trt8 maxpool的問題 about yolo-tensorrt HOT 3 OPEN

抱歉 我覺得問題也不在這 我再查查看 不過真是沒道理 trt7 ok trt8則失敗

from yolo-tensorrt.

sorry, 我應該確定是maxpool的問題,因在建enging時(以下我只列部分)
(11) conv-bn-leaky 64 x 200 x 200 128 x 200 x 200 280160
(12) skip 128 x 200 x 200 128 x 200 x 200 -
(13) maxpool 128 x 200 x 200 128 x 100 x 100 280160
(14) conv-bn-leaky 128 x 100 x 100 128 x 100 x 100 428128

WARNING: Weights [name=conv_11 + batch_norm_11.weight] had the following issues when converted to FP16:
WARNING: - Subnormal FP16 values detected.
WARNING: If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.
WARNING: Weights [name=conv_14 + batch_norm_14 + PWN(leaky_14).weight] had the following issues when converted to FP16:
WARNING: - Subnormal FP16 values detected.
WARNING: If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights.

列config時沒錯 建enging時沒有13(maxpool)
請問這要改哪? 謝謝

from yolo-tensorrt.

这个升级到tensorrt8后NvInfer.h中的这个class TRT_DEPRECATED IOutputDimensionsFormula被遗弃了，所以m_TinyMaxpoolPaddingFormula也被注释掉了，我看这个代码的readme里也把对yolov tiny的支持去掉了，不知道后续用什么替代方案来支持呢？

from yolo-tensorrt.