icevision

icevision copied to clipboard

While running the application i get the below error in the application. Please guide me to solve it. `RuntimeError: stack expects each tensor to be equal size, but got [1,...

balavenkatesh3322

Does Icevision support segmentation masks in the RLE bitmask format?

1

I tried `parsers.COCOMaskParser` to load my COCO dataset but getting an error: `ValueError: invalid literal for int() with base 10: 'YXi61og0000og00QXO00000O1000000O10O100000O100000000O10000000000O10000000000O01000000000O100000000000000O100000000000000O10001O0000000000000000000O10000000001O000O100000000000001O00000000000O2O0000000` Does that mean icevision only supports polygons for COCO...

Robotatron

How to use Metrics class to check the performance of the trained model

12

## 📓 New **Is this a request for a tutorial or for an example?** Tutorial **What is the task?** Lets say I trained a model and now I want to...

tugot17

Lib restructure

1

His PR refactors ross and ultralytics to the new structure.

fstroth

segmentation fault core dump when converting a single mask record with .to_mask

3

## 🐛 Bug I have the following record ``` {'common': {'width': 6443, 'height': 4176, 'record_id': 0, 'filepath': Path('/root/data-cv2/Coincident/S1A_IW_GRDH_1SDV_20200729T034859_20200729T034924_033664_03E6D3_93EF/Background.png'), 'img': None}, 'detection': {'areas': [3833, 2466, 17029], 'bboxes': [, , ], 'labels':...

rbavery

update install script with lates mmdet dist to fix yolox input size i…

3

I modified the install script in order to fix the input_size issue with yolox, as pointed out by @dnth

fabiogeraci

Updating and adding tests for better test coverage

1

This PR is still work in progress! Pls don't merge yet! The goal is to add tests for parts that are not covered atm to prepare for the big changes...

fstroth

Adding Coco Metric for inference

9

I added some convenient methods to easily calculate the COCO metric at inference when ground truth records are available ``` infer_dl = model_type.infer_dl(valid_ds, batch_size=4, shuffle=False) preds = model_type.predict_from_dl(model, infer_dl, keep_images=True)...

ai-fast-track

negative samples are not implemented for mmdet models

1

## 🐛 Bug **Describe the bug** `Negative samples still needs to be implemented. This error might appear due to cropping, please check your transformations.` **To Reproduce** train a model with...

rbavery

see discussion in this closed issue. opening this new one since this closed issue hasn't been re-opened: https://github.com/airctic/icevision/issues/1080

rbavery