/yinruiying/torch/install/bin/luajit: /home/yinruiying/torch/install/share/lua/5.1/trepl/init.lua:389: module 'hdf5' not found:No LuaRocks module found for hdf5
no field package.preload['hdf5']
no file '/home/yinruiying/.luarocks/share/lua/5.1/hdf5.lua'
no file '/home/yinruiying/.luarocks/share/lua/5.1/hdf5/init.lua'
no file '/home/yinruiying/torch/install/share/lua/5.1/hdf5.lua'
no file '/home/yinruiying/torch/install/share/lua/5.1/hdf5/init.lua'
no file './hdf5.lua'
no file '/home/yinruiying/torch/install/share/luajit-2.1.0-beta1/hdf5.lua'
no file '/usr/local/share/lua/5.1/hdf5.lua'
no file '/usr/local/share/lua/5.1/hdf5/init.lua'
no file '/home/yinruiying/.luarocks/lib/lua/5.1/hdf5.so'
no file '/home/yinruiying/torch/install/lib/lua/5.1/hdf5.so'
no file '/home/yinruiying/torch/install/lib/hdf5.so'
no file './hdf5.so'
no file '/usr/local/lib/lua/5.1/hdf5.so'
no file '/usr/local/lib/lua/5.1/loadall.so'
stack traceback:
[C]: in function 'error'
/home/yinruiying/torch/install/share/lua/5.1/trepl/init.lua:389: in function 'require'
...e/yinruiying/Desktop/ring/env/AlphaPose/predict/util.lua:7: in main chunk
[C]: in function 'dofile'
main-alpha-pose.lua:7: in main chunk
[C]: in function 'dofile'
...ying/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50
/home/yinruiying/Desktop/ring/env/local/lib/python2.7/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float
to np.floating
is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/home/yinruiying/Desktop/ring/env/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/yinruiying/Desktop/ring/env/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
IOError: Unable to open file (unable to open file: name = '/home/yinruiying/Desktop/ring/env/AlphaPose/examples/results/POSE/test-pose.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
visualization...
Traceback (most recent call last):
File "json-video.py", line 63, in
with open(jsonpath) as f:
IOError: [Errno 2] No such file or directory: '/home/yinruiying/Desktop/ring/env/AlphaPose/examples/results/POSE/alpha-pose-results-forvis.json'
How can I deal with it? Thanks.
generating bbox from Faster RCNN...
Traceback (most recent call last):
File "demo-alpha-pose.py", line 22, in
from newnms.nms import soft_nms
File "/home/luoyuncen/AlphaPose/human-detection/tools/../lib/newnms/nms.py", line 3, in
from cpu_nms import cpu_nms, cpu_soft_nms
ImportError: No module named cpu_nms
pose estimation with RMPE...
when i run the cmd ./run.sh --indir examples/demo/ --outdir examples/results/ --vis
, I got error
Traceback (most recent call last): File "demo-alpha-pose.py", line 30, in <module> from tqdm import tqdm ImportError: No module named tqdm
But I have installed tqdm,I don't know what's wrong i did Thanks
When estimating the keypoints with flag '--vis', such an error sometimes happens:
"_tkinter.TclError: no display name and no $DISPLAY environment variable" which is called back from the predict/json/json-video.py
And this bug is likely related to the version of matplotlib, and for my own case, this can be fixed in method below:
before the statement at the beginning of json-video.py:
import matplotlib.pyplot as plt
insert two lines:
import matplotlib
matplotlib.use('Agg')
Hi, I noticed this edition of RMPE performanced much better than before, from 61% mentioned in ICCV paper to 72%.
However, I just checked the link of paper and found out it had not been updated yet. So, when will the updated paper be released ?
At last, congratulation for your great work .
Hi, I followed the instruction to install AlphaPose, but when I run the test demo, it comes out this error. How to solve this. Thanks.
cetc@cetc-computer:/桌面/HD/AlphaPose-master/human-detection/lib$ make clean/桌面/HD/AlphaPose-master/human-detection/lib$ make
rm -rf /.pyc
rm -rf /.so
cetc@cetc-computer:
python3 setup.py build_ext --inplace
running build_ext
skipping 'utils/bbox.c' Cython extension (up-to-date)
building 'utils.cython_bbox' extension
creating build
creating build/temp.linux-x86_64-3.6
creating build/temp.linux-x86_64-3.6/utils
{'gcc': ['-Wno-cpp', '-Wno-unused-function']}
gcc -pthread -B /home/cetc/anaconda3/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/cetc/anaconda3/lib/python3.6/site-packages/numpy/core/include -I/home/cetc/anaconda3/include/python3.6m -c utils/bbox.c -o build/temp.linux-x86_64-3.6/utils/bbox.o -Wno-cpp -Wno-unused-function
gcc -pthread -shared -B /home/cetc/anaconda3/compiler_compat -L/home/cetc/anaconda3/lib -Wl,-rpath=/home/cetc/anaconda3/lib -Wl,--no-as-needed -Wl,--sysroot=/ build/temp.linux-x86_64-3.6/utils/bbox.o -o /home/cetc/桌面/HD/AlphaPose-master/human-detection/lib/utils/cython_bbox.cpython-36m-x86_64-linux-gnu.so
skipping 'utils/nms.c' Cython extension (up-to-date)
building 'utils.cython_nms' extension
{'gcc': ['-Wno-cpp', '-Wno-unused-function']}
gcc -pthread -B /home/cetc/anaconda3/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/cetc/anaconda3/lib/python3.6/site-packages/numpy/core/include -I/home/cetc/anaconda3/include/python3.6m -c utils/nms.c -o build/temp.linux-x86_64-3.6/utils/nms.o -Wno-cpp -Wno-unused-function
gcc -pthread -shared -B /home/cetc/anaconda3/compiler_compat -L/home/cetc/anaconda3/lib -Wl,-rpath=/home/cetc/anaconda3/lib -Wl,--no-as-needed -Wl,--sysroot=/ build/temp.linux-x86_64-3.6/utils/nms.o -o /home/cetc/桌面/HD/AlphaPose-master/human-detection/lib/utils/cython_nms.cpython-36m-x86_64-linux-gnu.so
rm -rf build
cetc@cetc-computer:~/桌面/HD/AlphaPose-master$ ./run.sh --indir examples/demo/ --outdir examples/results/ --vis
0
generating bbox from Faster RCNN...
Traceback (most recent call last):
File "demo-alpha-pose.py", line 22, in
from newnms.nms import soft_nms
File "/home/cetc/桌面/HD/AlphaPose-master/human-detection/tools/../lib/newnms/nms.py", line 4, in
from cpu_nms import cpu_nms, cpu_soft_nms
ModuleNotFoundError: No module named 'cpu_nms'
pose estimation with RMPE...
./run.sh: 行 78: th: 未找到命令
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/home/cetc/anaconda3/lib/python3.6/site-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/cetc/anaconda3/lib/python3.6/site-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = '/home/cetc/桌面/HD/AlphaPose-master/examples/results/POSE/test-pose.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
visualization...
Traceback (most recent call last):
File "json-video.py", line 63, in
with open(jsonpath) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/cetc/桌面/HD/AlphaPose-master/examples/results/POSE/alpha-pose-results-forvis.json'
Hi,
Is there any flag during running to store heatmaps rather keypoints? Thanks!
您好,目前给的例子只是用了图片或者视频流作为输入,是否支持实时采集摄像头数据,然后进行处理呢?谢谢!
I've been installed tensorflow, torch, hdf5, etc... But there are still problem running.
./run.sh --indir examples/demo --outdir examples/results/ --gpu 0 --batch size 3
``0generating bbox from Faster RCNN... /usr/local/lib/python2.7/dist-packages/h5py/__init__.py:34: FutureWarning: Conversion of the second argument of issubdtype from
float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
2018-03-16 10:43:14.883830: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-03-16 10:43:15.014889: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-03-16 10:43:15.015286: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1060 6GB major: 6 minor: 1 memoryClockRate(GHz): 1.7845
pciBusID: 0000:01:00.0
totalMemory: 5.93GiB freeMemory: 5.66GiB
2018-03-16 10:43:15.015300: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:01:00.0, compute capability: 6.1)
Loaded network ../output/res152/coco_2014_train+coco_2014_valminusminival/default/res152.ckpt
/home/tiger/work/fall_detection/AlphaPose-master/./examples/demo
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:04<00:00, 1.41s/it]
pose estimation with RMPE...
MPII
/home/tiger/torch/install/bin/luajit: main-alpha-pose.lua:96: 'for' step must be a number
stack traceback:
main-alpha-pose.lua:96: in function 'loop'
main-alpha-pose.lua:176: in main chunk
[C]: in function 'dofile'
...iger/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50
/usr/local/lib/python2.7/dist-packages/h5py/init.py:34: FutureWarning: Conversion of the second argument of issubdtype from float
to np.floating
is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 271, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 101, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (/tmp/pip-nCYoKW-build/h5py/_objects.c:2840)
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (/tmp/pip-nCYoKW-build/h5py/_objects.c:2798)
File "h5py/h5f.pyx", line 78, in h5py.h5f.open (/tmp/pip-nCYoKW-build/h5py/h5f.c:2117)
IOError: Unable to open file (Unable to open file: name = '/home/tiger/work/fall_detection/alphapose-master/./examples/results/pose/test-pose.h5', errno = 2, error message = 'no such file or directory', flags = 0, o_flags = 0)`
Any suggestions?Thank you ahead
Hi, MVIG groups:
I'm quite a newer for human keypoint detection, thanks for your excellent work. I have a question, how to deal with invisible keypoints during train? And, I can't find the preprocess code for MSCOCO to make the annt.h5
file, so I'm confused.
An error occurred when I used it to test my own video,
’
convert video to images...
./run.sh: line 55: ffmpeg: command not found
generating bbox from Faster RCNN...
/usr/local/lib/python2.7/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float
to np.floating
is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
2018-03-14 00:18:30.331615: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2018-03-14 00:18:30.331682: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2018-03-14 00:18:30.331704: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
Loaded network ../output/res152/coco_2014_train+coco_2014_valminusminival/default/res152.ckpt
/home/hansheng/AlphaPose/video-tmp
0it [00:00, ?it/s]
pose estimation with RMPE...
MPII
HDF5-DIAG: Error detected in HDF5 (1.8.11) thread 140542779459456:
#000: ../../../src/H5Dio.c line 171 in H5Dread(): no output buffer
major: Invalid arguments to routine
minor: Bad value
/home/hansheng/torch/install/bin/luajit: /home/hansheng/torch/install/share/lua/5.1/hdf5/dataset.lua:78: HDF5DataSet:all() - failed reading data from [HDF5DataSet (83886081 /xmin DATASET)]
stack traceback:
[C]: in function 'error'
/home/hansheng/torch/install/share/lua/5.1/hdf5/dataset.lua:78: in function 'all'
/home/hansheng/AlphaPose/predict/util.lua:39: in function 'loadAnnotations'
main-alpha-pose.lua:27: in main chunk
[C]: in function 'dofile'
...heng/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00406670
/usr/local/lib/python2.7/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float
to np.floating
is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
parametric-pose-nms-MPII.py:104: UserWarning: loadtxt: Empty input file: "/home/hansheng/AlphaPose/examples/results/BBOX/score-proposals.txt"
scores_proposals = np.loadtxt(os.path.join(outputpath,"BBOX/score-proposals.txt"), ndmin=1)
parametric-pose-nms-MPII.py:18: UserWarning: loadtxt: Empty input file: "scores-proposals.txt"
proposal_scores = np.loadtxt("scores-proposals.txt", ndmin=1)
visualization...
0it [00:00, ?it/s]
rendering video...
./run.sh: line 96: ffmpeg: command not found
‘
I found that I haven't downloaded such h5 file when I run run.sh. Where can I download this file?
Hi,
I am wondering when the tracking part code would be released?
Also, I have a question about the tracking paper, by saying "drop low-score keypoints before generating result", are you referring to keep joints that only have a confidence higher than the threshold, e.g. keep only 5 joints of a person, or referring to if the keypoints score of one person is pretty low, the entire predicted person is ruled out.
Also, did you filter low confidence bbox first before performing tracking as the "Detect-and-Track" paper mentioned?
Many thanks.
@hjhhh3000
The log of run is shown as following:
generating bbox from Faster RCNN...
Traceback (most recent call last):
File "demo-alpha-pose.py", line 118, in
os.mkdir(args.outputpath)
OSError: [Errno 2] No such file or directory: 'examples/results/'
pose estimation with RMPE...
./run.sh: 行 78: th: 未找到命令
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/usr/lib/python2.7/dist-packages/h5py/_hl/files.py", line 272, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/usr/lib/python2.7/dist-packages/h5py/_hl/files.py", line 92, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (/build/h5py-nQFNYZ/h5py-2.6.0/h5py/_objects.c:2577)
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (/build/h5py-nQFNYZ/h5py-2.6.0/h5py/_objects.c:2536)
File "h5py/h5f.pyx", line 76, in h5py.h5f.open (/build/h5py-nQFNYZ/h5py-2.6.0/h5py/h5f.c:1811)
IOError: Unable to open file (Unable to open file: name = 'examples/results/pose/test-pose.h5', errno = 2, error message = 'no such file or directory', flags = 0, o_flags = 0)
Thanks for sharing your code publicly. When I training in my own dataset, I face the following problems.
"module 'stn' not found". I have read your paper 'RMPE: Regional Multi-Person Pose Estimation', the 'addSSTN' in file 'opts.lua' should be set true during training process.
In your 'AlphaPose/train/README.md' you said that "We finetune our model based on the pre-trained pyraNet model." Is possible to train from scratch in my own dataset?
Thanks for your replay!
I follow the steps, but when I run.sh ,it makes a mistake cannot found the file test-Pose.h5
hi,when I run this command "./run.sh --indir examples/demo/ --outdir examples/results/ --vis" ,it returns the following error,I don't know what's the 'th' command mean,please give me some advice ,thanks
the entire error information as follow:
pose estimation with RMPE...
./run.sh: line 78: th: command not found
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
IOError: Unable to open file (unable to open file: name = '/home/zzy/work/AlphaPose/examples/results/POSE/test-pose.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
visualization...
Traceback (most recent call last):
File "json-video.py", line 63, in
with open(jsonpath) as f:
IOError: [Errno 2] No such file or directory: '/home/zzy/work/AlphaPose/examples/results/POSE/alpha-pose-results-forvis.json
@YuliangXiu
Hey, I have some questions when i run the poseflow part of this repo to track pedestrians. Could you me a hand?
Globally optimal solution is obtained by the Hungarian algorithm to solve bipartite matching problem. Thus no matter what the similarity is, one node in set A will be assigned a node from set B even if the smallest similarity is negative, if there are same number of nodes in A and B, which will cause many mismatches. So I'm wondering whether a threshold is needed to select convincing matches after the line: 120 in tracker.py.
I find a margin '10 frames' is set to find the lost target. And for the lost target, the box and pose corresponding to the lastest detection are copied. However, matching points obtained by deepmatching are between successive frames. So, i think the copy operator may leads to mismatches in some cases. Am i right?
Hi, can you forecast how many fps show on GTX 1050?
您好 非常冒昧的打扰了。我是ustc的学生。貌似pose track 的数据集官网下载通道关闭,我非常急用。您能通过网盘或者邮件分享这个数据集给我一下吗
Hi, I followed the instruction to install AlphaPose, but when I run the test demo, it comes out this error. How to solve this. Thanks.
~/project/AlphaPose$ ./run.sh --indir examples/demo/ --outdir examples/results/ --vis
0
generating bbox from Faster RCNN...
Traceback (most recent call last):
File "demo-alpha-pose.py", line 22, in
from newnms.nms import soft_nms
File "/nfs/home/longwei/project/AlphaPose/human-detection/tools/../lib/newnms/nms.py", line 4, in
from gpu_nms import gpu_nms
ImportError: No module named 'gpu_nms'
pose estimation with RMPE...
./run.sh: line 78: th: command not found
_frozen_importlib:321: FutureWarning: Conversion of the second argument of issubdtype from float
to np.floating
is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type
.
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/nfs/home/longwei/anaconda2/envs/mask_rcnn_old/lib/python3.4/site-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/nfs/home/longwei/anaconda2/envs/mask_rcnn_old/lib/python3.4/site-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = '/nfs/home/longwei/project/AlphaPose/examples/results/POSE/test-pose.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
visualization...
Traceback (most recent call last):
File "json-video.py", line 63, in
with open(jsonpath) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/nfs/home/longwei/project/AlphaPose/examples/results/POSE/alpha-pose-results-forvis.json'
/home/liutl/torch7/install/bin/luajit: /home/liutl/torch7/install/share/lua/5.1/trepl/init.lua:389: module 'threads' not found:No LuaRocks module found for threads
no field package.preload['threads']
no file '/home/liutl/.luarocks/share/lua/5.1/threads.lua'
no file '/home/liutl/.luarocks/share/lua/5.1/threads/init.lua'
no file '/home/liutl/torch7/install/share/lua/5.1/threads.lua'
no file '/home/liutl/torch7/install/share/lua/5.1/threads/init.lua'
no file './threads.lua'
no file '/home/liutl/torch7/install/share/luajit-2.1.0-beta1/threads.lua'
no file '/usr/local/share/lua/5.1/threads.lua'
no file '/usr/local/share/lua/5.1/threads/init.lua'
no file '/home/wanggw/.luarocks/share/lua/5.1/threads.lua'
no file '/home/wanggw/.luarocks/share/lua/5.1/threads/init.lua'
no file '/home/liutl/.luarocks/lib/lua/5.1/threads.so'
no file '/home/liutl/torch7/install/lib/lua/5.1/threads.so'
no file './threads.so'
no file '/usr/local/lib/lua/5.1/threads.so'
no file '/usr/local/lib/lua/5.1/loadall.so'
no file '/home/wanggw/.luarocks/lib/lua/5.1/threads.so'
stack traceback:
[C]: in function 'error'
/home/liutl/torch7/install/share/lua/5.1/trepl/init.lua:389: in function 'require'
main-alpha-pose.lua:1: in main chunk
[C]: in function 'dofile'
...utl/torch7/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00406620
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
IOError: Unable to open file (unable to open file: name = '/home/wanggw/Work/AlphaPose-master/AlphaPose-master/examples/results/POSE/test-pose.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
visualization...
Traceback (most recent call last):
File "json-video.py", line 63, in
with open(jsonpath) as f:
IOError: [Errno 2] No such file or directory: '/home/wanggw/Work/AlphaPose-master/AlphaPose-master/examples/results/POSE/alpha-pose-results-forvis.json'
wanggw@liutl:~/Work/AlphaPose-master/AlphaPose-master$
Hey,in the parallel SPPE branch,how to calculate the loss between the center-located ground truth poses and the output?And how to make the center-located ground truth pose image?Is it just cropped from the origin image?
how about inference time?
I have read the paper about RMPE, in which symmetric spatial transformer network(SSTN) was used to enhance SPPE. However, i didn't find SSTN in the 'final_model.t7' when drawing the network graph using nngraph, so i wonder whether the SSTN is used in the final model?
i installed tensorflow(CPU&GPU) on python3 before, however the AlphaPose is based on python2, so i installed tensorflow1.6 with python2, and when it runs the ./run.sh,the feedback:
generating bbox from Faster RCNN... /home/ann/.local/lib/python2.7/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from
floatto
np.floatingis deprecated. In future, it will be treated as
np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
2018-04-08 16:41:40.420039: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Loaded network ../output/res152/coco_2014_train+coco_2014_valminusminival/default/res152.ckpt
/home/ann/AlphaPose/examples/demo/
0%| | 0/3 [00:00<?, ?it/s]unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
33%|███████████████ | 1/3 [00:31<01:02, 31.42s/it]unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
67%|██████████████████████████████ | 2/3 [00:59<00:29, 29.98s/it]unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
unknown error
100%|█████████████████████████████████████████████| 3/3 [01:28<00:00, 29.57s/it]
pose estimation with RMPE...
/home/ann/torch/install/bin/lua: /home/ann/torch/install/share/lua/5.2/trepl/init.lua:389: /home/ann/.luarocks/share/lua/5.2/hdf5/ffi.lua:56: expected align(#) on line 579
stack traceback:
[C]: in function 'error'
/home/ann/torch/install/share/lua/5.2/trepl/init.lua:389: in function 'require'
/home/ann/AlphaPose/predict/util.lua:7: in main chunk
[C]: in function 'dofile'
/home/ann/torch/install/share/lua/5.2/paths/init.lua:84: in function 'dofile'
main-alpha-pose.lua:7: in main chunk
[C]: in function 'dofile'
.../ann/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: in ?
/home/ann/.local/lib/python2.7/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float
to np.floating
is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/home/ann/.local/lib/python2.7/site-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/ann/.local/lib/python2.7/site-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
IOError: Unable to open file (unable to open file: name = '/home/ann/AlphaPose/examples/results/POSE/test-pose.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
visualization...
Traceback (most recent call last):
File "json-video.py", line 63, in
with open(jsonpath) as f:
IOError: [Errno 2] No such file or directory: '/home/ann/AlphaPose/examples/results/POSE/alpha-pose-results-forvis.json'maybe there are some problems with tf but i have no idea about these instructions. what else module do i must install? and the tf version:
tf.version
'1.6.0'`
please help me, thank u
Hello, when I turn on the --sep
flag, all results are still saved in one file alpha-pose-results.json
.
There only exists a single .json file in folder sep-json
.
./run.sh --indir ../data --outdir ../alphapose --vis --sep --gpu 0,1 --batch 5
Can U help me to separate the results? Thank you ahead~
Hello,
First of all thank you for sharing your implementation which seems really promising ! I tried to install following the Readme instructions but when I try to download the data from posetrack using :
cat .tar | tar -xvf - -i
I run into an error ..
It seems that some images are corrupted and so the decompression fails.
Did you have similar problems during decompression of the dataset ? If so how did you solve the problem ?
Finally, is it necessary to download the whole posetrack dataset or only specific batch ? Would it be possible to add those informations in the Readme ?
Thank you again for sharing your work,
Cheers
Using a GTX 1080 with 8 GB RAM what would you expect human detection inference performance to be?
I made some changes to demo-alpha-pose.py related to TensorFlow session config. I removed allow_growth=True
and replaced it with per_process_gpu_memory_fraction=4
and then I run 3 docker instances. This has been an easy way in the past for me to maximize the GPU utilization. I'm able to keep the GPU at 90%+ utilization based on watching watch -n 1 nvidia-smi
I did NOT adjust any of the config variables and I removed writing to HDF5 files and instead push to MongoDB via RabbitMQ.
I'm only getting around 1.8-2 images (3264x1836 resolution which gets scaled down as cfg.TEST.MAX_SIZE=1000
) per second though. Is that expected? I believe I was getting closer to 3-4 images per second using this card while running inference on Mask RCNN (Matterports version) I'll test using my 1080 TI's in a few days to see the performance bump with more CUDA cores and memory.
Hello, I installed torch as #10 mentioned but still can't run the demo. The result looks like:
`XX::~/AlphaPose$ ./run.sh --indir examples/demo/ --outdir examples/results/ --gpu 0,1,2,3 --batch 5
0
generating bbox from Faster RCNN...
2018-02-14 15:50:23.741917: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2018-02-14 15:50:23.741941: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2018-02-14 15:50:23.741946: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2018-02-14 15:50:23.741950: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2018-02-14 15:50:23.741954: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2018-02-14 15:50:23.976259: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties:
name: TITAN X (Pascal)
major: 6 minor: 1 memoryClockRate (GHz) 1.531
pciBusID 0000:06:00.0
Total memory: 11.90GiB
Free memory: 11.29GiB
2018-02-14 15:50:24.133633: W tensorflow/stream_executor/cuda/cuda_driver.cc:523] A non-primary context 0x3fe2bc0 exists before initializing the StreamExecutor. We haven't verified StreamExecutor works with that.
2018-02-14 15:50:24.134315: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 1 with properties:
name: TITAN X (Pascal)
major: 6 minor: 1 memoryClockRate (GHz) 1.531
pciBusID 0000:0b:00.0
Total memory: 11.90GiB
Free memory: 11.75GiB
2018-02-14 15:50:24.135003: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0 1
2018-02-14 15:50:24.135014: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0: Y Y
2018-02-14 15:50:24.135018: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 1: Y Y
2018-02-14 15:50:24.135032: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: TITAN X (Pascal), pci bus id: 0000:06:00.0)
2018-02-14 15:50:24.135039: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:1) -> (device: 1, name: TITAN X (Pascal), pci bus id: 0000:0b:00.0)
Loaded network ../output/res152/coco_2014_train+coco_2014_valminusminival/default/res152.ckpt
/home/icl/AlphaPose/examples/demo/
100%|████████████████████████████████████████████████████████| 3/3 [00:03<00:00, 1.18s/it]
pose estimation with RMPE...
/home/icl/torch/install/bin/lua: /home/icl/torch/install/share/lua/5.2/trepl/init.lua:389: /home/icl/torch/install/share/lua/5.2/trepl/init.lua:389: module 'bit' not found:No LuaRocks module found for bit
no field package.preload['bit']
no file '/home/icl/.luarocks/share/lua/5.2/bit.lua'
no file '/home/icl/.luarocks/share/lua/5.2/bit/init.lua'
no file '/home/icl/torch/install/share/lua/5.2/bit.lua'
no file '/home/icl/torch/install/share/lua/5.2/bit/init.lua'
no file '/home/icl/.luarocks/share/lua/5.1/bit.lua'
no file '/home/icl/.luarocks/share/lua/5.1/bit/init.lua'
no file '/home/icl/torch/install/share/lua/5.1/bit.lua'
no file '/home/icl/torch/install/share/lua/5.1/bit/init.lua'
no file './bit.lua'
no file '/home/icl/torch/install/share/luajit-2.1.0-beta1/bit.lua'
no file '/usr/local/share/lua/5.1/bit.lua'
no file '/usr/local/share/lua/5.1/bit/init.lua'
no file '/home/icl/.luarocks/lib/lua/5.2/bit.so'
no file '/home/icl/torch/install/lib/lua/5.2/bit.so'
no file '/home/icl/torch/install/lib/bit.so'
no file '/home/icl/.luarocks/lib/lua/5.1/bit.so'
no file '/home/icl/torch/install/lib/lua/5.1/bit.so'
no file './bit.so'
no file '/usr/local/lib/lua/5.1/bit.so'
no file '/usr/local/lib/lua/5.1/loadall.so'
stack traceback:
[C]: in function 'error'
/home/icl/torch/install/share/lua/5.2/trepl/init.lua:389: in function 'require'
/home/icl/AlphaPose/predict/util.lua:7: in main chunk
[C]: in function 'dofile'
/home/icl/torch/install/share/lua/5.2/paths/init.lua:84: in function 'dofile'
main-alpha-pose.lua:7: in main chunk
[C]: in function 'dofile'
.../icl/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: in ?
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 272, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 92, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (/tmp/pip-4rPeHA-build/h5py/_objects.c:2684)
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (/tmp/pip-4rPeHA-build/h5py/_objects.c:2642)
File "h5py/h5f.pyx", line 76, in h5py.h5f.open (/tmp/pip-4rPeHA-build/h5py/h5f.c:1930)
IOError: Unable to open file (Unable to open file: name = '/home/icl/alphapose/examples/results/pose/test-pose.h5', errno = 2, error message = 'no such file or directory', flags = 0, o_flags = 0)
`
I try to google it. But there is no module named "bit"... Module "bit32" have been installed with lua2.
So.. Could anyone give any suggestion?
Many thanks~
Hey, @YuliangXiu
This is a very good job.
But when I tried to read the codes in poseflow , i find some bugs there.
I think the method 'cal_bbox_iou' is not correct. for example, when there is no overlap between boxA and boxB, the iou get by this function is wrong.
Thus, I think it may be modified like this:
def cal_bbox_iou(boxA, boxB): xA = max(boxA[0], boxB[0]) yA = max(boxA[2], boxB[2]) xB = min(boxA[1], boxB[1]) yB = min(boxA[3], boxB[3]) if xA < xB and yA < yB: interArea = (xB - xA + 1) * (yB - yA + 1) boxAArea = (boxA[1] - boxA[0] + 1) * (boxA[3] - boxA[2] + 1) boxBArea = (boxB[1] - boxB[0] + 1) * (boxB[3] - boxB[2] + 1) iou = interArea / float(boxAArea + boxBArea - interArea+0.00001) else: iou=0. return iou
Is there something I ignoring?
I think I have installed the package correctly! I am working on Ubuntu 16.04, TF-gpu v1.4. I literally follow the instruction of installation. But when I ran the demo:
./run.sh --indir examples/demo/ --outdir examples/results/ --vis
I found error message here when the code tried to create a local save:
/home/ruoyuli/torch/install/bin/luajit: /home/ruoyuli/.luarocks/share/lua/5.1/hdf5/file.lua:10: HDF5File.__init() requires a fileID - perhaps you want HDF5File.create()?
stack traceback:
[C]: in function 'assert'
/home/ruoyuli/.luarocks/share/lua/5.1/hdf5/file.lua:10: in function '__init'
/home/ruoyuli/.luarocks/share/lua/5.1/torch/init.lua:91: in function </home/ruoyuli/.luarocks/share/lua/5.1/torch/init.lua:87>
[C]: in function 'open'
/home/ruoyuli/AlphaPose/predict/util.lua:34: in function 'loadAnnotations'
main-alpha-pose.lua:27: in main chunk
[C]: in function 'dofile'
...yuli/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50
/home/ruoyuli/.conda/envs/tf_p2.7/lib/python2.7/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype fromfloat
tonp.floating
is deprecated. In future, it will be treated asnp.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/home/ruoyuli/.conda/envs/tf_p2.7/lib/python2.7/site-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/ruoyuli/.conda/envs/tf_p2.7/lib/python2.7/site-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
IOError: Unable to open file (unable to open file: name = '/home/ruoyuli/AlphaPose/examples/results/POSE/test-pose.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
visualization...
Traceback (most recent call last):
File "json-video.py", line 63, in
with open(jsonpath) as f:
IOError: [Errno 2] No such file or directory: '/home/ruoyuli/AlphaPose/examples/results/POSE/alpha-pose-results-forvis.json'
Any suggestions ? Thank you ahead!
In your code, has a word " require 'stn' ", but I can't found this file.
Thank you!
Hi, I met such a problem:
Loaded network ../output/res152/coco_2014_train+coco_2014_valminusminival/default/res152.ckpt
/home/yinruiying/Desktop/ring/env/AlphaPose/examples/demo/
50%|█████████████████████████████████████████████████████████████▌ | 2/4 [00:03<00:03, 1.53s/it]
Traceback (most recent call last):
File "demo-alpha-pose.py", line 176, in
num_boxes=demo(sess, net, im_name, xminarr,yminarr,xmaxarr,ymaxarr,results,score_file,index_file,num_boxes,inputpath, mode)
File "demo-alpha-pose.py", line 67, in demo
scores, boxes = im_detect(sess, net, im)
File "/home/yinruiying/Desktop/ring/env/AlphaPose/human-detection/tools/../lib/model/test.py", line 91, in im_detect
blobs, im_scales = _get_blobs(im,scale)
File "/home/yinruiying/Desktop/ring/env/AlphaPose/human-detection/tools/../lib/model/test.py", line 63, in _get_blobs
blobs['data'], im_scale_factors = _get_image_blob(im,scale)
File "/home/yinruiying/Desktop/ring/env/AlphaPose/human-detection/tools/../lib/model/test.py", line 35, in _get_image_blob
im_orig = im.astype(np.float32, copy=True)
AttributeError: 'NoneType' object has no attribute 'astype'
pose estimation with RMPE...
MPII
/home/yinruiying/torch/install/bin/luajit: /home/yinruiying/torch/install/share/lua/5.1/hdf5/group.lua:327: HDF5Group:read() - no such child 'xmin' for [HDF5Group 33554432 /]
stack traceback:
[C]: in function 'error'
/home/yinruiying/torch/install/share/lua/5.1/hdf5/group.lua:327: in function 'read'
...e/yinruiying/Desktop/ring/env/AlphaPose/predict/util.lua:39: in function 'loadAnnotations'
main-alpha-pose.lua:27: in main chunk
[C]: in function 'dofile'
...ying/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50
/home/yinruiying/Desktop/ring/env/local/lib/python2.7/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float
to np.floating
is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/home/yinruiying/Desktop/ring/env/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/yinruiying/Desktop/ring/env/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
IOError: Unable to open file (unable to open file: name = '/home/yinruiying/Desktop/ring/env/AlphaPose/examples/results/POSE/test-pose.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
Then how can I settle it? Thanks...
Unable to open file: name = '/home/zlc/network/alphapose/examples/results/pose/test-pose.h5
IOError: [Errno 2] No such file or directory: '/home/zlc/Network/AlphaPose/examples/results/POSE/alpha-pose-results-forvis.json'
when i run './run.sh --indir examples/demo/ --outdir examples/results/ --vis', i don't know where can i find these two files.
I tried to run the demo and got the following errors:
generating bbox from Faster RCNN...
2018-02-27 20:27:32.093717: I tensorflow/core/common_runtime/gpu/gpu_device.cc:938] Found device 0 with properties:
name: Tesla K80
major: 3 minor: 7 memoryClockRate (GHz) 0.8235
pciBusID 0000:06:00.0
Total memory: 11.20GiB
Free memory: 11.13GiB
2018-02-27 20:27:32.093935: I tensorflow/core/common_runtime/gpu/gpu_device.cc:959] DMA: 0
2018-02-27 20:27:32.093947: I tensorflow/core/common_runtime/gpu/gpu_device.cc:969] 0: Y
2018-02-27 20:27:32.093960: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1028] Creating TensorFlow device (/gpu:0) -> (device: 0, name: Tesla K80, pci bus id: 0000:06:00.0)
Loaded network ../output/res152/coco_2014_train+coco_2014_valminusminival/default/res152.ckpt
/home/xxx/github/AlphaPose/examples/demo/
It seems like a version compatability problem.
However, I am not familiar with LUA.
Could you kindly give me some advice?
this file(alpha-pose-results-forvis.json) can not find
I' have followed the tutorial steps to test the demo but i'm getting the following error:
$ ./run.sh --indir examples/demo/ --outdir examples/results/ --vis
0
generating bbox from Faster RCNN...
/usr/local/lib/python2.7/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
2018-02-05 20:54:09.837963: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
Loaded network ../output/res152/coco_2014_train+coco_2014_valminusminival/default/res152.ckpt
/home/daniel/Documentos/AlphaPose/examples/demo/
100%|████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:48<00:00, 16.12s/it]
pose estimation with RMPE...
MPII
[======================================== 69/69 ======================================>] Tot: 6s757ms | Step: 99ms
----------Finished----------
/usr/local/lib/python2.7/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
visualization...
0%| | 0/3 [00:00<?, ?it/s]
Traceback (most recent call last):
File "json-video.py", line 66, in <module>
display_pose(inputpath, outputpath, imgname)
File "json-video.py", line 53, in display_pose
fig.savefig(os.path.join(outputpath,'RENDER',imgname.split('/')[-1]),pad_inches = 0.0, bbox_inches=extent, dpi=12.91)
File "/home/daniel/.local/lib/python2.7/site-packages/matplotlib/figure.py", line 1834, in savefig
self.canvas.print_figure(fname, **kwargs)
File "/home/daniel/.local/lib/python2.7/site-packages/matplotlib/backend_bases.py", line 2267, in print_figure
**kwargs)
File "/home/daniel/.local/lib/python2.7/site-packages/matplotlib/backends/backend_agg.py", line 584, in print_jpg
return background.save(filename_or_obj, format='jpeg', **options)
File "/usr/lib/python2.7/dist-packages/PIL/Image.py", line 1675, in save
save_handler(self, fp, filename)
File "/usr/lib/python2.7/dist-packages/PIL/JpegImagePlugin.py", line 708, in _save
ImageFile._save(im, fp, [("jpeg", (0, 0)+im.size, 0, rawmode)], bufsize)
File "/usr/lib/python2.7/dist-packages/PIL/ImageFile.py", line 480, in _save
e = Image._getencoder(im.mode, e, a, im.encoderconfig)
File "/usr/lib/python2.7/dist-packages/PIL/Image.py", line 431, in _getencoder
return encoder(mode, *args + extra)
TypeError: integer argument expected, got float
Sorry but I don't know very much about python its libs, does anyone know what's going on?
Environment:ubuntu 16.04;cuda 9.0.176;cuDNN 7.0.5;TensorFlow 1.6.0(gpu).
Reference to #10 #3,
I've been installed torch,lucrocks,hdf5,etc...But there are still problems running...
name@name-All-Series:~/AlphaPose$ ./run.sh --indir examples/demo/ --outdir examples/results/ --vis
0
generating bbox from Faster RCNN...
/usr/local/lib/python2.7/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype fromfloat
tonp.floating
is deprecated. In future, it will be treated asnp.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
2018-03-06 17:32:48.947257: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2018-03-06 17:32:49.022229: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:898] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-03-06 17:32:49.022485: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1212] Found device 0 with properties:
name: GeForce GTX 750 major: 5 minor: 2 memoryClockRate(GHz): 1.188
pciBusID: 0000:01:00.0
totalMemory: 1.95GiB freeMemory: 1.64GiB
2018-03-06 17:32:49.022502: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1312] Adding visible gpu devices: 0
2018-03-06 17:32:49.244052: I tensorflow/core/common_runtime/gpu/gpu_device.cc:993] Creating TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 1403 MB memory) -> physical GPU (device: 0, name: GeForce GTX 750, pci bus id: 0000:01:00.0, compute capability: 5.2)
Loaded network ../output/res152/coco_2014_train+coco_2014_valminusminival/default/res152.ckpt
/home/name/AlphaPose/examples/demo/
0%| | 0/3 [00:00<?, ?it/s]2018-03-06 17:32:55.388581: W tensorflow/core/common_runtime/bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.05GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2018-03-06 17:32:55.500633: W tensorflow/core/common_runtime/bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.05GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2018-03-06 17:32:56.432382: W tensorflow/core/common_runtime/bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to allocate 922.50MiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
67%|██████████████████████████████ | 2/3 [00:07<00:03, 3.52s/it]2018-03-06 17:33:01.331154: W tensorflow/core/common_runtime/bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.05GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2018-03-06 17:33:01.411505: W tensorflow/core/common_runtime/bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.05GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2018-03-06 17:33:01.501123: W tensorflow/core/common_runtime/bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.07GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2018-03-06 17:33:02.435389: W tensorflow/core/common_runtime/bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.05GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2018-03-06 17:33:02.543607: W tensorflow/core/common_runtime/bfc_allocator.cc:219] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.05GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
100%|█████████████████████████████████████████████| 3/3 [00:10<00:00, 3.45s/it]
pose estimation with RMPE...
/home/name/torch/install/bin/lua: /home/name/torch/install/share/lua/5.2/trepl/init.lua:389: /home/name/torch/install/share/lua/5.2/hdf5/ffi.lua:56: expected align(#) on line 579
stack traceback:
[C]: in function 'error'
/home/name/torch/install/share/lua/5.2/trepl/init.lua:389: in function 'require'
/home/name/AlphaPose/predict/util.lua:7: in main chunk
[C]: in function 'dofile'
/home/name/torch/install/share/lua/5.2/paths/init.lua:84: in function 'dofile'
main-alpha-pose.lua:7: in main chunk
[C]: in function 'dofile'
...oyer/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: in ?
/usr/local/lib/python2.7/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype fromfloat
tonp.floating
is deprecated. In future, it will be treated asnp.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 269, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 78, in h5py.h5f.open
IOError: Unable to open file (unable to open file: name = '/home/name/AlphaPose/examples/results/POSE/test-pose.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)
visualization...
Traceback (most recent call last):
File "json-video.py", line 63, in
with open(jsonpath) as f:
IOError: [Errno 2] No such file or directory: '/home/name/AlphaPose/examples/results/POSE/alpha-pose-results-forvis.json'
So,how can I solve it?
I have tried several pictures in the demo without any problem . But when I want to use the demo on larger data, the program goes down and the error info:
0it [00:00, ?it/s]
pose estimation with RMPE...
MPII
/home/shiyx/torch/install/bin/luajit: bad argument #2 to '?' (out of bounds
at/home/shiyx/torch/pkg/torch/lib/TH/generic/THStorage.c:202)
Hi, could you tell me the detailed name of the data used in PoseFlow/deepmatching.py, I donn't know which the data you used that satisfied the condition of "len(a.split("/")) == 9". When I debug the code, the value of vidnames is empty.
I find that I can run AlphaPose
normally without PoseFlow
component. What is the relationship between AlphaPose and PoseFlow ?
Hi , I follow each steps and got the following error when I run the run.sh command as show on guide , pls help, thanks!
generating bbox from Faster RCNN...
Traceback (most recent call last):
File "demo-alpha-pose.py", line 31, in
from nets.vgg16 import vgg16
File "/home/chikiuso/Downloads/AlphaPose/human-detection/tools/../lib/nets/vgg16.py", line 11, in
import tensorflow.contrib.slim as slim
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/init.py", line 31, in
from tensorflow.contrib import factorization
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/factorization/init.py", line 24, in
from tensorflow.contrib.factorization.python.ops.gmm import *
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/factorization/python/ops/gmm.py", line 27, in
from tensorflow.contrib.learn.python.learn.estimators import estimator
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/learn/init.py", line 88, in
from tensorflow.contrib.learn.python.learn import *
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/learn/python/init.py", line 23, in
from tensorflow.contrib.learn.python.learn import *
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/init.py", line 25, in
from tensorflow.contrib.learn.python.learn import estimators
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/init.py", line 297, in
from tensorflow.contrib.learn.python.learn.estimators.dnn import DNNClassifier
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/dnn.py", line 30, in
from tensorflow.contrib.learn.python.learn.estimators import dnn_linear_combined
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/dnn_linear_combined.py", line 31, in
from tensorflow.contrib.learn.python.learn.estimators import estimator
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 49, in
from tensorflow.contrib.learn.python.learn.learn_io import data_feeder
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_io/init.py", line 21, in
from tensorflow.contrib.learn.python.learn.learn_io.dask_io import extract_dask_data
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_io/dask_io.py", line 26, in
import dask.dataframe as dd
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/dask/dataframe/init.py", line 3, in
from .core import (DataFrame, Series, Index, _Frame, map_partitions,
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/dask/dataframe/core.py", line 40, in
pd.core.computation.expressions.set_use_numexpr(False)
AttributeError: 'module' object has no attribute 'expressions'
pose estimation with RMPE...
/home/chikiuso/torch/install/bin/lua: .../chikiuso/torch/install/share/lua/5.1/trepl/init.lua:389: ...me/chikiuso/torch/install/share/lua/5.1/hdf5/ffi.lua:56: expected align(#) on line 687
stack traceback:
[C]: in function 'error'
.../chikiuso/torch/install/share/lua/5.1/trepl/init.lua:389: in function 'require'
/home/chikiuso/Downloads/AlphaPose/predict/util.lua:7: in main chunk
[C]: in function 'dofile'
.../chikiuso/torch/install/share/lua/5.1/paths/init.lua:84: in function 'dofile'
main-alpha-pose.lua:7: in main chunk
[C]: in function 'dofile'
.../torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: ?
./run.sh: line 79: 15096 Segmentation fault (core dumped) CUDA_VISIBLE_DEVICES=${GPU_ID} th main-alpha-pose.lua predict ${INPUT_PATH} ${OUTPUT_PATH} ${GPU_NUM} ${BATCH_SIZE} ${DATASET}
/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/h5py/init.py:34: FutureWarning: Conversion of the second argument of issubdtype from float
to np.floating
is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
Traceback (most recent call last):
File "parametric-pose-nms-MPII.py", line 256, in
get_result_json(args)
File "parametric-pose-nms-MPII.py", line 243, in get_result_json
test_parametric_pose_NMS_json(delta1, delta2, mu, gamma,args.outputpath)
File "parametric-pose-nms-MPII.py", line 99, in test_parametric_pose_NMS_json
h5file = h5py.File(os.path.join(outputpath,"POSE/test-pose.h5"), 'r')
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/h5py/_hl/files.py", line 271, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/home/chikiuso/.conda/envs/py27/lib/python2.7/site-packages/h5py/_hl/files.py", line 101, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (/feedstock_root/build_artefacts/h5py_1491364442174/work/h5py-2.7.0/h5py/_objects.c:2846)
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (/feedstock_root/build_artefacts/h5py_1491364442174/work/h5py-2.7.0/h5py/_objects.c:2804)
File "h5py/h5f.pyx", line 78, in h5py.h5f.open (/feedstock_root/build_artefacts/h5py_1491364442174/work/h5py-2.7.0/h5py/h5f.c:2123)
IOError: Unable to open file (Unable to open file: name = '/home/chikiuso/downloads/alphapose/examples/results/pose/test-pose.h5', errno = 2, error message = 'no such file or directory', flags = 0, o_flags = 0)
visualization...
mkdir: cannot create directory ‘/home/chikiuso/Downloads/AlphaPose/examples/results//RENDER’: No such file or directory
Traceback (most recent call last):
File "json-video.py", line 63, in
with open(jsonpath) as f:
IOError: [Errno 2] No such file or directory: '/home/chikiuso/Downloads/AlphaPose/examples/results/POSE/alpha-pose-results-forvis.json'
There are proposal_scores = np.loadtxt("scores-proposals.txt")
in parametric-pose-nms-MPII.py and parametric-pose-nms-COCO.py.
But when there is only one number in scores-proposals.txt - it means there is only one person in pic,
proposal_scores[i]
may be wrong, because proposal_scores.shape
will be ().
So I change the code to
proposal_scores = np.loadtxt("scores-proposals.txt", ndmin=1)
I test it in centos6, python2.7, numpy 1.14
Error message when do make under /AlphaPose/human-detection/lib/newnms
python setup_linux.py build_ext --inplace
Traceback (most recent call last):
File "setup_linux.py", line 56, in <module>
CUDA = locate_cuda()
File "setup_linux.py", line 51, in locate_cuda
for k, v in cudaconfig.iteritems():
AttributeError: 'dict' object has no attribute 'iteritems'
Makefile:2: recipe for target 'all' failed
make: *** [all] Error 1
Is it because cuda is not installed correctly? Any suggestion ?
How many fps can the whole algorithm achieve when run end-to-end(including the human detector part)?
Can AlphaPose run in real time?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.