Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

tmp for response #13

Open
fychao opened this issue Mar 15, 2018 · 1 comment
Open

tmp for response #13

fychao opened this issue Mar 15, 2018 · 1 comment

Comments

@fychao
Copy link
Owner

fychao commented Mar 15, 2018

In inRange function prepare.py Line: 91, it compares timestamps from each image file, located in ./cctv_imgs/$CCTV_CODE, and converted speed timestamp, which is provided from extracted xml.gz file in ./cctv_imgs/speed/. If difference between image and speed timestamps is within range 0-60, this function will return an tuple (point, tm) and back to Line: 136.

So if your server time is not synchronized with an up-to-date ntpdate server, time convert function will not be accurate and cause mis-match condition, so Line: 139 would have no image/speed-pairs to do.

@fychao
Copy link
Owner Author

fychao commented Mar 15, 2018

command lines

   76  w3m "https://drive.google.com/uc?export=download&confirm=NSrC&id=1c7woFGnUlsdYvAyZ6SLR0rNyqEt4y18q"
   77  ls
   78  tar jxvf cctv_imgs.tbz
   79  ls
   80  ./prepare.py -t

output

(test) fychao@ubuntu:~/functionality-scenario-test-A-2018$ ./prepare.py -t
Using TensorFlow backend.
INFO:root:Preparing data for vdid: nfbVD-N1-N-89.990-M-LOOP
INFO:root:Scanning image files in directory: ./cctv_imgs/nfbCCTV-N1-N-90.01-M
INFO:root:Found image files: 53369
Loading Speed: 100%|############################| 10/10 [00:13<00:00,  1.35s/it]
Find Images: 100%|#####################| 53369/53369 [00:01<00:00, 47829.19it/s]
Mapping Speed: 100%|#################| 53369/53369 [00:00<00:00, 2019795.09it/s]
Make DataFrame: 100%|##########################| 10/10 [00:00<00:00, 985.90it/s]
Image Count in DataFrame
count       4
unique      4
top       152
freq        1
Name: image_count, dtype: int64
Mapping X&y: 100%|################################| 4/4 [00:01<00:00,  2.19it/s]
INFO:root:       --== dimensions ==--
X dim:(12, 30, 120, 176, 1), Y dim:(12,)
Speed(y) distributions:
 90.0     9
100.0    3
dtype: int64
Saving Sample: 100%|###########################| 12/12 [00:00<00:00, 229.75it/s]

file system layout

(bench_int_serv) root@ca67b9fa31c4:~/github/functionality-scenario-test-A-2018# ls -al
total 3725120
drwxrwxr-x 5 root root       4096 Mar 15 16:19 .
drwxrwxr-x 3 root root       4096 Mar 15 09:37 ..
drwxrwxr-x 8 root root       4096 Mar 15 09:37 .git
-rw-rw-r-- 1 root root      35147 Mar 15 09:37 LICENSE
-rw-rw-r-- 1 root root      16006 Mar 15 09:37 README.md
drwxrwxr-x 4 root root       4096 Mar  9 07:30 cctv_imgs
-rw-rw-r-- 1 root root 3814213631 Mar 15 09:38 cctv_imgs.tbz
-rw-rw-r-- 1 root root     184826 Mar 15 09:37 cctvid-vd-dest-cctv_url.csv
drwxrwxr-x 3 root root       4096 Mar 15 16:18 datasets
-rwxrwxr-x 1 root root       9402 Mar 15 09:37 feed.py
-rwxrwxr-x 1 root root      10217 Mar 15 09:37 prepare.py
-rw-rw-r-- 1 root root       1154 Mar 15 09:37 requirements.txt
-rwxrwxr-x 1 root root      11078 Mar 15 09:37 train.py
(bench_int_serv) root@ca67b9fa31c4:~/github/functionality-scenario-test-A-2018# tree -d
.
|-- cctv_imgs
|   |-- nfbCCTV-N1-N-90.01-M
|   `-- speed
`-- datasets
    `-- nfbCCTV-N1-N-90.01-M

5 directories

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant