Unable to map memory? Nvidia Feforce RTX 2060
Posted: Fri Apr 23, 2021 2:55 pm
I'm trying to run training with Input A and B, each containing maybe 100-200 images.
Even chose "Trainer: lightweight" and "Batch Size: 1"
I have a Nvidia Feforce RTX 2060 with 6gb
And i receive this error:
Code: Select all
Loading...
Setting Faceswap backend to AMD
04/23/2021 16:43:39 INFO Log level set to: INFO
04/23/2021 16:43:40 INFO Setting up for PlaidML
04/23/2021 16:43:40 INFO Using GPU(s): ['NVIDIA Corporation - GeForce RTX 2060 (experimental)', 'NVIDIA Corporation - GeForce RTX 2060 (supported)']
04/23/2021 16:43:40 INFO Successfully set up for PlaidML
04/23/2021 16:43:41 INFO Model A Directory: 'C:\Users\vinko\Videos\Faceswap Project #1\Faces Extracted A' (293 images)
04/23/2021 16:43:41 INFO Model B Directory: 'C:\Users\vinko\Videos\Faceswap Project #1\Faces Extracted B' (174 images)
04/23/2021 16:43:41 WARNING At least one of your input folders contains fewer than 250 images. Results are likely to be poor.
04/23/2021 16:43:41 WARNING You need to provide a significant number of images to successfully train a Neural Network. Aim for between 500 - 5000 images per side.
04/23/2021 16:43:41 INFO Training data directory: C:\Users\vinko\Videos\Faceswap Project #1\Model AB
04/23/2021 16:43:41 INFO ===================================================
04/23/2021 16:43:41 INFO Starting
04/23/2021 16:43:41 INFO Press 'Stop' to save and quit
04/23/2021 16:43:41 INFO ===================================================
04/23/2021 16:43:42 INFO Loading data, this may take a while...
04/23/2021 16:43:42 INFO Loading Model from Lightweight plugin...
Using plaidml.keras.backend backend.
04/23/2021 16:43:43 INFO No existing state file found. Generating.
04/23/2021 16:43:43 INFO Opening device "opencl_nvidia_geforce_rtx_2060.0"
04/23/2021 16:43:43 INFO Loading Trainer from Original plugin...
Unable to map memory: CL_MEM_OBJECT_ALLOCATION_FAILURE04/23/2021 16:43:44 ERROR Unable to map memory: CL_MEM_OBJECT_ALLOCATION_FAILURE
04/23/2021 16:43:44 CRITICAL Error caught! Exiting...
04/23/2021 16:43:44 ERROR Caught exception in thread: '_training_0'
04/23/2021 16:43:44 ERROR You do not have enough GPU memory available to train the selected model at the selected settings. You can try a number of things:
04/23/2021 16:43:44 ERROR 1) Close any other application that is using your GPU (web browsers are particularly bad for this).
04/23/2021 16:43:44 ERROR 2) Lower the batchsize (the amount of images fed into the model each iteration).
04/23/2021 16:43:44 ERROR 3) Use a more lightweight model, or select the model's 'LowMem' option (in config) if it has one.
Process exited.