bowenc0221 / panoptic-deeplab

This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)

bowenc0221/panoptic-deeplab Issues

using demo.py to predict an image,But it's all black
Closed 3 years ago3
CUDA out of memory even on Google colab
Closed 2 years ago1
No module named ‘torchvision.models.utils‘ errors
Updated 10 months ago
Assertion Error : Please run `python cityscapesscripts/preparation/createPanopticImgs.py` to generate label files
Updated a year ago1
How to transfer this model to coreml?
Updated a year ago
Demo.py not working
Updated a year ago1
CUDA error: an illegal memory access was encountered CUDA kernel
Updated a year ago
Cityscapes has around 30 classes, but it handles 19
Closed 2 years ago2
Errors during the evaluation phase
Updated 2 years ago
IndexError: index -1 is out of bounds for axis 0 with size 0
Closed 2 years ago1
Low PQ in inference
Updated 2 years ago
Assertion Error when loading the cityscapes dataset
Closed 2 years ago2
[Contribution welcome] Reproduce COCO results
Closed 3 years ago4
Reproduce the results PQ 61.12% on the Cityscapes datasets
Updated 2 years ago
Attribute 'ignore_label' does not exist in the metadata of dataset '/raid/Bansi/Cityscapes/gtFine/train': metadata is empty.
Closed 2 years ago
[Discussion] Changing Instance Segmentation Head to 2D Detection Head
Closed 2 years ago1
How to visualize all panoptic segmentation results of validation dataset
Closed 3 years ago4
custom dataset register for Panoptic-deeplab
Closed 3 years ago6
Where to find the following files to train Panoptic-Deeplab model
Closed 3 years ago2
Error in loading pickle weights
Closed 3 years ago3
RuntimeError: CUDA error: out of memory
Closed 3 years ago1
Problem about visulizing the predict result
Closed 3 years ago1
About the Mean and Std of Mapillary_Vistas dataset?
Closed 3 years ago4
How to transfer this model to onnx?
Updated 3 years ago1
How
Closed 3 years ago
Unable to generate input image
Updated 3 years ago1
AssertionError: Config file does not exist!
Updated 3 years ago
About pretraining with Mapillary Vistas
Closed 3 years ago2
Train model Error: Unknown LR scheduler: WarmupPolyLR
Closed 3 years ago2
where is the address of the google drive of the trained model?
Closed 3 years ago
Using panoptic segmentation in Python
Closed 3 years ago4
Config file for COCO (old version)
Closed 3 years ago1
Ordered Dictionary Error (.pkl) and Gibberish Random Output!
Closed 3 years ago2
Is it possible to train custom data with 1 GPU?
Closed 3 years ago5
Confusions about multi-scale test
Closed 3 years ago5
Large crop size [1024, 2048] training with 32 gpus getting bad results
Closed 3 years ago1
Problem with training/inference
Closed 3 years ago3
custom coco format panoramic segmentation dataset
Closed 3 years ago9
Feature Request: Add inference-only to train_net.py
Closed 3 years ago3
about 'unlabeled' category in Detectron2
Closed 3 years ago2
Question about the implementation between the two codebase (D2 & Pytorch)
Closed 3 years ago1
The poor Instance Segmentation performance on COCO
Closed 3 years ago2
How to generate json files?
Closed 3 years ago3
pool_kernal_size error!
Closed 3 years ago2
convert-pretrain-model-to-d2.py working poorly with Panoptic-DeepLab X65-DC5 model
Closed 3 years ago2
Can't correctly crop the coco image
Closed 3 years ago2
RuntimeError: each element in list of batch should be of equal size
Closed 3 years ago2
Training panoptic segmentation for a custom dataset in coco-panoptic format
Closed 3 years ago6
Can't find the dilation rate setting in Backbone
Closed 3 years ago1
AssertionError: Default process group is not initialized
Closed 3 years ago2