tanzhenyu

Results 117 comments of tanzhenyu

Re Pretrained Weights -- do you have a colab that can help us evaluate the model using the weights from Google Drive?

> @tanzhenyu Here is a [Colab link](https://colab.research.google.com/drive/1ZxiUKAgdyK_qAspgouNRjiaKHAa_zgdw?usp=sharing) > > Few notes: > > * The evaluation requires TFRecords created via[ scripts in tensorflow/tpu repository](https://github.com/tensorflow/tpu/tree/master/tools/datasets#imagenet_to_gcspy). > * The colab is mostly...

Also I'm leaning towards only supporting Linux *for now* until we know better

> Cool! I think it would be super-useful to let people understand better how to replicate these experiments. I'm looking forward to it! I think we should provide some training...

> @tanzhenyu I think this is probably out of scope for the package in that it would cost 800K to retrain. > > Maybe useful in our fine-tuning journey, but...

> Possibly a stupid question on my end - should I pre-train it on ImageNet-1K and provide the weights? @LukeWood It'd be strongly preferred if this can be pretrained and...

> Thank you for the clarification @tanzhenyu! I'm off to pretrain it then. Is there a standard augmentation pipeline used by most models here or do I just go ahead...

> > 1. follow the original augs from the paper and achieve similar accuracy; > > I think this one is really important, especially when you want to have a...