Jin Zhe

How to better do batch inference on multiple images

4

Hi there! My apologies if this is a stupid question as I am still very new to TF. I am trying to use PSP50 (pre-trained on ADE20K) for inference on...

Discrepancy on query size

1

Hi Harvey, In your paper it was stated that > "For each class, we pick k labeled instances as our support set and **16** instances for the query set for...

Cannot use C3D v1.1 for demo

3

Hi Zhengshou, Thank you very much for your work on S-CNN. I'm currently trying to run the demo using C3D v1.1 but I realized the demo code was written for...

`_dist2plane` triggers codegen Warning

2

**Describe the bug/To Reproduce** The following warning appears when I use [`Distance2PoincareHyperplanes`](https://github.com/geoopt/geoopt/blob/master/examples/hyperbolic_multiclass_classification.ipynb) as the classifier for `torchvision.models.efficientnet_v2_s`. ``` ~/miniconda3/envs/a5000/lib/python3.10/site-packages/geoopt/manifolds/stereographic/math.py:1562: UserWarning: operator() profile_node %301 : int = prim::profile_ivalue(%299) does not have...

`Trainer`'s `.init_module()` context does not initialize model on target device

1

### Bug description I refer to the documentation on https://lightning.ai/docs/pytorch/stable/advanced/model_init.html which states "you can force PyTorch to create the model directly on the target device" when using the `.init_module()` context....