What changes between caffe and pytorch bottleneck styles in an MMDetection ResNet?
Computer VisionLevel: AdvancedBackbone implementation compatibility
What changes between caffe and pytorch bottleneck styles in an MMDetection ResNet?
Hints
- Which convolution performs spatial downsampling?
- Can two shape-compatible implementations behave differently?
Answer
This answer is part of mentoring
Advanced questions come with a full breakdown and a mock interview with a working quant researcher. The first call is free.
Source and licence: OpenMMLab — MMDetection FAQ · Apache-2.0 · answer: Quantoros editorial