lucasjinreal/DCNv2_latest

Error occurs when running testcpu.py

Open

#16 opened on Mar 15, 2021

View on GitHub
 (4 comments) (3 reactions) (0 assignees)C++ (130 forks)github user discovery
help wanted

Repository metrics

Stars
 (675 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

After building, when I run testcpu.py directly, the error occurs as follows:

Traceback (most recent call last): File "/home/bst/Documents/Projects/Official/Object_Detection/BBAVectors-Oriented-Object-Detection/models/DCNv2/testcpu.py", line 255, in <module> example_dconv() File "/home/bst/Documents/Projects/Official/Object_Detection/BBAVectors-Oriented-Object-Detection/models/DCNv2/testcpu.py", line 175, in example_dconv output = dcn(input) File "/home/bst/anaconda2/envs/Python3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/bst/Documents/Projects/Official/Object_Detection/BBAVectors-Oriented-Object-Detection/models/DCNv2/dcn_v2.py", line 191, in forward self.deformable_groups, File "/home/bst/Documents/Projects/Official/Object_Detection/BBAVectors-Oriented-Object-Detection/models/DCNv2/dcn_v2.py", line 39, in forward ctx.deformable_groups, IndexError: Dimension out of range (expected to be in range of [-2, 1], but got 2)

Contributor guide

Research direction
Check the input tensor dimensions in the DCNv2 forward method, ensuring they match the expected shape for deformable convolution (e.g., batch, channels, height, width). The IndexError suggests a dimension mismatch, possibly due to incorrect input size or deformable groups parameter. Trace the shape through the code and verify compatibility with the deformable convolution implementation.
Tech stack
pythonpytorch
Domain
machine learningcomputer vision
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorch
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65