metasequoia

Can the quantized model trained by pytorch qat be converted to the mnn model?

test performance on big face

1

the performance on big face is very poor

after training with this densenet, I cannot freeze the ckpt to pb. KeyError: u'cond/linear_batch_1/cond_1/AssignMovingAvg/linear_batch/moving_mean/linear_batch/linear_batch/moving_mean/Switch/read'

how to fuse conv and bn when using this repo to perform quantization aware training? show in the code snippet,like fuse_model func: `import geffnet model = geffnet.efficientnet_lite0(pretrained=True, drop_rate=0.25, drop_connect_rate=0.2) mode.fuse_model()...

I suggest the ONNX should change the name to be OPEN NNE, just like opencv,opencl,etc.

support for tensorflow 1.10+

8

will adabelief support for tensorflow 1.10+

An empty project

1

An empty project, with just a readme, getting so many stars, is truly unbelievable.

3D Computation Clarity in unet_3d, resnet_3d, and transform_3d

1

I have a question: unet_3d, resnet_3d, and transform_3d only deal with dimensional transformations, yet there is no indication anywhere that 3D computation is necessary.

lvmLoadData problem

1

when running any demo ,it can't find the lvmLoadData[] function .

how to run VILA1.5-40B-AWQ

1

Please provide a script to run the VILA1.5-40b int4 quantized model. like this: