runing error #1
Comments
|
please see the updated readme |
hi again and thanks for response
|
|
may be you need a GPU, the code doesn't support cpu |
|
did you use amd or nvidia gpu ? and which model?
…On Mon, Sep 17, 2018 at 2:40 AM Mhttx ***@***.***> wrote:
may be you need a GPU, the code don't support cpu
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#1 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AZb7B3ZVyudBTHZE1hCSk6OmKu-8rIlFks5ub0POgaJpZM4WWnG5>
.
|
|
nvidia gtx1070, tensorflow-gpu |
|
ok, thanks and good luck.
…On Mon, Sep 17, 2018 at 2:51 AM Mhttx ***@***.***> wrote:
nvidia gtx1070, tensorflow-gpu
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#1 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AZb7B_Y1K3qH9_nO4hLqc7nKhumz_Xd-ks5ub0aAgaJpZM4WWnG5>
.
|
|
hi again and Sorry i got bothered again
i find that if i convert image shape from NCHW to NHWC to can run this code
successfully but i dont know how to do it can you help me?
i also read this link and could not understand how to change your code to
run it for me.
https://stackoverflow.com/questions/37689423/convert-between-nhwc-and-nchw-in-tensorflow
thanks.
On Mon, Sep 17, 2018 at 3:09 AM Mohamad Shadfar <[email protected]>
wrote:
… ok, thanks and good luck.
On Mon, Sep 17, 2018 at 2:51 AM Mhttx ***@***.***> wrote:
> nvidia gtx1070, tensorflow-gpu
>
> —
> You are receiving this because you authored the thread.
> Reply to this email directly, view it on GitHub
> <#1 (comment)>,
> or mute the thread
> <https://github.com/notifications/unsubscribe-auth/AZb7B_Y1K3qH9_nO4hLqc7nKhumz_Xd-ks5ub0aAgaJpZM4WWnG5>
> .
>
|
|
you can try input image in NHWC format and set data_format = 'channels_last' here line 97 in master.py |
|
hi mohi@mohi:~/Multi-Camera-Object-Tracking-via-Transferring-Representation-to-Top-View-master$ python3 master.py |
|
sorry for the bug, i updated the line 498~504 in resnet.py |
|
hi it work .thanks
how can i save a matrix that name is for example (0_id) and track the
person (0_id) who go through cameras respectively and result save in matrix
like following :
0_id = [0,1,3,2] and each element in that array is the way that person with
0_id pass through the cameras which are in different places .
i mean the person with 0_id first detect in camera 0 then detect and
recognize in camera 1 then detect and recognize in camera 3 then detect and
recognize in camera2 .
?
…On Mon, Sep 17, 2018 at 10:12 PM Mhttx ***@***.***> wrote:
sorry for the bug, i updated the line 498~504 in resnet.py
<https://github.com/Mhttx2016/Multi-Camera-Object-Tracking-via-Transferring-Representation-to-Top-View/blob/14d4303779fb331db22f911301b54b9c06c5a751/box2vec/resnet.py#L498>
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#1 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AZb7Bw_avyk6CnWGFHQFA0ieCki7zIOxks5ucFaQgaJpZM4WWnG5>
.
|
|
and how can i increace the number of cameras?
On Tue, Sep 18, 2018 at 5:54 AM Mohamad Shadfar <[email protected]>
wrote:
… hi it work .thanks
how can i save a matrix that name is for example (0_id) and track the
person (0_id) who go through cameras respectively and result save in matrix
like following :
0_id = [0,1,3,2] and each element in that array is the way that person
with 0_id pass through the cameras which are in different places .
i mean the person with 0_id first detect in camera 0 then detect and
recognize in camera 1 then detect and recognize in camera 3 then detect and
recognize in camera2 .
?
On Mon, Sep 17, 2018 at 10:12 PM Mhttx ***@***.***> wrote:
> sorry for the bug, i updated the line 498~504 in resnet.py
> <https://github.com/Mhttx2016/Multi-Camera-Object-Tracking-via-Transferring-Representation-to-Top-View/blob/14d4303779fb331db22f911301b54b9c06c5a751/box2vec/resnet.py#L498>
>
> —
> You are receiving this because you authored the thread.
> Reply to this email directly, view it on GitHub
> <#1 (comment)>,
> or mute the thread
> <https://github.com/notifications/unsubscribe-auth/AZb7Bw_avyk6CnWGFHQFA0ieCki7zIOxks5ucFaQgaJpZM4WWnG5>
> .
>
|
|
Hi how can I increase the number of camera?and how much?
…On 11:21AM, Mon, Sep 17, 2018 Mhttx ***@***.***> wrote:
nvidia gtx1070, tensorflow-gpu
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#1 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AZb7B_Y1K3qH9_nO4hLqc7nKhumz_Xd-ks5ub0aAgaJpZM4WWnG5>
.
|
|
Hi currentUrl E:\Multi-Camera-Object-Tracking-via-Transferring-Representation-to-Top-View-master help me to solve this issue. |
|
Please set data_format=None simply it will work on GPU or CPU. |
|
hi when i try master.py i got this error, anyone can help me? |
|
|
|
hey @leijuzi , i had the same output when run the program . |
|
Downgrade your numpy to 1.16.3 or 1.16.2 or 1.16.1 |
|
Have you got the data (for which permission is required) ?
…On Tue, Oct 15, 2019 at 10:36 AM Nakhonsoft ***@***.***> wrote:
how to fix error like this?
help me please!
WARNING:tensorflow:From
C:\Users\Adasoft.conda\envs\tracker\lib\site-packages\tensorflow\python\training\saver.py:1276:
checkpoint_exists (from tensorflow.python.training.checkpoint_management)
is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
Load weights from box2vec\model\model-86000 for box_to_vect! frame_id: 100 frame_id:
101 frame_id: 102 frame_id: 103 frame_id: 104 frame_id: 105 frame_id: 106 frame_id:
107 frame_id: 108
frame_id: 109
Traceback (most recent call last):
File "master.py", line 284, in
demo(save=True)
File "master.py", line 213, in demo
embedding = get_embedding(boxes, frames, box_to_vect, sess)
File "master.py", line 68, in get_embedding
bbox_batch[:, 0] = bbox_batch[:, 0] / frames[0].shape[1]
AttributeError: 'NoneType' object has no attribute 'shape'
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#1>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ALVOZX2EOV6J7Y4RQAA2QBTQOVD5FANCNFSM4FS2OG4Q>
.
|
|
you can also replace this line with the following https://github.com/Mhttx2016/Multi-Camera-Object-Tracking-via-Transferring-Representation-to-Top-View/blob/14d4303779fb331db22f911301b54b9c06c5a751/master.py#L195
|
Instead of downgrading numpy, just modify: np.load(detection_file, allow_pickle=True) in line 26. |
hi ...
when i run the code i got this following error :
currentUrl
currentUrl /home/mohi/Multi-Camera-Object-Tracking-via-Transferring-Representation-to-Top-View-master/box2vec
parentUrl /home/mohi/Multi-Camera-Object-Tracking-via-Transferring-Representation-to-Top-View-master
video_files:
['data/train/lab/4p-c0.avi', 'data/train/lab/4p-c1.avi', 'data/train/lab/4p-c2.avi', 'data/train/lab/4p-c3.avi']
detection_files:
['data/train/lab/4p-c0.pickle', 'data/train/lab/4p-c1.pickle', 'data/train/lab/4p-c2.pickle', 'data/train/lab/4p-c3.pickle']
Traceback (most recent call last):
File "master.py", line 284, in
demo(save=True)
File "master.py", line 188, in demo
caps, detections, video_length = get_caps_and_pickles(video_files, detection_files)
File "master.py", line 26, in get_caps_and_pickles
detections.append(np.load(detection_file))
File "/home/mohi/.local/lib/python3.6/site-packages/numpy/lib/npyio.py", line 384, in load
fid = open(file, "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'data/train/lab/4p-c0.pickle'
help to solve this issue thanks.
The text was updated successfully, but these errors were encountered: