Yolov4 +darknet 19 custom data

Please provide the following information when requesting support.

• Hardware: A4000
• Network Type Yolo_v4
• TLT Version dockers: [‘nvidia/tao/tao-toolkit’]
format_version: 2.0
toolkit_version: 4.0.0
published_date: 12/08/2022
when start training get below error :-

ValueError: The shape of the input to “Flatten” is not fully defined (got (1024, None, None). Make sure to pass a complete “input_shape” or “batch_input_shape” argument to the first layer in your model.

Please share full spec file and full log.

sorry issue has been resolve

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.