Giters
zimenglan-sysu-512
/
Focal-Loss
loss layer of implementation
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
125
Watchers:
13
Issues:
18
Forks:
41
zimenglan-sysu-512/Focal-Loss Issues
How to define focal loss in train_val.prototxt, two classes with softmax?
Updated
4 years ago
Comments count
4
when have two classes, it not work.
Updated
4 years ago
Comments count
1
If this layer support multi classes?
Updated
5 years ago
How to use propagate_down?
Updated
5 years ago
Comments count
1
about the alpha parameter
Closed
7 years ago
Comments count
3
include/caffe/layers/focal_loss_layer.hpp(68): error: identifier "FocalLossParameter_Type" is undefined
Closed
6 years ago
Check failed: outer_num_ * inner_num_ == bottom[1]->count() (4 vs. 1) ERROR!
Updated
6 years ago
faster-rcnn+Focal Loss accuracy
Updated
6 years ago
Comments count
1
How to replace FocalLoss in testing phase?
Updated
6 years ago
Segmentation fault
Closed
7 years ago
Comments count
4
caffe_gpu_scal(count, alpha_, power_prob_data);
Updated
6 years ago
Comments count
2
Negative sample not add in loss
Updated
6 years ago
Add a license file
Updated
6 years ago
Comments count
2
How about the result of SSD with focal-loss?
Updated
6 years ago
Comments count
13
about beta_
Updated
7 years ago
Comments count
1
break when save model
Updated
7 years ago
Comments count
2
The first term of “grad” seems to be wrong
Updated
7 years ago
Comments count
8
focal-loss = 87.3365
Updated
7 years ago
Comments count
5