NextCloud/dlib
1
0
Fork 0
mirror of https://github.com/davisking/dlib.git synced 2024-11-01 10:14:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix trainer with unsupervised loss (#2436)

Browse Source 
* Don't try to use labels in unsupervised losses

I hope that is the right way of fixing this...

* fix it by duplicating most code in send_job (works on my machine)

I will probably need to find a way to reuse the code

* try to fix it reusing the code... not sure though

* Revert "try to fix it reusing the code... not sure though"

This reverts commit f308cac6df.

* check the type of the training label to fix the issue instead
This commit is contained in:
Adrià Arrufat 2021-09-27 20:47:04 +09:00 committed by GitHub
parent b9f04fdc45
commit 8a2c744207
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
dlib/dnn/trainer.h
View File

@ -1199,6 +1199,8 @@ namespace dlib
const auto prev_dev = dlib::cuda::get_device();
const bool has_unsupervised_loss = std::is_same<no_label_type, training_label_type>::value;
double j = 0;
for (size_t i = 0; i < devs; ++i)
@ -1211,7 +1213,8 @@ namespace dlib
if (start < stop)
{
devices[i]->net.to_tensor(dbegin+start, dbegin+stop, job.t[i]);
job.labels[i].assign(lbegin+start, lbegin+stop);
if (!has_unsupervised_loss)
job.labels[i].assign(lbegin+start, lbegin+stop);
job.have_data[i] = true;
}
else