Daniel Li

A follow up to this question, can we use CfgNode like dict? i.e. cfg['key'] can return the value of the key.

Here is my implementation (copied from the config.py) ``` _VALID_TYPES = {tuple, list, str, int, float, bool} def convert_to_dict(cfg_node, key_list=[]): """ Convert a config node to dictionary """ if not...

That file `imagenet_eval.py` needs some maintenance. You should change it to `transforms.Normalize(mean=model.mean, std=model.std),`

@Jerryzcn How do you come up with the name `resnest14` and `resnest26`? I count the number of Conv2d in the resnest26 and they are definitely not equal to 26.

Sorry I don't. If I remember correctly the intermediate representations are provided directly.

It seems like after training the network, using the `checkpoint_future.tar` from `ablation_cache/skipLSTM/30_04_2020_10_46/split-0` we can get a better result than the pre-trained model, but it is still worse than what the...

The statement in your first sentence is correct, and I think they did implement it. Read the line 167-173 in the `infer-main.ipynb` from your IDE, or what I copy pasted...