Is there something wrong with q_values' computation ?

sadeepj / crfasrnn_keras

CRF-RNN Keras/Tensorflow version

http://crfasrnn.torr.vision

MIT License

603 stars 169 forks source link

Is there something wrong with q_values' computation ? #23

Closed LandyGuo closed 6 years ago

LandyGuo commented 6 years ago

According to the original paper,

we use Ui(l) to denote the negative of the unary energy intoduced in the previous section

since unary energy is computed as: -log(p) , where p = softmax(FCN_OUT), so the initial q_values in crfrnn_layer.py should be log(softmax(unaries)) instead of directly using unaries ? Am I right ? hoping for your response.

glhfgg1024 commented 6 years ago

Hi, please check this issue: https://github.com/sadeepj/crfasrnn_keras/issues/4