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

I Can't calculate the eao #13

Open
DOCNULL opened this issue Sep 15, 2019 · 15 comments
Open

I Can't calculate the eao #13

DOCNULL opened this issue Sep 15, 2019 · 15 comments

Comments

@DOCNULL
Copy link

DOCNULL commented Sep 15, 2019

No description provided.

@DOCNULL
Copy link
Author

DOCNULL commented Sep 15, 2019

since I don't know what the needed format for the out put bbox, and I use the format from the GT_bbox TXT but still get nothing.

@DOCNULL
Copy link
Author

DOCNULL commented Sep 15, 2019

(tensorflow) G:\Tracking\pysot-toolkit-master>python bin/eval.py --dataset_dir G:\Tracking\pysot-toolkit-master\VOT2016 --dataset VOT2016 --tracker_result_dir G:\Tracking\pysot-toolkit-master\some.txt --trackers MAX
loading VOT2016: 100%|██████████████████████████████████████| 1/1 [00:00<00:00, 30.35it/s, graduate]
eval ar: 100%|████████████████████████████████████████████████████████| 1/1 [00:01<00:00, 1.07s/it]
eval eao: 0%| | 0/1 [00:00<?, ?it/s]multiprocessing.pool.RemoteTraceback:
"""
Traceback (most recent call last):
File "C:\Users\1\AppData\Local\conda\conda\envs\tensorflow\lib\multiprocessing\pool.py", line 119, in worker
result = (True, func(*args, **kwds))
File ".\pysot\evaluation\eao_benchmark.py", line 43, in eval
eao = self._calculate_eao(tracker_name, self.tags)
File ".\pysot\evaluation\eao_benchmark.py", line 111, in _calculate_eao
max_len = max([len(x) for x in all_overlaps])
ValueError: max() arg is an empty sequence
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "bin/eval.py", line 147, in
trackers), desc='eval eao', total=len(trackers), ncols=100):
File "C:\Users\1\AppData\Local\conda\conda\envs\tensorflow\lib\site-packages\tqdm_tqdm.py", line 1005, in iter
for obj in iterable:
File "C:\Users\1\AppData\Local\conda\conda\envs\tensorflow\lib\multiprocessing\pool.py", line 731, in next
raise value
ValueError: max() arg is an empty sequence

@Puzzle0612
Copy link

Did you find any solutions? I met the same problem as well...

@Dtappledoghuati
Copy link

Did you find any solutions? I met the same problem as well...

I also encountered the same problem.

@harindermashiana
Copy link

Same problem. Please resolve this issue soon, if anybody has found the solution do explain.

@Dtappledoghuati
Copy link

Set the “results” folder in the folder, the “OTB100” folder in the “results” folder, and the result folders that are run out of various trackers in the “OTB100” folder, such as SiamMask, SiamRPN, etc. , put the results into it.

@harindermashiana
Copy link

Set the “results” folder in the folder, the “OTB100” folder in the “results” folder, and the result folders that are run out of various trackers in the “OTB100” folder, such as SiamMask, SiamRPN, etc. , put the results into it.

The problem is with the VOT dataset not OTB and can you be more clear about directories you mentioned?

@harindermashiana
Copy link

harindermashiana commented Oct 28, 2019

I think there is problem with my results directory, which looks like as follows:
This results directory is placed inside the model directory

results
 |VOT2018
   | model
     | result1.txt
     | result2.txt
     ...

@harindermashiana
Copy link

I think there is problem with my results directory, which looks like as follows:
This results directory is placed inside the model directory

results
 |VOT2018
   | model
     | result1.txt
     | result2.txt
     ...

Solved it. There is supposed to be a directory named baseline in model directory. The .txt files should be in baseline directory.

@Singapore-mor
Copy link

Set the “results” folder in the folder, the “OTB100” folder in the “results” folder, and the result folders that are run out of various trackers in the “OTB100” folder, such as SiamMask, SiamRPN, etc. , put the results into it.

Can you draw the success_precision picture?

@Dtappledoghuati
Copy link

Dtappledoghuati commented Nov 6, 2019 via email

@MaMingyueIT
Copy link

download the Raw results in http://www.votchallenge.net/vot2018/results.html
Set --tracker_result_dir to the decompressed address of the above package
Then worked!!

@zhangyuran-gg
Copy link

设置目录了,仍然没有解决

@zhangyuran-gg
Copy link

设置目录后就解决了吗

@bobo-liang
Copy link

请问该问题有解决吗

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

8 participants