Jeff Tang

Sorry I’m currently on a trip without my computer but I’ll take a look in about a week after I’m back. Thanks! Sent from my iPhone > On Oct 21,...

@bosuksh sorry for the late reply. Definitely - there're many online tutorials on how to select a photo from library and use the selected photo. Below is some code snippet...

@thewozz sorry i don't have a swift version of Ch 3 ready but you can follow the swift project in Ch 2 and add the swift code to select a...

This works for me on TF 1.4 recently: python tensorflow/tools/quantization/quantize_graph.py --input=darkflow/built_graph/tiny-yolo.pb --output_node_names=output --output=quantized_tiny-yolo.pb --mode=weights python tensorflow/tools/quantization/quantize_graph.py --input=darkflow/built_graph/tiny-yolo-voc.pb --output_node_names=output --output=quantized_tiny-yolo-voc.pb --mode=weights

Which torch and torchvision versions are you using?

Looks like your model's output is a tensor list instead of a tuple that the model that comes with the demo app outputs. Below is from IValue.java which you can...

1. Have you tried `python models/export.py` and used the generated `yolov5s.torchscript.pt` to see if it works with the app? 2. Add the following two lines after `y = model(img) #...

The reasons you see `torch.Size([16, 16128, 26])` instead of `torch.Size([16, 25200, 85])` are: 1. you set input image size to be 512 instead of the default 640 and 2. your...

If your model's output is a tensor list then `mModule.forward(IValue.from(inputTensor)).toList()` or `mModule.forward(IValue.from(inputTensor)).toTensorList()` should work. But your latest Android error message says "actual type 7", meaning your model's output is `TYPE_CODE_TUPLE`...

Glad it works for you! What was the cause and fix for the problem?