Thomas Ressler-Antal
Thomas Ressler-Antal
I try to train data2vec on music data (the FMA dataset). I've made some modifications to the feature extractor ConvNet (I've made it a small ResNet essentially), and reduced the...
Hey, I am not sure, if this is the right place for the question, but I am seeking some quick advice for choosing the right positional encoding. I have a...
Hey, great work! I just wanted to ask whether you might have the loss curves of your runs so that I can compare with my experiments a little bit?
Hey, Is it sufficient to have the spectograms in half precision format (float16)? And did you train your model with mixed precision?
### 🐛 Describe the bug The problem only occurs under some specific conditions: 1. The video backend is 'video_reader' 2. The VideoReader object is initialized with raw bytes rather than...
### 🐛 Describe the bug When applying the resize operation on a floating point image (e.g. bounded between 0 and 1) with bicubic interpolation mode, the resulting tensor might contain...
### Describe the bug 'translate_x' is in the default policy list twice, whereas 'translate_y' is missing. ### Reproduction steps ```bash 1. Open kornia/augmentation/auto/rand_augment/rand_augment.py ``` ### Expected behavior Current default_policy list:...
Hey, amazing project! Just wanted to ask whether the checkpoints for the _compact_ models (i.e. C1) are available aswell? The provided checkpoints only seem to contain the baseline models. Best...
### 🐛 Describe the bug I am compiling a method (mode=default, fullgrph=True), which calls torchvision.transforms.v2.functional.resize_image. However, I receive an error, which indicates that the interpolate method is not implemented. I...