search

cfotache / pytorch_objectdetecttrack

Object detection in images, and tracking across video frames
483 stars 253 forks source link

YOLOV3-Tiny Runtime Error #10

Open ngingihy opened 5 years ago

ngingihy commented 5 years ago

When running object_tracker.py using yolov3-tiny weights and cfg file, I get the following:

RuntimeError: Given groups=1, weight of size 256 256 3 3, expected input[1, 384, 26, 26] to have 256 channels, but got 384 channels instead

Any help will be greatly appreciated..

kd4293accio commented 5 years ago

@cfotache @ngingihy have you solved this issue?

ebernalg92 commented 4 years ago

https://github.com/eriklindernoren/PyTorch-YOLOv3/issues/82

Solved!

modify model.py

filters = 0 for layer_i in layers: if(layer_i > 0): filters += output_filters[layer_i+1] else: filters += output_filters[layer_i]