-
Hi,
Based on the lst files included in the repository,I am assuming you are using COCO2014 for training right.However I couldn't find the annotations/labels for the cocostuff 2014.As of now only 2017…
-
Hi! I’m training a **panoptic segmentation fpn** model from detectron2 on a **custom dataset following COCO format**. After reading other issues like #1691, I managed to register, train and evaluate t…
-
Hello,
I am trying to use the evaluation code for prediction on COCO 2017 dataset for replicating/measuring zero-shot performance on coco2017/
Steps I followed:
1. created the DATASET folder…
-
I'm following the `train_a_new_model_on_a_new_dataset_from_scratch.ipynb` and used `python3.11 -m venv venv && source venv/bin/activate` for virtual env.
I noticed that the `corenet` doesn't have …
-
## Instructions To Reproduce the Issue:
I want to train the panoptic segmentation model on a custom data set, however, before I prepare my own custom data set I wanted to make sure that the trainin…
-
The do block and spaced dot attribute syntax make for really nice looking coco, but the compiled javascript collapses all the newlines inside a do-block or the usual jQuery chaining style method calls…
-
I had ran inference using the 'swin_large_IN21k_384_bs16_100ep' weight, and obtained the semantic segmenation masks. But, the colours in the mask do not match with the colours in the stuff_colours in …
-
from the official coco website
Images
2014 Train images [83K/13GB]
2014 Val images [41K/6GB]
2014 Test images [41K/6GB]
2015 Test images [81K/12GB]
2017 Train images [118K/18GB]
2017 Val imag…
-
Hello, when I run the Python script datasets/prepare_coco_stuff_sem_seg.py to generate a dataset, it shows 0it [00:00, ?it/s], and when I execute python train_net.py --num-gpu 1 --config-file configs/…
-
Hello,
I used pretrained model for coco stuff to test on val .
I generated instances for val dataset.
so to generate images , the model take val instance as input,
but why the path for val_img…