Closed GoGoPen closed 1 year ago
Hi @GoGoPen
Did you get model(you installed) in model list window? If you can't see your model, refer to "https://github.com/openvinotoolkit/cvat/issues/2245" Bye
Hi @GoGoPen
Did you get model(you installed) in model list window? If you can't see your model, refer to "#2245" Bye
The issue you mentioned is not related to mine. The first docker command I wrote already included serverless function. I could find the models installed are shown in the Nuclio with "Running" status. But the inference failed.
@GoGoPen Hi, could you also attach the logs from the cvat container?
@GoGoPen Hi, could you also attach the logs from the cvat container?
Thank you very much for your reply and help. Here are all the logs of all container from CVAT. For nginx:stable-alpine , it only gives empty log.
cvat_elastic.txt cvat_elasticsearch
cvat_kibana.txt cvat_kibana
cvat_logstash.txt cvat_logstash
cvat_postgres.txt postgres:10-alpine
cvat_quay.txt quay.io/nuclio/dashboard:1.4.8-amd64
cvat_redis.txt redis:4.0-alpine
cvat_server.txt cvat/server
cvat_ui.txt cvat/ui
nginx.txt nginx:stable-alpine
cvat_tf.txt cvat/tf.faster_rcnn_inception_v2_coco:latest
@GoGoPen , thanks for the report.
Just some thoughts and observation:
cvat_tf.txt
I can see that the function is up and running but it has not invoked by a reason (no logs about that).cvat_server.txt
I see that the server tries to call a function but it gets 500 error by a reason.cvat_quay.txt
I see that we have two functions: dextr and faster. First one isn't healthy but faster is fine. When we try to call it, CVAT gets I/O timeout.A couple of questions:
@GoGoPen , thanks for the report.
Just some thoughts and observation:
- From
cvat_tf.txt
I can see that the function is up and running but it has not invoked by a reason (no logs about that).- From
cvat_server.txt
I see that the server tries to call a function but it gets 500 error by a reason.- From
cvat_quay.txt
I see that we have two functions: dextr and faster. First one isn't healthy but faster is fine. When we try to call it, CVAT gets I/O timeout.20.10.09 08:43:18.781 �[37m.api/function_invocations�[0m �[33m(W)�[0m Failed to invoke function {"err": "Failed to send HTTP request", "errVerbose": "\nError - Post \"http://172.17.0.1:33783\": dial tcp 172.17.0.1:33783: i/o timeout\n /nuclio/pkg/platform/abstract/invoker.go:119\n\nCall stack:\nFailed to send HTTP request\n /nuclio/pkg/platform/abstract/invoker.go:119\nFailed to send HTTP request", "errCauses": [{"error": "Post \"http://172.17.0.1:33783\": dial tcp 172.17.0.1:33783: i/o timeout"}]} 20.10.09 08:43:18.782 �[37m dashboard.server�[0m �[32m(D)�[0m Handled request {"requestMethod": "POST", "requestPath": "/api/function_invocations", "requestHeaders": {"Accept":["*/*"],"Accept-Encoding":["gzip, deflate"],"Connection":["close"],"Content-Length":["2325689"],"Content-Type":["application/json"],"User-Agent":["python-requests/2.24.0"],"X-Nuclio-Function-Name":["tf.faster_rcnn_inception_v2_coco"],"X-Nuclio-Function-Namespace":["nuclio"],"X-Nuclio-Log-Level":[""],"X-Nuclio-Path":["/"],"X-Nuclio-Project-Name":["cvat"],"X-Nuclio-Target":["tf.faster_rcnn_inception_v2_coco"]}, "requestBody": "{\"image\": \"/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAIBAQEBAQIBAQECAgICAgQDAgICAgUEBAMEBgUGBgYFBgYGBwkIBgcJBwYGCAsICQoKCgoKBggLDAsKDAkKCgr/2wBDAQICAgICAgUDAwUKBwYHCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgoKCgr/wAARCAhwDwADASIAAhEBAxEB/
A couple of questions:
- What OS do you use?
- Did automatic annotation work for you in the past?
- Please try these steps: https://github.com/openvinotoolkit/cvat/blob/develop/CONTRIBUTING.md#dl-models-as-serverless-functions and report your results
- Please use nuctl 1.4.18 for your experiments (for now). The best version is 1.5.1 because it contains a couple of fixes for CVAT but I have not tested it yet.
What OS do you use? I am using Ubuntu 18.04.
Did automatic annotation work for you in the past? I have started to use CVAT recently (Oct-1) . When I first use CVAT, it is not working for me already.
Please try these steps: https://github.com/openvinotoolkit/cvat/blob/develop/CONTRIBUTING.md#dl-models-as-serverless-functions and report your results
I used nuctl-1.4.18 as suggested to build to annotation models. Both examples from installation were built properly and showed "Running" Status in the nuclio.
Then I tried to use the DEXRT segmentation annotation tools. It gives
Interaction error occured
Error: Request failed with status code 500. "500 Server Error: Internal Server Error for url: http://nuclio:8070/api/function_invocations".
I have also tried to use Yolo V3 TF, it gives
Error: Inference status for the task 5 is failed. requests.exceptions.HTTPError: 500 Server Error: Internal Server Error for url: http://nuclio:8070/api/function_invocations
cvat_server_log.txt cvat_ui_log.txt dashboard_log.txt
nuctl get function
NAMESPACE | NAME | PROJECT | STATE | NODE PORT | REPLICAS
nuclio | deploy | cvat | ready | 32769 | 1/1
nuclio | openvino.dextr | cvat | ready | 32768 | 1/1
Thank you very much.
Hi, I'm having the same issue when using matterport's Mask RCNN and f-BRS, although I don't have Mask RCNN deployed now. Interestingly, DEXTR causes no error whatsoever.
When using f-BRS, the following error prompts:
Interaction error occured
Error: Request failed with status code 500.
"500 Server Error: Internal Server Error for url: http://nuclio:8070/api/function_invocations".
I'm using Ubuntu 20.04 distro in WSL2.
Some info below:
docker_logs_ps.txt nuctl_get_functions.txt nuctl_version.txt docker_logs_cvat.txt docker_logs_cvat_db.txt docker_logs_cvat_proxy.txt docker_logs_cvat_redis.txt docker_logs_cvat_ui.txt docker_logs_nuclio-nuclio-openvino_dextr.txt docker_logs_nuclio-nuclio-pth_saic-vul_fbrs.txt
@borgarpa did you manage to solve it for f-BRS , i am having the exact same problem
I will close the issue as outdated. Please, reopen if still relevant.
I am encountering the problem in the automatics annotation tools.
I initialized the CVAT with the following command
Then, I have used nuctl-1.4.17-linux-amd64 and nuctl-1.1.37-linux-amd64 to build the automatic annotation tool. For example,
It is properly built and running in nuclio. However, when I try to run the inference.
The following error message showed in the CVAT,
Here are the relevant informations.
nuctl get functions
Log of the cvat/openvino.dextr:latest (5a0c2e4f3ca0)
Thank you very much for your help.