Closed ontheway16 closed 2 years ago
Ok solved,
name: "yolov4"
platform: "tensorrt_plan"
max_batch_size: 1
input [
{
name: "input"
data_type: TYPE_FP32
format: FORMAT_NCHW
dims: [ 3, 608, 608 ]
}
]
output [
{
name: "detections"
data_type: TYPE_FP32
dims: [159201, 1, 1]
}
]
Yes, the newest version has changes, you need to adapt a few things or check out release 1.3.
Just built everything from scratch, and set the batch to 16 in main.cpp, but getting the following error;