Guanghui Ren(任广辉)

icon indicating a website link https://scholar.google.com/citations?user=oqN1dA8AAAAJ icon indicating an email [email protected]

icon company CoLab@BUAA icon location Beijing,China icon location CoLab@BUAA; University of Chinese Academy of Sciences; Xi'an Jiao Tong University

Results 5 comments of Guanghui Ren(任广辉)

Fix parse bug

It's ok on torch1.6.0

Fix parse bug

@lxgyChen do you use `Upsample` layer in yolov5s? `Upsample` layer will be converted to ``` , %224 : Double() = onnx::Constant[value={2}](), scope: CustomizedNet/Upsample[Sampling30] , %225 : Double() = onnx::Constant[value={2}](), scope:...

Fix parse bug

@lxgyChen As mentioned above, `Upsample` layer will be converted to `onnx:: Constant` and other layers. If you want to use Upsample, you should modify code to merge `onnx:: Constant`, ......

ctypes.ArgumentError: argument 1: <class 'TypeError'>: wrong type

@edgarscr https://github.com/sergiomsilva/alpr-unconstrained/issues/22 ```python im = load_image(image.encode('ascii'), 0, 0) ```

预备知识1

@qiaokang0 主要是想讲一下这些库中一般是如何存储这些数组的，然后便于利于理解ATEN下TH THC这些"古老"的底层库数据结构