Oguzhan Gencoglu comments

Results 101 comments of


                                            Oguzhan Gencoglu

Support for Python 3.12: deprecated imp module

Thanks for the reply. [skl2onnx](https://onnx.ai/sklearn-onnx/) library supports a lot of base models from scikit-learn. If `treeple` models can use similar classes, it should be straightforward. Note that ONNX is quite...

ONNX support

Because pickle is a python-specific format and one can not serve pickle in frontend (Typescript or javascript) or embed in some C++ application etc. I may have a look during...

Add Additional Transformations for Image Augmentation, better Finetuning on Small Datasets

It makes more sense to simply provide a yaml template that defines `albumentations` augmentations and the path to this can be passed as an argument. Everyone can then decide their...

Add Additional Transformations for Image Augmentation, better Finetuning on Small Datasets

Something like: `model.train(..., augmentations_val: None, augmentations_train: 'path/to/aug_train.yaml')` Claude 3.7 with albumentations docs added as docs in Cursor can one-shot this probably.

Add Additional Transformations for Image Augmentation, better Finetuning on Small Datasets

Something like ``` Dataset_1: HorizontalFlip: p: 0.5 VerticalFlip: p: 0.5 Affine: scale: - 0.4 - 1 balanced_scale: true keep_ratio: true cval: - 1 - 1 - 1 cval_mask: 0 interpolation:...

Cells sometimes do not render when scrolling down in presence of large outputs

This happens in `jupyterlab==4.4.0` on chrome even if the outputs are cleaned. So it is not a large output issue.

Cells sometimes do not render when scrolling down in presence of large outputs

There are actually 2 separate issues: - some cells or some of their parts not rendering randomly - scrolling suddenly jumping some cells completely

Input Shape for Training and Inference with Pretrained Models

@hamac03 just to clarify: the requirement of "divisibly by 32" depends on the number of encoder-decoder stages. 5 stages of downsampling gives us 2^5=32 but it depends on the number...