Piotr Chudzik
Piotr Chudzik
I have the same problem with dict input: File "/home/snow_ripple/workspace/01_detection/mmdet/apis/inference.py", line 96, in _inference_single hl_graph = hl.build_graph(model, **data) TypeError: build_graph() got an unexpected keyword argument 'img' Is there a workaround...
Thanks @zhangjing1997 ! What is the point of getBuff(0)? Which module have the definition of this function? I assume it is just a placeholder so I modified it to: graph...
@narendasan any news on this?
I thought that onnx supports dynamic input sizes now, from: https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html "Note that the input size will be fixed in the exported ONNX graph for all the input’s dimensions, unless...
PyTorch 1.2 supports dynamic input now, such as: model = models.resnet18() dummy_input = torch.zeros(1, 3, 224, 224) inputs = ['images'] outputs = ['scores'] dynamic_axes = {'images': {0: 'batch'}, 'scores': {0:...
Trying to install it on 16.04 as well, @weep33 how do you change distro from xenial to vivid?
Thanks @weep33 it works now! Btw is this project dead? No one seems to contribute to it for a long time now..
Hey @jordanparker6 Can you share your config for LayoutLMv3ForObjectDetectionConfig please?
Many Thanks @jordanparker6 ! I am trying to use your code with funsd dataset, however I am not sure if I am modelling the no-object class correctly. So with LMV3...