When I try to run the compatibility test for synthesis challenge, I got the following error.
Does anyone know how to solve it?
Here is the error message:
```
docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: exec: "infer": executable file not found in $PATH: unknown.
ERRO[0000] error waiting for container:
ERROR:
message: DockerRun runner failed to run MLCube.
description: Error occurred while running MLCube task (docker=docker, run_args=--gpus=all --network=none, env_args=, volumes=--volume /home/winston/.medperf/api_medperf_org/data/748b1eefd395fd782cccc6faa4bcdbbaea621f85/data:/mlcube_io0 --volume /home/winston/.medperf/api_medperf_org/cubes/b60c9c8b1b28180a59b47fb1710d243c6e83c6a2/workspace:/mlcube_io1 --volume /home/winston/.medperf/api_medperf_org/cubes/b60c9c8b1b28180a59b47fb1710d243c6e83c6a2/workspace/additional_files/weights:/mlcube_io2 --volume /home/winston/.medperf/api_medperf_org/tmp39750/2725696:/mlcube_io3, image=pytorch/pytorch:1.10.0-cuda11.3-cudnn8-runtime, task_args=['infer', '--data_path=/mlcube_io0', '--parameters_file=/mlcube_io1/parameters.yaml', '--weights=/mlcube_io2', '--output_path=/mlcube_io3']).
context: {'status': 'exited', 'code': 127, 'cmd': 'docker run --gpus=all --network=none --volume /home/winston/.medperf/api_medperf_org/data/748b1eefd395fd782cccc6faa4bcdbbaea621f85/data:/mlcube_io0 --volume /home/winston/.medperf/api_medperf_org/cubes/b60c9c8b1b28180a59b47fb1710d243c6e83c6a2/workspace:/mlcube_io1 --volume /home/winston/.medperf/api_medperf_org/cubes/b60c9c8b1b28180a59b47fb1710d243c6e83c6a2/workspace/additional_files/weights:/mlcube_io2 --volume /home/winston/.medperf/api_medperf_org/tmp39750/2725696:/mlcube_io3 pytorch/pytorch:1.10.0-cuda11.3-cudnn8-runtime infer --data_path=/mlcube_io0 --parameters_file=/mlcube_io1/parameters.yaml --weights=/mlcube_io2 --output_path=/mlcube_io3'}
? Model MLCube failed.
WARNING: Failed to premanently cleanup some files. Consider deleting '/home/winston/.medperf/.trash/39750' manually to avoid unnecessary storage.
```
Here is my config file:
```
name: missing_modality
description: mlcube for missing modality challenge
authors:
- {name: Winston}
platform:
accelerator_count: 1
docker:
# Image name
image: pytorch/pytorch:1.10.0-cuda11.3-cudnn8-runtime
# Docker build context relative to $MLCUBE_ROOT. Default is `build`.
build_context: "../project"
# Docker file name within docker build context, default is `Dockerfile`.
build_file: "Dockerfile"
gpu_args: --gpus=all
tasks:
infer:
# Computes predictions on input data
parameters:
inputs: {
data_path: ,
parameters_file: parameters.yaml,
# Feel free to include other files required for inference.
# These files MUST go inside the additional_files path.
# e.g. model weights
weights: additional_files/weights
}
outputs: {output_path: {type: directory, default: }}
```
Created by Qingqiao Hu euler_q Hi @euler_q ,
Thank you for sharing your setup! It looks like in your config file, you have specified to run a `pytorch/pytorch:1.10.0-cuda11.3-cudnn8-runtime` container rather than the one you've created. This will explain the error you received about "infer" not being found:
```
unable to start container process: exec: "infer": executable file not found in $PATH: unknown.
```
Instead of `pytorch/pytorch:1.10.0-cuda11.3-cudnn8-runtime`, please enter the name of the Docker image you have pushed up to Synapse, something like this: `docker.synapse.org//:`
Let us know if you have any questions!
CC: @hasank
Drop files to upload
Error when running the compatibility test for synthesis challenge page is loading…