Hello everyone, please help me with this problem.
I tested my docker in local and it works normally.
But when I submitted it and I got the error No *.nii.gz files found; please check whether running the Docker container locally will result in a NIfTI file within the time constraint.
I tried several times but it's still not worked.
Please help me.
Thank you.
Created by Thanh Do osfa @osfa ,
Thank you for confirming! We have made note of your final submission :) Hi @vchung,
In case you haven't seen the previous comment, I just want to remind you that we use docker.synapse.org/syn25976390/mip:15 as our final submission.
Thank you so much ^^
Best regards,
Thanh Do Hello @vchung ,
Thank you. I have no more questions.
I want to confirm my final submission for the test dataset is: docker.synapse.org/syn25976390/mip:15
Thank you for your help.
Best regards,
Thanh Do
@osfa ,
Thank you for the update; I saw that you were able to get scored submissions. I wanted to quickly follow up and see if you had additional questions/issues? Hello @vchung,
I have another question.
My submission id is 9716250.
It runs well on synapse docker but result still No *.nii.gz files found; please check whether running the Docker container locally will result in a NIfTI file within the time constraint.
After I check log.txt, it shows 0 error but this:
Start testing BraTS 2021 Testing Dataset - MIP Team
---Timing cost: 354.29836773872375 seconds ---
Thank you so much for using code. MIP Team
test.py:112: DeprecationWarning: get_data() is deprecated in favor of get_fdata(), which has a more predictable return type. To obtain get_data() behavior going forward, use numpy.asanyarray(img.dataobj).
* deprecated from version: 3.0
* Will raise as of version: 5.0
data = proxy.get_data()
/app/utils/parser.py:76: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
ret = parse(yaml.load(f))
I have fixed the time limitation. The warning on synapse docker is the same as the warning on my local PC. But on my local PC, I have the output files, on synapse, I got the error.
Please help me fix this problem.
Thank out.
@osfa ,
Thank you for your patience! The Challenge Organizers have been made aware of your particular issue, and they have agreed that we will consider your team's model for the next part of the phase (where your model will be evaluated against the 500 cases). Unfortunately however, we will not be able to evaluate your model at this time, as the 390-second time limit is already implemented into the submission system for this phase.
Please confirm whether the model from submission 9716091 is the one you would like considered under your team's name, or if not, please provide the image and tag you would like submitted instead, e.g. `docker.synapse.org/{project id}/{image name}:{tag}`.
Hi @vchung ,
I ran my model on GPU 1080 Nvidia with 8gb GPU memory. @osfa ,
Apologies for the confusion. The message received in the email is just a general message to indicate that prediction files were not generated in `/output`, either due to exceeding the time limit or other.
Also, thank you for sending the video. I will bring up your issue up to the Challenge Organizers. For full transparency, can you let me know what your GPU specs are? Dear @vchung,
I've sent you an email about how I ran my docker locally.
Please check it out.
Also, I have a question. No *.nii.gz files found issue come from input or output?
Please help me out soon because we have a little time left.
Best regards,
Thanh Do Hello @vchung ,
Sorry for the late reply.
I ran my model on my local PC and it took 295.56 seconds for two samples.
@osfa ,
Thank you for your patience. We locally ran your model of submission 9716091 on a machine with the exact specs as the submission system and received the following stats:
```sh
$ docker container inspect mip
[
{
"Id": "9cb304244d11951a806ced5b2bd7016ac9b6b99f6ac6c14e2680ca6afdc4d229",
"Created": "2021-09-20T07:14:56.652710518Z",
"Path": "bash",
"Args": [
"/app/run.sh"
],
"State": {
"Status": "exited",
"Running": false,
"Paused": false,
"Restarting": false,
"OOMKilled": false,
"Dead": false,
"Pid": 0,
"ExitCode": 0,
"Error": "",
"StartedAt": "2021-09-20T07:15:12.592191601Z",
"FinishedAt": "2021-09-20T07:22:18.141845935Z"
},
...
}
]
```
Using the `StartedAt` and `FinishedAt` values, we were able to calculate the model's execution time of one case at ~426 seconds:
```python
>>> from dateutil import parser
>>> start = parser.isoparse("2021-09-20T07:15:12.592191601Z").timestamp()
>>> end = parser.isoparse("2021-09-20T07:22:18.141845935Z").timestamp()
>>> end - start
425.549654006958
```
When you ran the model locally on your machine, how long did it take? Hi @vchung,
My submission id is 9716091.
Thank you. Hi @osfa ,
To better help you, can you let me know the ID of the submission(s) you are asking for more details on?
Drop files to upload
No *.nii.gz files found; please check whether running the Docker container locally will result in a NIfTI file within the time constaint. page is loading…