Qi Liu

1. lib/network/senet_pytorch and lib/network/ncnet_pytorch are empty. lacks the backbones for imagenet. 2. torch.nn.modules.module.ModuleAttributeError: 'Sequential' object has no attribute 'cn'. It seems that the code base lacks the channel correlation module....

Error: Kernel size can't be greater than actual input size

1

in inference, if I choose audios with small size (e.g. fold10/7913-3-3-0.wav, fold10/7913-3-1-0.wav), the error will occur: Kernel size can't be greater than actual input size How shall I fix the...

module 'torch' has no attribute '_TensorBase'

1

in ur utils/array_tool.py, you use t._TensorBase but when I run the code, it turns wrong and pops up: AttributeError: module 'torch' has no attribute '_TensorBase'

can't convert CUDA tensor to numpy

3

there is a problem in line 248 of trainer.py: meter.add(loss_d[key]) TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first. how to solve...

the dataset of this repo is NYU_V2, but if I want to use SUN-RGBD instead, shall I just change the imgs from depth and raw depth folders?

No file named 'indicator/solo_pairs.txt'

1

Line #54 in Discriminative-Sounding-Objects-Localization/music-exp/data/cut_audios.py