Breeze.

I also have this requirement. At present, I am facing a data set of 1536×320, and the size of each image may be inconsistent (floating in this ratio). Because it...

hi @mmuckley，I copied the above code to my machine, but modified batch Szie. The figure below is the result of `mprof run --include-children file.py`  I didn't even finish an...

I was in a similar situation. The problem was solved by installing your Py3.9 environment directly with Conda, however, creating a Py3.9 environment from Conda normally and pip install git+https://github.com/facebookresearch/fastMRI.git...

I tried calling `return kspace_torch` after each line of UnetDataTransform and found that `kspace_torch = to_tensor(kspace)` doesn't have a memory leak. After mask_func I started having problems, but when I...

> @834799106推理管道已发布，请参阅。 Thanks for your work but i get a few problem in inference.sh. Hope you can check it .For example where is predict.py and Traceback (most recent call last):...

> @834799106 I have updated the inference pipeline and README.md, could you follow the instructions to try again? I suggest you first read the inference code to understand it before...

> 也许最好一次训练 1 个模型。 Yes, I only train one model at a time, but I need two or more when I build it, otherwise I will have some problems with...

> Have you used the `RandomResizedCrop()` function, or `ResizedCropRGBImageDecoder()` class? No, Just reading the data, the data itself is not consistent and I don't want to resize it.

> What are you actually trying to do Here's the size range of my data: {(448, 132, 10, 9, 12), (448, 132, 10, 10, 12), (512, 204, 10, 11, 12),...

Me too.