Docker environment using mediapipe pip package >= 0.10.8 loops indefinitely in create_from_options

[raksac]

OS Platform and Distribution

Linux Ubuntu 20.04 kernel version 5.15.0-91-generic x86_64

Compiler version

gcc 9.4.0

Programming Language and version

Python 3.8.10

Installed using virtualenv? pip? Conda?(if python)

pip

MediaPipe version

0.10.8

Bazel version

N/A

XCode and Tulsi versions (if iOS)

N/A

Android SDK and NDK versions (if android)

N/A

Android AAR (if android)

None

OpenCV version (if running on desktop)

4.2.0

Describe the problem

Running python script in a docker environment fails to complete. HandLandmarker.create_from_options(...) does not complete (line 11) in the code line below never completes. Signals are disabled, using SIGINT does not break out to the python shell.

Using mediapipe pip package 0.10.7, the script runs to completion as expected..

The system has a NVIDIA RTX 4000 GPU card, usign CPU delegate does not make a difference either

Complete Logs

(Pdb) p options
HandLandmarkerOptions(base_options=BaseOptions(model_asset_path='/home/ubuntu/src/hand_landmark/models/hand_landmarker.task', model_asset_buffer=None, delegate=None), running_mode=<VisionTaskRunningMode.IMAGE: 'IMAGE'>, num_hands=2, min_hand_detection_confidence=0.5, min_hand_presence_confidence=0.5, min_tracking_confidence=0.5, result_callback=None)
(Pdb) l
  1  	# STEP 1: Import the necessary modules.
  2  	import mediapipe as mp
  3  	from mediapipe.tasks import python
  4  	from mediapipe.tasks.python import vision
  5
  6  	# STEP 2: Create an HandLandmarker object.
  7  	base_options = python.BaseOptions(model_asset_path='/home/ubuntu/src/hand_landmark/models/hand_landmarker.task')
  8  	options = vision.HandLandmarkerOptions(base_options=base_options,
  9  	                                       num_hands=2)
 10  	print("INIT")
 11  ->	detector = vision.HandLandmarker.create_from_options(options)
 12
 13
 14  	print("SUCCESS")
(Pdb) n

ubuntu@ubuntu:~$ docker info
Client: Docker Engine - Community
 Version:    24.0.7
 Context:    default
 Debug Mode: false
 Plugins:
  buildx: Docker Buildx (Docker Inc.)
    Version:  v0.11.2
    Path:     /usr/libexec/docker/cli-plugins/docker-buildx
  compose: Docker Compose (Docker Inc.)
    Version:  v2.21.0
    Path:     /usr/libexec/docker/cli-plugins/docker-compose

Server:
 Containers: 6
  Running: 6
  Paused: 0
  Stopped: 0
 Images: 15
 Server Version: 24.0.7
 Storage Driver: overlay2
  Backing Filesystem: extfs
  Supports d_type: true
  Using metacopy: false
  Native Overlay Diff: true
  userxattr: false
 Logging Driver: json-file
 Cgroup Driver: cgroupfs
 Cgroup Version: 1
 Plugins:
  Volume: local
  Network: bridge host ipvlan macvlan null overlay
  Log: awslogs fluentd gcplogs gelf journald json-file local logentries splunk syslog
 Swarm: inactive
 Runtimes: runc io.containerd.runc.v2 nvidia
 Default Runtime: runc
 Init Binary: docker-init
 containerd version: 61f9fd88f79f081d64d6fa3bb1a0dc71ec870523
 runc version: v1.1.9-0-gccaecfc
 init version: de40ad0
 Security Options:
  apparmor
  seccomp
   Profile: builtin
 Kernel Version: 5.15.0-91-generic
 Operating System: Ubuntu 20.04.6 LTS
 OSType: linux
 Architecture: x86_64
 CPUs: 20
 Total Memory: 31.06GiB
 Name: ubuntu
 ID: ab9fe0ee-3b64-49ae-92fb-58ba415dea20
 Docker Root Dir: /var/lib/docker
 Debug Mode: false
 Experimental: false
 Insecure Registries:
  127.0.0.0/8
 Live Restore Enabled: false

ubuntu@ubuntu:~$ nvidia-smi
Sun Jan 14 22:42:14 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 545.23.08              Driver Version: 545.23.08    CUDA Version: 12.3     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA RTX 4000 SFF Ada ...    On  | 00000000:01:00.0  On |                  Off |
| 30%   35C    P8               9W /  70W |    434MiB / 20475MiB |      6%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
+---------------------------------------------------------------------------------------+