Thien Tran
Thien Tran
## Thoughts - segmentation head (semantic and instance) - instance segmentation requires some kind of pooling? - human pose head - tracker.py -> (outside model). include BYTE algo. can work...
### System Info NA ### Who can help? @sgugger ### Information - [ ] The official example scripts - [ ] My own modified scripts ### Tasks - [ ]...
I think the outer shortcut connection is unnecessary for RRDB. There is already a shortcut connection for Dense blocks, thus the original input is already propagated through the dense blocks....
# What does this PR do? Fixes #25307 - Add field `attention_mask` to Wav2Vec2BaseModelOutput - Return updated attention mask for Wav2VecModel, Data2VecAudioModel, HubertModel, SEWModel, SEWDModel, WavLMModel, Wav2Vec2ConformerModel, UniSpeechModel, UniSpeechSatModel -...
In chapter 5.3. The scattering PDF, when we integrate over the hemisphere, it is written that $pScatter(\theta_o
Class `ConvLoRA` currently only works for Conv2d. By inspecting the shape of `B @ A`, which is (out_channels // groups * kernel_size, in_channels * kernel_size), we can see that it...
## 🚀 Feature Add other input formats for users' convenience when using Object Detector in Kornia. Some suggestions - Local image file path - Online url - numpy.ndarray (may be...
### 🐛 Describe the bug ```python import torch from torchaudio.transforms import TimeMasking, FrequencyMasking x = torch.randn(80, 100) FrequencyMasking(10)(x) # this works TimeMasking(10)(x) # this doesn't ``` Error message ``` File...
### 🚀 The feature [TimeStretch](https://pytorch.org/audio/stable/generated/torchaudio.transforms.TimeStretch.html) is not in SpecAugment. It should be Time Warping instead. Time Warping does not change the spectrogram shape, but "warp" the content. I want to...
## 📚 Documentation **Description** As per title. There is no documentation on T5 model although it exists https://pytorch.org/text/stable/models.html