Void Main

Results 41 comments of Void Main

I totally agreed with this `grayscale(0.5) blur(10px)` style, that's great! As for achievement registration, I don't know if we can read some cson files inside the package, so developers can...

:thumbsup: for integration, but I don't know if there's a programmers' game center or what?

Hi @ntasfi , I'm trying to add a new game to PLE. Hope you like it. :heart:

I tried to secretly copy the signature to .h file, and used it in the `viewWillDisappear:` and `viewDidLoad` method when pushing a new view controller, the frame did change to...

Same issue here, debug a little deeper, the root cause is in the model code, there's some python code that manages a tuple list: ``` original_image_sizes: List[Tuple[int, int]] = []...

Besides, as for now, Torch-TensorRT doesn't seem to support models with `Tensor[]` as input. For example, for FasterRCNN model, the model is defined as: ``` graph(%self : __torch__.torchvision.models.detection.faster_rcnn.___torch_mangle_47.FasterRCNN, %images.1 :...

Hi @peri044 @narendasan , thank you so much for the suggestions and sorry for my late reply. I edited `modeling_bert.py` and set `require_full_compilation=True` to make sure the whole graph is...

Also, I got a lot of warnings during the inference, but these warnings seem to be ignorable: ``` WARNING: [Torch-TensorRT TorchScript Conversion Context] - Tensor DataType is determined at build...

I'm using the latest commit: ``` >>> import torch_tensorrt >>> torch_tensorrt.__version__ '1.1.0a0+4fd886d0' ```

> @narendasan the fix seems ok to me. The graph for inceptionv3 scripted has the following > > ``` > %self.Conv2d_1a_3x3.conv.bias.1 : NoneType = prim::Constant() > %1611 : str =...