load resnet18 onnx模型失败

[复制链接] · 发表于 2019-7-31 13:28:40

verbose=True
完整的日志

只看该作者 · 发表于 2019-8-1 18:43:56

模型是自己用pytorch（1.1）训练的，保存成onnx的
转换代码
from rknn.api import RKNN

if __name__ == '__main__':
rknn = RKNN()
rknn.config(channel_mean_value='0 0 0 255', reorder_channel='0 1 2')
print('--> Loading model\n')
rknn.load_onnx('./resnet.onnx')
print('done\n')
print('--> Building model\n')
rknn.build(do_quantization=False)
print('done\n')
rknn.export_rknn('./resnet.rknn')

# Release RKNN Context
rknn.release()

只看该作者 · 发表于 2019-8-2 15:10:45

FFFOCUS 发表于 2019-8-1 18:43
模型是自己用pytorch（1.1）训练的，保存成onnx的
转换代码
from rknn.api import RKNN

does your pytorch model contain torch.view?
you can just replace it with squeeze/unsqueeze operator.

只看该作者 · 发表于 2019-8-2 15:13:08

zhangyu 发表于 2019-8-2 15:10
does your pytorch model contain torch.view?
you can just replace it with squeeze/unsqueeze operato ...

btw, transconv2d has a bug when bias=False. so bias can only be True

只看该作者 · 发表于 2019-8-5 20:07:01

zhangyu 发表于 2019-8-2 15:13
btw, transconv2d has a bug when bias=False. so bias can only be True

The picture below shows the difference between the public resnet18 with format onnx and my own resnet18 with format onnx which is produced by pytorch（version1.1）.

load resnet18 onnx模型失败

本帖子中包含更多资源

本帖子中包含更多资源