Aditya Oke

Results 48 issues of Aditya Oke

Closes #6499 I think ready for a initial round of review. Will love to understand a bit more and then continue. I will mostly to wrap up this before the...

module: models
new feature
cla signed

As discussed in #6457 ## The current problem We do not restrict the reduction mode in losses. There are only three cases possible, ["none", "mean", "sum"]. If the user passes...

enhancement
help wanted
module: ops
good first issue

### 🚀 The feature Currently we do ``` self.mlp = MLP(dim, [int(dim * mlp_ratio), dim], activation_layer=nn.GELU, inplace=None, dropout=dropout) ``` But according to original implementation it is https://github.com/microsoft/Swin-Transformer/blob/afeb877fba1139dfbc186276983af2abb02c2196/models/swin_transformer.py#L197 ``` def __init__(self,...

### 🚀 The feature The original paper describes a few more configurations based on swin Transformer. 1. Swin Large: Simply a large model of swin transformer, needs a few config...

enhancement
module: models

### 🚀 The feature Followup to #6323 Addition of Dice Loss to torchvision. ### Motivation, pitch Mainly Dice loss is used for semantic segmentation. I want to understand the technical...

module: ops
new feature

### 🚀 The feature The main Idea is to port the SwinTransformer3d model from torchmulitmodal to torchvision. Need to keep in mind the nuances and code structure of torchvision https://github.com/facebookresearch/multimodal/blob/main/torchmultimodal/modules/encoders/swin_transformer_3d_encoder.py...

1. Describe your new request in detail So the thick mode of connecting to Oracle Database supports Kerberos External Authentication. While it's not supported in Thin mode. This makes it...

enhancement

### Clear and concise description of the problem A list of few new features that can make Code Generator super awesome 1. Side by side comparison of pytorch vs ignite...

enhancement
hacktoberfest