name | about | labels |
---|---|---|
Bug Report | Convolution operator gets a wrong result. | kind/bug |
Ascend
/GPU
/CPU
):Uncomment only one
/device <>
line, hit enter to put that in a new line, and remove leading whitespaces from that line:/device ascend
/device gpu
/device cpu
The models including:
lite-model_east-text-detector_int8_1.tflite
lite-model_deeplabv3-xception65_1_default_1.tflite
lite-model_deeplabv3-xception65-cityscapes_1_default_1.tflite
lite-model_deeplabv3-xception65-ade20k_1_default_1.tflite
lite-model_deeplabv3-mobilenetv3-cityscapes_1_default_1.tflite
lite-model_deeplabv3-mobilenetv2_dm05_1_default_1.tflite
lite-model_deeplabv3-mobilenetv2_1_default_1.tflite
lite-model_deeplabv3-mobilenetv2-ade20k_1_default_1.tflite
lite-model_cartoongan_dr_1.tflite
lite-model_arbitrary-image-stylization-inceptionv3_dr_transfer_1.tflite
lite-model_arbitrary-image-stylization-inceptionv3_dr_predict_1.tflite
lite-model_arbitrary-image-stylization-inceptionv3-dynamic-shapes_dr_predict_1.tflite
Hey wang_shaocong, Welcome to MindSpore Community.
All of the projects in MindSpore Community are maintained by @mindspore-ci-bot.
That means the developers can comment below every pull request or issue to trigger Bot Commands.
Please follow instructions at https://gitee.com/mindspore/community/blob/master/command.md to find the details.
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。
权重int8,输入fp32的卷积算子精度问题
暂不支持动态量化,建议精度对比跟pb模型对比
官网没有提供对应pb模型,暂时无法对比
mslite不支持动态量化方式,与tflite 动态量化精度对比没有参考性,
实际上mslite是用fp32实现精度更高,所以该问题为非问题
登录 后才可以发表评论