How to create the optimal alternative GCP instance for proteinfer.

[yonesora56]

I am terribly sorry to ask such a basic question, but I would like to ask you about creating a GCP instance.

I attempted to utilize proteinfer in the CLI by following the instructions in the README to create an instance. However, I encountered the below error.

gcloud compute instances create proteinfer-gpu \
--machine-type n1-standard-8 \
--zone us-west1-b \
--accelerator type=nvidia-tesla-v100,count=1 \
--image-family ubuntu-2004-lts \
--image-project ubuntu-os-cloud \
--maintenance-policy TERMINATE \
--boot-disk-size 250

ERROR

ERROR: (gcloud.compute.instances.create) Could not fetch resource:
---
code: ZONE_RESOURCE_POOL_EXHAUSTED
errorDetails:
- help:
    links:
    - description: Troubleshooting documentation
      url: https://cloud.google.com/compute/docs/resource-error
- localizedMessage:
    locale: en-US
    message: A n1-standard-8 VM instance is currently unavailable in the us-west1-b
      zone. Alternatively, you can try your request again with a different VM hardware
      configuration or at a later time. For more information, see the troubleshooting
      documentation.
- errorInfo:
    domain: compute.googleapis.com
    metadatas:
      attachment: ''
      vmType: n1-standard-8
      zone: us-west1-b
      zonesAvailable: ''
    reason: resource_availability
message: The zone 'projects/proteinfer/zones/us-west1-b' does not have enough
  resources available to fulfill the request.  Try a different zone, or try again
  later.

Are there any alternative parameters that would work best for using Proteinfer, such as machine type, zones, accelerators, etc.?

[gioodm]

I am having the same problem, did you find any solutions?

[piroyon]

The CLI version of proteinfer can be executed even without GCP.
NVIDIA GPU and python3.7 are required.
I was able to run proteinfer on a G4dn instance of AWS EC2. The nvidia gpu environment is as follows

$ nvidia-smi 
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 530.41.03              Driver Version: 530.41.03    CUDA Version: 12.1     |
|-----------------------------------------+----------------------+----------------------+
| 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  Tesla T4                        Off| 00000000:00:1E.0 Off |                    0 |
| N/A   26C    P8               14W /  70W|      2MiB / 15360MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+                                                                               

proteinfer uses Tensorflow1 so python must be 3.7.