flutter_pytorch_mobile
flutter_pytorch_mobile copied to clipboard
A flutter plugin for pytorch model inference. Supports image models as well as custom models.
Hi, we experienced some leaks in our iOS app, after some investigation we found two memory leaks: - rawBytes in UIImageExtension (calloc not freed) - normalizedBuffer in UIImageExtension (malloc not...
I replaced this line in the main.dart of the example program String pathCustomModel = "assets/models/yolov5s.pt"; After compiling and running on the IOS emulator, an error is reported: [enforce fail at...
Android is quite notorious for deprecating things. When I try to run the example app, I get this: ```diff ────────────────────────────────────────────────────────────────────────────── Your Flutter application is created using an older version of...
As far as I know, yolov5 is developed on pytorch framework (https://github.com/ultralytics/yolov5), so is the model created by yolov5 flutter_pytorch_monile readable?
I was just wondering what type of image models [`predictImage`](https://github.com/fynnmaarten/flutter_pytorch_mobile/blob/3a8848d6ef726e2d491d79a9f355f7f7171b71dc/android/src/main/java/io/fynn/pytorch_mobile/PyTorchMobilePlugin.java#L102) actually supports. I'm assuming here image classification models are supported, but what about other types of models, like for example...
Hi, I am using pytorch v0.2.2 with iOS, after profiling the app I discovered memory leak related to the PyTorchMobilePlugin Malloc 3.98 MiB 61 < multiple > 243.05 MiB -[PyTorchMobilePlugin...
OS: Windows 11 Package: Anaconda pytorch_mobile: ^0.2.1 PyTorch : 1.8.1 I'm getting this error when trying to load the model: >E/PyTorchMobile( 7949): assets/MobileNetV3_2.pt is not a proper model >E/PyTorchMobile( 7949):...
I found three articles in the pytorch docs that talk about using GPU on edge devices: 1. [IOS GPU IN PYTORCH](https://pytorch.org/tutorials/prototype/ios_gpu_workflow.html) 2. [PYTORCH VULKAN BACKEND](https://pytorch.org/tutorials/prototype/vulkan_workflow.html) 3. [CONVERT MOBILENETV2 TO NNAPI](https://pytorch.org/tutorials/prototype/nnapi_mobilenetv2.html)...
i read the example codes but it seems only support object detection right now, so i am wondering can this package supports a GAN model ?