hufangjian

Results 15 comments of hufangjian

回归损失 loss=inf

学习率调小一点。

Function names and buildId information is missing for some frames due to unreadable libraries.

没有，是我这边的代码偶发性的。

编译windows Demo .\build_msvc_native.bat报错

报同样的错误。

编译windows Demo .\build_msvc_native.bat报错

我直接下载的TNN-master 跟TNN-0.3.0都是不行的。相同的错误。加了opencv编译的后面就报错了。 ![image](https://user-images.githubusercontent.com/30458099/119087491-cec74480-ba39-11eb-8778-5a5a077b4d12.png)

编译windows Demo .\build_msvc_native.bat报错

git clone 下载编译的是没问题的

pytoch->onnx->tensorflow how to conevrt from NCHW(onnx) to NHWC(tensorflow lite)

my comond： onnx-tf convert -i Zero_DCE_640_dele.sim.onnx -o test --device CPU but the tensorflow lite mode is NCHW not NHWC. ![image](https://user-images.githubusercontent.com/30458099/106988163-058a8f00-67aa-11eb-83c7-d7432b7fb2a7.png)

pytoch->onnx->tensorflow how to conevrt from NCHW(onnx) to NHWC(tensorflow lite)

I try: onnx-tf convert -i Zero_DCE_640_dele.sim.onnx -o test --device CUDA It did no worked. have you ever test some model?

pytoch->onnx->tensorflow how to conevrt from NCHW(onnx) to NHWC(tensorflow lite)

this is my onnx file which convert from pytorch. the input shape is (1x3x360x640 ) NCHW。 [model.zip](https://github.com/onnx/onnx-tensorflow/files/5947909/model.zip) 1. run “onnx-tf convert -i Zero_DCE_640_dele.sim.onnx -o test --device CUDA“ to tensorflow save_model...

pytoch->onnx->tensorflow how to conevrt from NCHW(onnx) to NHWC(tensorflow lite)

通过openvino转换。

PR #399 仍然不支持的算子

相同的错误。