-
The Siamese network example doesn't work because the `ExactNumBotomBlobs()` for the ContrastiveLossLayer in loss_layers.hpp returns 4 instead of 3. Not sure why this has been changed since it is corre…
d4nst updated
9 years ago
-
This might be a silly question but here goes:
I have modified the mnist siamese network example to work for a set of image pairs that I have and I have trained that network. I am trying to use it in …
-
I have trained the Siamese network as mentioned in the tutorial: http://caffe.berkeleyvision.org/gathered/examples/siamese.html
The tutorial includes a contrastive loss function which merges the two …
-
Hi,
I am wondering why need propagate back to bottom[1] in Smooth_L1_Loss? Is it strange to propagate to target box which actually is label for bbox regression?
Thanks much!
This is in the followin…
-
Hi,
I started with Caffe and the mnist example ran well.
However, I can not understand how am I suppose to use this for my own data for a classification task.
What should be the data format? Where sh…
-
Hi,
I'm running on Ubuntu 14.4 LTS.
ERROR: Expected caffe suffix "-nv". libcaffe.so does not match. Are you building from the NVIDIA/caffe fork?
```
ubuntu@ip-10-0-1-51:~/digits$ pip install -r req…
-
Hello guys,
I'm currently on Arch Linux, and have installed the latest CUDA SDK (Version 7, as of today).
When I tried building the package today, it failed (done with makepkg via a local PKGBUILD), …
-
name: "face_siamese_train_test"
layers {
name: "pair_data"
type: DATA
top: "pair_data"
top: "sim"
data_param {
source: "lbph_siamese_train_leveldb"
batch_size: 10
}
include: { p…
-
If I use the following feature layer, the loss do not converge. Here, only the num_output is changed to 1 other than default 2 as in mnist_siamese_train_test.prototxt. Does anyone know the reason?
lay…
-
Ok, so I already put a ticket here the other day, but DS closed the Issue before my problem was solved! I'm not spamming, I need your help! I enabled every individual world in the config, and even ena…