notabigfish

Hi, I converted the deploy.caffemodel from coco to voc using coco2voc.py. But only got 54.76% mAP on VOC07 test. Could anyone shares your mAP on VOC07 test? Thanks!

Does MorphNet support conv3d?

3

Hi, I'm applying MorphNet on tf.contrib.layers.conv3d(), but it seems that no ops are found. `INFO:tensorflow:OpRegularizerManager starting analysis from: [].` `INFO:tensorflow:OpRegularizerManager found 46 ops and 0 sources.` `INFO:tensorflow:OpRegularizerManager regularizing 0 groups.`...

Hi, the AUC of DIEN in original paper is 0.8453(mean) on Amazon books dataset. But I only got 0.8279. Is this result reasonable? Has anyone got a higher AUC? Thank...

Hi, I'm confused about the 209th line in model.py. `conv_decode4 = conv_layer_with_bn(upsample4, [7, 7, 64, 64], phase_train, False, name="conv_decode4")` Why is activation=**False**? According to the paper, ReLU is used in...

Hi, thanks for the excellent codes! I'm a little confused about the "Scale" layer after "BatchNormalization" layer. Why are scale parameters not directly set in "BatchNormalization()", but written in a...

Why is 'activation=False' in decoder?

3

Hi, I'm studying on SegNet and your codes are excellent for understanding the whole structure of SegNet. While reading your codes, I felt a little confused about the 35th line...

Is there pre-trained model using Flow images?

3

Hi, thank you for these clear and efficient codes! May I ask, if you have trained this model on Optical Flow images?

Questions about paper

1

Hi, the paper is great and thank you for sharing your code. I have a few questions about the paper: 1. In section 3.1.3, "_The initial value of thresholds for...

Could you please provide the original distorted fisheye image?

1

Hi, is it possible for you to provide the original fisheye image like the following one? Thank you!