rknn-toolkit2

rknn-toolkit2 copied to clipboard

我正依据Rockchip_User_Guide_RKNN_Toolkit2手册第40页中的说明排查模型转换时的精度损失问题，如说明中，我以 rknn = RKNN(verbose='Debug') 创建了rknn对象，执行脚本后，获得了check*.pkl与check*.onnx一系列文件，请问文件中所说的 “check results” 在哪个文件中？如何查看？

fediel

请问可以支持动态shape模型转换吗

1

shivabohemian

zen-xingle

rknn.build failure at Global Average Pool input height/width > 128

11

I am running rknn toolkit for building a model.rknn for running on RK3566. After rknn.load_onnx() successfully, when run rknn.build(), the following error message occur: --> Loading model: ./rknn_models/model_3566.onnx done -->...

ynjiun

请问有 rknn-toolkit2 1.2.0版本吗

1

tian123-zxc

torch.sqrt() tooklit2 1.3 do not support

bopker

W __init__: rknn-toolkit2 version: 1.3.0-11912b58 W config: 'target_platform' is None, use rk3566 as default, Please set according to the actual platform! --> Loading model W load_onnx: Model converted from tf2onnx,...

alexHxun

ONNX Build model failed! IndexError: vector::_M_range_check: __n (which is 4) >= this->size() (which is 4)

2

python test.py W __init__: rknn-toolkit2 version: 1.3.4b4-ad9ac429 --> Config model done --> Loading model done --> Building model I base_optimize ... I base_optimize done. I I fold_constant ... W build:...

lht0223

您好，我有一个操作很简单的分类模型，它使用pytorch-qat（torch版本为1.7.1）进行训练，训练时没有fuse_bn，训练完之后的模型使用rknn-toolkit1可以正常转为rknn，但是使用rknn-toolkit2时发生了如下报错：  从报错中我无法定位问题在哪里，转换过程中使用的模型结构为  转换代码如下： import numpy as np import cv2 from rknn.api import RKNN import torchvision.models as models import torch import os if...

shupinghu

Would it be possible to get opset 13 support? Thanks!

peterwilli