Could a new type of loss be introduced for classes? about epro-pnp-v2 HOT 3 OPEN

Theoretically these logprobs can be backpropagated. But I don't think information extracted from the pose distribution can help improve the classification.

+ np.log(orient_bins / (2 * np.pi)) is meant to convert the bin probabilities into a continuous density function on [0, 2pi), such that the integral equals 1. This is mainly for visualization purpose.

from epro-pnp-v2.

I was experimenting with this and I have a question in connection with this.

from epro-pnp-v2.

Theoretically these logprobs can be backpropagated. But I don't think information extracted from the pose distribution can help improve the classification.

I understand. But theoretically, the yaw angle distribution evaluated with some density from 0 to 2pi would roughly look like the logprobs here?

np.log(orient_bins / (2 * np.pi)) is meant to convert the bin probabilities into a continuous density function on [0, 2pi), such that the integral equals 1. This is mainly for visualization purpose.

I don't understand this. Without np.log(orient_bins / (2 * np.pi)), the probabililities sum to one, with it they don't.

from epro-pnp-v2.