whats the retinaface of resnet50 input shape?

[DDFlyInCode]

whats the retinaface of resnet50 input shape?

[biubug6]

When training, input is cropped to 840*840 defined in "data/config.py".

[DDFlyInCode]

how about inference？

[DDFlyInCode]

i found inference code can recevied any inputshape image. This may lead some problems in model convert when I use onnx. Because onnx model is base on static map ,can not auto resize with mutil size image. I dont know what to do ! Looking forward to help , thx. By the way! Your project is amazing

[biubug6]

When testing, I provide original image size as input in widerface val. You can scale image to a certain size according to the effect and your needs. See "test_widerface.py" for details.

[biubug6]

Because of the full convolution structure of network, It don't lead some problems in model convert when I convert model from onnx to NCNN and deploy the model.

[xsacha]

Ultimately the model still prefers its training dimensions, but it will work at any resolution. You should set the size based on the minimum face size you desire.

[SnowRipple]

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 specified as a dynamic axes" Making input fixed makes results worse for datasets with differently sized images (like Widerface). Did anyone tried onnx version with dynamic input sizes?

[SnowRipple]

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: 'batch'}} torch.onnx.export(model, dummy_input, 'test.onnx', input_names=inputs, output_names=outputs, dynamic_axes=dynamic_axes)

[121649982]

Because of the full convolution structure of network, It don't lead some problems in model convert when I convert model from onnx to NCNN and deploy the model.

can you share your demo how to load onnx model ,please? thank you

[venki-lfc]

For people who have trouble in exporting to onnx model with arbitrary height and width, You can do the following way:

model.eval()

# Define the input and output names for the ONNX model
input_names = ["input"]
output_names = ["output"]

# Export the PyTorch model to ONNX format
output_path = "retinaface.onnx"

batch_size = 1 # random initialization
dummy_input = torch.randn(batch_size, 3, 640, 640) # This is a random tensor with the same shape as the expected input
dynamic_axes = {'input' : {2 : 'height', 3:'width'}, # enables the model to accept dynamic batch sizes
                }

torch.onnx.export(model, dummy_input.to(device), output_path,
                  do_constant_folding=True,
                  input_names=input_names, output_names=output_names,
                  dynamic_axes=dynamic_axes)

The ONNX model can now accept images of any input size just like pytorch. And you don't have to worry about resizing the input images. Just follow the pre- and post-processing steps in detect.py