8b5344ee2d
Added BFLOPs output for network configurations
2018-05-14 13:34:40 +03:00
028696bf15
Output improvements for detector results:
...
When printing detector results, output was done in random order, obfuscating results for interpreting. Now:
1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score
2. Text output is sorted by rect lefts to simplify finding appropriate rects on image
3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated
4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones
5. Most probable label for rect is always written first
Also:
6. Message about low GPU memory include required amount
2018-05-03 16:33:46 +03:00
9bae70b225
Accelerated by another 5% using FP16/32 Batch-norm for Tensor Cores.
2018-04-17 02:51:11 +03:00
c52fa47428
Loss-graph store automatically (iterations == max_batches) at the end of training
2018-04-16 13:09:10 +03:00
eb9c88ef73
Fixed bug in Tensor Cores V100 (1. Desc in Batch norm, 2. Manually selected algo).
...
Also fixed time measure on Linux for multi-threading.
2018-04-15 01:51:21 +03:00
537d135feb
Improve training performance - batch-norm using cuDNN.
2018-03-20 02:16:51 +03:00
880cf187d8
Fixed multi-GPU training for Tensor Cores
2018-03-09 19:44:46 +03:00
cad4d1618f
Added support for Tensor Cores CC >= 7.0 (V100). For FP16/32 (mixed precision) define CUDNN_HALF should be used.
2018-02-25 16:29:44 +03:00
cd2bdec090
Updated to CUDA 9.1. And fixed no_gpu dependecies.
2018-02-23 15:05:31 +03:00
f558d5c39c
Fix
2018-02-22 23:16:36 +03:00
dda993f3dd
Use half_float16 instead of float32 if defined both CUDNN and CUDNN_HALF. Use Tensor Cores.
2018-02-22 22:54:40 +03:00
033e934ce8
If there is excessive GPU-RAM consumption by CUDNN then then do not use Workspace
2018-02-21 19:14:01 +03:00
4b0be8c701
Optimized resizing of network for random=1
2018-02-21 15:06:11 +03:00
bc810016a1
cuDNN 6.0 supported. Also speed of console example improved.
2017-08-03 01:36:22 +03:00
d7a30ada7e
Fixed behavior if missing library cudnn.lib
2017-01-16 12:51:42 +03:00
3b9afd4cd2
Fixed behavior if missing library cudnn.lib
2017-01-16 00:44:41 +03:00
62235e9aa3
cpu batch norm works
2016-11-18 21:51:36 -08:00
fc9b867dd9
🔥 🔥 :dragonite:
2016-11-16 00:15:46 -08:00
0d6b107ed2
hey
2016-11-15 22:53:58 -08:00
c7a700dc22
new font strategy
2016-11-05 14:09:21 -07:00
352ae7e65b
ADAM
2016-10-26 08:35:44 -07:00
481b57a96a
So I have this new programming paradigm.......
2016-09-24 23:12:54 -07:00
73f7aacf35
better multigpu
2016-09-20 11:34:49 -07:00
5c067dc447
good chance I didn't break anything
2016-09-12 13:55:20 -07:00
8f1b4e0962
updates and things
2016-09-01 16:48:41 -07:00
845ab75796
some more stuff
2016-08-05 15:27:07 -07:00
9361292c42
updates
2016-07-19 14:50:01 -07:00
08c7cf9c88
no mean on input binarization
2016-06-19 14:28:15 -07:00
8322a58cf6
hate warnings
2016-06-14 11:30:28 -07:00
7520949d84
idk just in case
2016-06-08 11:07:31 -07:00
8a767f1066
stuff for carlo
2016-06-06 15:48:52 -07:00
4625a16ffd
tactics
2016-06-06 13:22:45 -07:00
ec3d050a76
hope i didn't break anything
2016-06-02 15:25:24 -07:00
881d6ee9b6
fixed
2016-05-13 13:46:31 -07:00
13209df7bb
art, cudnn
2016-05-13 11:59:43 -07:00
c7b10ceadb
so much need to commit
2016-05-06 16:25:16 -07:00
cff59ba135
go updates
2016-03-16 04:30:48 -07:00
913d355ec1
lots of stuff
2016-01-28 12:30:38 -08:00
1578ec70d7
idk
2016-01-18 15:40:14 -08:00
9802287b58
some fixes
2015-12-18 15:55:58 -08:00
c2738835f0
Faster batch normalization
2015-12-07 17:18:04 -08:00
8fd18add6e
CVPR Experiments
2015-11-03 19:23:42 -08:00
c40cdeb402
lots of comparator stuff
2015-10-09 12:50:43 -07:00
8bcdee8658
Some bug fixes, random stuff
2015-09-01 11:22:03 -07:00
846b3b4366
Added COCO, fixed memory leaks
2015-07-30 16:19:14 -07:00
fdcc096694
Fixed some problems with visualizing networks
2015-07-24 15:14:23 -07:00
d00f0a1ccd
Changes to make routing work better
2015-07-21 16:09:33 -07:00
a08ef29e08
NIGHTMARE!!!!
2015-07-10 16:38:14 -07:00
11c72b1132
testing on one image
2015-06-11 15:38:58 -07:00
cbc9984a17
NIPS
2015-06-10 00:11:41 -07:00
