curtis.abcd

Architecture Search on Cifar100 or imagenet?

2

I have tried to search architectures on cifar100, but validation accuracy was so low : 0.59~0.64 Also the found architecture have only skip-connection and pooling layers. Do you have any...

Do you have validation loss value or graph? I can't find them which is needed for comparison with my model.

Can you post a validation loss?

1

I saw training loss around 20~30 values in your readme. What about validation loss value? Is validation loss value similar to the training one?

**Bug description** Please enter a clear and concise description of what the bug is. I see this : https://parl.ai/projects/bb3/ When I run this ```parlai interactive --init-opt gen/opt_bb3 --opt-server API_SERVER --loglevel...

Reproducibility Problem(ResNet-50 on ImageNet)

20

Below is the top1 errors with N and M grid search, epoch=180. M\N | 1 | 2 | 3 -- | -- | -- | -- 5 | 0.2318 |...

Inference Speed Test?

9

It would be great if you test your code to check the inference speed.

Zoomed-in bounding boxes are never getting smaller.

Support BFloat16 ?

1

### Describe the issue When will be Tensor type Bfloat16 supported? ### To reproduce - ### Urgency _No response_ ### Platform Linux ### OS Version Ubuntu 18.04 ### ONNX Runtime...

Loss Function : L1 Norm or L2 Norm?

2

L2 Loss seems to be the right one.