Vadim Kantorov

Swin-L pretrained checkpoints used

1

Hi @dbofseuofhust, @vaesl! Can't find in the code the URLs to the ImageNet-pretrained Swin-L. Which checkpoints did you use? https://github.com/microsoft/Swin-Transformer provides many different ones. Could you please publish a config...

Hi! Would you have any guidance / code on reproducing the decoder attention visualization? (fig. 4 from A.3). I'm worried of making some padding-related mistakes while working with `sampled_locations` Thanks!

We are trying to reproduce some of your results on the newly available Russian speech-to-text dataset: https://github.com/snakers4/open_stt . The key questions are model capacity, model depth, compute requirements for training....

https://github.com/mravanelli/SincNet/blob/master/dnn_models.py#L106-L108 : ```python #self.window_ = torch.hamming_window(self.kernel_size) n_lin=torch.linspace(0, (self.kernel_size/2)-1, steps=int((self.kernel_size/2))) # computing only half of the window self.window_=0.54-0.46*torch.cos(2*math.pi*n_lin/self.kernel_size); ``` Could it be replaced instead by `self.window_ = torch.hamming_window(kernel_size)[:kernel_size // 2]`? Or...

Dynamic index update

3

Hi! Do I understand correctly that MRPT does not currently support dynamic index update / rebalancing?

torchaudio.load to optionally accept a target sample_rate (and maybe backend=)

17

### 🚀 The feature E.g. OPUS format supports resampling as part of reading. There is no standard and uniform way of setting sample rate at decoding. E.g. sox sets it...

[dicscussion] Batched CPU/GPU audio decoding / encoding

8

### 🚀 The feature GPU audio decoding at least for some codecs is useful for wider usage of compressed audio for training ASR models. Maybe some neural codecs (I think...

Allow arbitrary-sized images by dynamic masking: upstream changes from Swin-Transformer-Object-Detection / SOLQ

2

Hi! To combine Swin transformer backbone with Deformable DETR detector, [SOLQ](https://github.com/megvii-research/SOLQ/blob/main/models/swin_transformer.py) did some changes to `swin_transformer.py` that allow to compute the padding mask dynamically and allow for arbitrary-sized images in...

FreeSOLO code release?

1

Hi! Looking forward to code release of FreeSOLO :) Thanks!

Split files

6

Could you please publish the COCO percent splits that you used? Providing the seed may not be enough or very convenient given that numpy.random.choice generation algorithm may depend on version...