Mohammed Al-Rawi

Is training ENAS to discover CNN architecture working already? If it is in progress, why a run example is given? ``` python main.py --network_type cnn --dataset cifar --controller_optim momentum --controller_lr_cosine=True...

@einarf that's totally correct, but I would like to use those streams in my application (stream of bytes and not as a file); in fact, I would like to store...

What I wanted is to pass `data` instead of reading it via `data = json.loads(fd.read())` (line 193) and other info red via file handler `fd = gzip.open(str(cache_name(self.file_name)), 'rb')` (lines 109-119)...

Thanks you for the heads up! I don't think I need to do this now, but maybe later. The only concern, although trivial, is that when the original file `OBJ`...

@mrbean-bremen why not then including the compression feature, especially lossless compression methods, in the pydicom?

@mrbean-bremen I think the compression is something easy to do using [BytesIO](https://pillow.readthedocs.io/en/3.1.x/reference/Image.html) of Pillow. Unfortunately, although I would love to contribute to pydicom, I have no time at the moment.

@mrbean-bremen would [imencode ](https://docs.opencv.org/3.4/d4/da8/group__imgcodecs.html#ga461f9ac09887e47797a54567df3b8b63)of OpenCV do?

Well, I think you can try whatever loss function, this is a no-big-deal. As for the buffer, it will start random pooling after it is filled (max-size=50). This won't affect...

Which python version are you using? And, did you get the reported accuracy?

Hi @cad0p, well, I have another machine with Linux ... unfortunately this is the one available at home at the moment, and I do not want to add extra load...