Arulkumar

Thanks for the heads up with this example. I have changed the `_decode_cfg_value` to handle this. Can you check if this handles your scenario?

@muzammil360 Such validation is already built-in to yacs with the method `_check_and_coerce_cfg_value_type` ([here](https://github.com/rbgirshick/yacs/blob/7b06e280216451b6f8536538548c75b861d9c22c/yacs/config.py#L460)). But the issue is that, every string is passed through `literal_eval` ([here](https://github.com/rbgirshick/yacs/blob/7b06e280216451b6f8536538548c75b861d9c22c/yacs/config.py#L410)) which changes `+123` to `123`....

I see. Thanks for the examples. I didn't think of this scenario. In my case, I just needed to mention the integer as string in YACS config. Not with a...

@dhaivat666 Can you give a short reproducible snippet? To me, It is able to load the array when using @xl-sr's suggestion.

From the below line, it seems like [0.0000, 1.0000, 2.0000] describes about occlusion. But they are removed from labels anyway. So I think they don't have any significance in YoLo...

@nitinsurya In my view, even during the prediction/test, the routing starts with equal probabilities for each primary capsule. So, we need these iterations even during test. what do you think?

Though each capsules norm is a probability [0-1], the capsules will be fighting within themselves to send the info to higher level capsules (based on their correlation with the output...

Maybe if you could write your understanding about capsules or point out the lines in the paper, it will be helpful to discuss and learn I guess. Anyway, I will...

Oh I see. My bad. I didn't see which softmax you are mentioning:) I think you are right. There is no need for softmax (since the vector's magnitude emulates probability)....

I had the same question. the dimension of logits is [10, 100, 1152, 1, 16]. i.e., [num_digits, batch_size, num_prevlayer_capsules, 1, digits_features_dim] since the softmax is taken over dim=2, the softmax...