jie
here is a bug: ` if isinstance(fill, numbers.Number): fill = fill, if isinstance(fill, numbers.Number) and len(img.shape) == 3: fill = (fill,) * 3 ` the type of fill is changed...
请问这个新工作的代码有开源的计划吗
> 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...
> 通过openvino转换。 我也尝试了，pytorch->onnx->openvino->tensorflow，这个流程太长了，最后输出结果误差较大。
modify the include_directories of caffe in CMakeLists.txt
the same problem, anyone solved it？
I didn't change the params and the batch size is 16. I also tried them with a batch size of 25, but still not work. I also tried lambda_cls=4000, but...
Finally, I get the correct result. You mentioned that you got the above problem because you had not computed the Action Units of each face correctly, so I use openface...
same problem
确实是个问题，会不会里面没有最后一个字符是“警”，“学”之类的车牌。应该把标签合并到一个list里，然后给出index。