load resnet18 onnx模型失败

verbose=True
完整的日志

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()

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.

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

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）.