lama

lama copied to clipboard

forward_front: ValueError: not enough values to unpack (expected 2, got 1)

3

Hi,first thx for ur excellent work! when I use celebA lama-deep model to predict with 'refine=True', there always a problem : File "/DATA/jupyter/personal/project/cover_diff/lama/saicinpainting/evaluation/refinement.py", line 128, in _infer z1,z2 = forward_front(masked_image)...

lucDoom

AssertionError: Unpadded size is required for the refinement

1

AssertionError: Unpadded size is required for the refinement

A913440

Suggestions requested for training a LAMA model on higher resolution data

2

Currently all LAMA models have been trained on 256x256 crops of 512x512 images. I would like to understand what changes should be made to train a LAMA model on a...

rachit221195

Prediction with refinement error

3

When trying refinement option with celeba small masks model: [2023-09-03 09:44:32,915][__main__][CRITICAL] - Prediction failed due to not enough values to unpack (expected 2, got 1): Traceback (most recent call last):...

MacM2Pro

predict, ValueError:not enough values to unpack (expected 2, got 1)

1

First of all, thank you for your great work! I want to use a lama-fourier model trained on the places dataset to make predictions on my own dataset, the command...

leayz-888

Hello, I'd like to inquire about why the training process remains stuck at this screen after I initiate the training using the command “python3 bin/train.py -cn lama-fourier location=my_dataset data.batch_size=10”.

Chi-Mz

I uploaed lama-cleaner-iOS. https://github.com/john-rocky/lama-cleaner-iOS Thank you for the great model.

john-rocky

ValueError: `Dataloader` returned 0 length. Please make sure that it returns at least 1 batch

19

Can you help me ?

wmrenr

training dataset example

1

any dataset example?

crapthings

Artifacts show up on outputs when using sharp edge mask

2

Hi! When I programmatically generate masks for inpainting (with very sharp edges, no blur or smooth transitioning between mask/background) I get slightly worse outputs (visible artifacts) but when I apply...

karolzak