Magicst6

> While applying ResNet are you passing labels? > If yes then for every patch the label has been included? As there are of 49 patches per image. > So...

> from torch.utils.ffi import _wrap_function > from _ext import lib as _lib, ffi as _ffi > > These two pieces of code always report errors, what can I do, can...

Hello Mr. Chan, - Can you please share quant. results (Table 2) for the BasicVSR trained on exactly the same settings as RealBasicVSR (dataset degradation model, number of iterations)? -...

I am also having the same issue with 2 GPUs (48 Gb Tesla). It is fascinating that the author could train the model on Titan Xp ?! Even though I...

Problem solved! The issue was in torchsummary, where I put 256x256 images. Anyway, the problem is in NLB, which consumes too much memory because of large matrix multiplication: `f =...

> > Problem solved! The issue was in torchsummary, where I put 256x256 images. Anyway, the problem is in NLB, which consumes too much memory because of large matrix multiplication:...

Hi @WoBuChiTang! Have you fixed that error? Did suggestions (reducing the learning rate and using AdamW) from Jason help? If yes, can you please share hyperparameters that you have used?

I also encountered the same problem. @kyhyk did you achieve the same performance on validation set?

Hello @jasonppy ! Now there are 3 of us =) Can you comment why Voicecraft did not use the Encodec pretrained for a general scenario?

Hi @rishikksh20! Thank you for sharing insights for multilanguage scenario! Have you tried training from scratch and compare with finetuned one? Also how do you assess (metrics) the quality of...