Seunghyun Lee

I tried to insert 2 Unsqueeze and 2 Squeeze nodes before/after the pad node to make the 2D input to 4D and then recover the 4D to 2D back. but...

the onnx file is here, [aslfeatv2_op11_custom_const_padding_v3.zip](https://github.com/onnx/onnx-tensorrt/files/6269667/aslfeatv2_op11_custom_const_padding_v3.zip) I'm not sure why it fails to infer the Padded shape of 2D input and padding value of [1, 0, 0, 0]... Please help...

I faced the same problem, when the parsing node is Pad and input tensor is 2D([2,2] shape ) and padding is [1,0,0,0] (it's for 4D). [03/24/2021-08:18:11] [I] [TRT] Parsing node:...

I met the same problem. and also, next lines shows "ValueError: could not convert string to float: '(1169.62109375, 0.0, 646.2950439453125, 0.0, 0.0, 1167.1051025390625, 489.9270324707031, 0.0, 0.0, 0.0, 1.0, 0.0, 0.0,...

I solved above but another errror TRAIN views are [ 1 2 3 4 5 6 7 8 9 11 12 13 14 15 16 17 18 19 21 22...

I found the way to migrate NDDS content to ArchViz project. But when I tried to drag-drop SceneCapturer_Simple, the mouse icon turned into "Banned" and I couldn't move it as...

Plus, when I double clicked any imported item(like DR_AnnotatedActor_BP or SceneCapturer_Simple so on), it shows an error saying " It can't load the blue print inheried from invalid class. Please...

no, it is because of cuda API. No relevance to Pytorch. just cast the second arg to (double). That's the best solution.

Originally tensorRT engine init(deserialization) and doInference(enqueue) parts are in one function. But if I want to call the init part only one time and then call doInference part several times...

I solved that BN layer issue following @jialee93's workaround but I got other issues related to custom loss functions backpropagation regarding the float/half data type mismatch. https://github.com/tianzhi0549/FCOS/issues/121