Borda Follow

Borda Follow

Jirka Borovec Borda

Computer Vision & Machine Learning & Bio-Medical Imaging & Deep Learning

Follow

216 followers · 166 following · 167

Highlights

Arctic Code Vault Contributor
Pro

Organizations

Pinned

pyImSegm

Image segmentation - general superpixel segmentation & center detection & region growing

Python 167 50
BIRL

BIRL: Benchmark on Image Registration methods with Landmark validations

Python 40 15
pyBPDL

Binary Pattern Dictionary Learning for gene activation in microscopy images

Python 5
PyTorchLightning/pytorch-lightning

The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate

Python 7.3k 839
ij-CMP-BIA

Extension for ImageJ (Fiji) by BIA segmentation methods as plugins and some other useful API for image segmentation.

Java 1 8
docker_python-opencv-ffmpeg

Forked from Valian/docker-python-opencv-ffmpeg

Dockerfile containing FFmpeg, OpenCV4 and Python2/3, based on Ubuntu LTS

Dockerfile 21 13

1,929 contributions in the last year

Activity overview

Contributed to PyTorchLightning/pytorch-lightning, PyTorchLightning/pytorch-lightning-bolts, Borda/BIRL and 5 other repositories

Contribution activity

August 2020

Created a pull request in PyTorchLightning/pytorch-lightning that received 8 comments

allow using apex with any PT version

What does this PR do? add extra argument which would switch between using Apex and native AMP in pt>=1.6 Fixes #2788 PR review Anyone in the commun…

+140 −139 • 8 comments

Fix install setup - push pypi Aug 7
clean imports Aug 7
build XLA with py3.6 [wip] Aug 7
fix docker builds Aug 7
allow finish remaining docker builds Aug 7
Tests/install pkg Aug 5
clean tests imports Aug 5
missing chlogs Aug 3

save last model after saving top_k when save_last=True Aug 8
allow using apex with any PT version Aug 8
hotfix on classification metrics Aug 8
Clarify what gpus=0 means in docs Aug 8
Fix Trainer arg name in docs Aug 8
Fix docs typo Aug 8
simplify tests & cleaning Aug 7
Fix accumulate_grad_batches for last batch Aug 7
Add lightning class playlist to docs Aug 7
Fix ddp for test Aug 7
Add support to Tensorboard logger for OmegaConf hparams Aug 7
Add tracking of basic states in Trainer [wip - to-be-merged after v0.9] Aug 7
fix set_epoch on TPUs Aug 7
Fix PR link in contributing.md Aug 7
Update CONTRIBUTING.md Aug 6
Add wandb autoclass in logger.rst Aug 6
Support limit_mode_batches (int) for infinite dataloader Aug 6
Added strict=False and hparams_file accepcts dict for load_from_checkpoint Aug 6
[Test] Add a more direct test of multi-gpu training working Aug 6
Support returning python scalars in DP Aug 6
Use .comet.config file for CometLogger Aug 6
Setup extras Aug 6
Update contributing guide Aug 6
Faster Accuracy metric Aug 6
updated sync bn Aug 5
Some pull request reviews not shown.

[blocked by #142] Try declarative command line for optimizer and optimizer parameters in MoCo Aug 5
Add Cityscapes DataModule + clean up DM docs Aug 5
Multi env refactor Aug 4
Loaders Aug 2

Created an issue in ultralytics/yolov5 that received 5 comments

train model on multiple folders/sources

🚀 Feature According the wiki now we can train model just from one source/folder. I would be interested in having option to define multiple folders...

5 comments

merging master to a PR Aug 7

Failing docker-Conda build Aug 7

You can’t perform that action at this time.