6593928855
Merge pull request #108 from akarazniewicz/device-model-mapping-for-CPU-inference
...
Mapping loaded, pretrained model to actual device.
2019-11-11 21:18:02 +09:00
be128d4d9f
Mapping loaded, pretrained model to actual device. Required for CPU only inference.
2019-11-11 12:36:06 +01:00
603d463e83
comment update
2019-11-04 04:52:51 +00:00
f9d1795350
comment update
2019-11-04 04:34:06 +00:00
1ef8f74224
comment update
2019-11-04 04:32:46 +00:00
1863c76b6a
Merge pull request #99 from tgalkovskyi/master
...
Sample ipython notebook demonstrating use of the code
2019-10-29 01:45:45 +09:00
9e5ae484c5
Sample ipython notebook demonstrating use of the code
2019-10-27 10:43:59 -04:00
2ca716f98a
Update README.md
2019-10-23 15:57:07 +09:00
9a3a14150c
Merge pull request #95 from varshaneya/master
...
removed align_corners=True
2019-10-23 15:55:00 +09:00
53509eab01
removed align_corners=True
...
Got this error in Pytorch 1.1.0:
TypeError: grid_sample() got an unexpected keyword argument 'align_corners'
2019-10-23 11:35:37 +05:30
9a6f6678b1
pad update
2019-10-23 05:39:34 +00:00
a19dc0f169
ctc fix..
2019-10-22 17:49:52 +00:00
8749902367
ctc update
2019-10-22 17:26:58 +00:00
ec5319296b
arrange
2019-10-22 13:58:23 +00:00
1493d2e8cd
Update README.md
2019-10-22 21:01:25 +09:00
e8b465d477
add confidence score
2019-10-22 11:46:45 +00:00
4381a5fb46
Merge pull request #91 from edwardpwtsoi/master
...
updated grid_sample arg align_corners=True
2019-10-22 14:31:26 +09:00
f5cf8555ef
updated grid_sample arg align_corners=True
...
UserWarning: Default grid_sample and affine_grid behavior will be changed to align_corners=False from 1.4.0. See the documentation of grid_sample for details.
2019-10-13 20:57:50 +08:00
ff7f7dbd71
Update README.md
2019-10-10 17:16:32 +09:00
6dc16df598
(ctc_a) (ctc_b) and fine tuning
2019-10-07 05:33:44 +00:00
e34c99c386
Update README.md
2019-10-03 16:59:42 +09:00
7a8717eb50
Update README.md
2019-10-03 15:41:40 +09:00
f2c54ae2a4
Delete trade-off.jpg
2019-10-03 15:22:38 +09:00
464b3395df
Update README.md
2019-10-03 15:21:42 +09:00
6985b0fa0a
Add files via upload
2019-10-03 15:21:03 +09:00
1d85fca2c3
Update README.md
2019-10-01 12:02:39 +09:00
235095fc9a
Update transformation.py
2019-09-27 18:06:16 +09:00
fc62d2232d
'minor'
2019-08-10 18:29:40 +09:00
1c6efa5218
'fix_ctc_loss_issue'
2019-08-07 16:42:42 +09:00
8f7255fb4b
.cuda() to .to(device)
2019-08-03 08:03:46 +00:00
7498f48452
no_grad instead of requires_grad False
2019-08-03 06:55:32 +00:00
d62daf3baa
Merge pull request #48 from YacobBY/patch-2
...
replaced deprecated fromstring() with frombuffer()
2019-08-03 15:04:38 +09:00
cbc1d9df0f
replaced deprecated fromstring() with frombuffer()
...
Kept seeing
`DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead imageBuf = np.fromstring(imageBin, dtype=np.uint8)`, this fixes the issue.
2019-08-01 16:28:41 +02:00
9128831f7b
Update README.md
2019-08-01 12:03:40 +09:00
b3b3889295
Merge pull request #46 from coallaoh/patch-1
...
Update README.md
2019-08-01 12:03:07 +09:00
42d9506787
Update README.md
2019-08-01 08:26:31 +09:00
533fdf01ba
fix encode with batch_max_length
2019-07-31 08:04:56 +00:00
bda81065a5
fix encode with batch_max_length
2019-07-31 08:03:53 +00:00
a239f46df3
'fix'
2019-07-26 15:02:05 +09:00
c189d3d8dc
Update README.md
2019-07-25 01:27:24 +09:00
7b938741bd
.
2019-07-24 16:20:25 +00:00
5d4ed385f4
Merge pull request #36 from YacobBY/patch-1
...
Nvidia Apex for FP16 calculations
2019-07-25 00:35:01 +09:00
2d45ba2fab
use amp grad clipping
2019-07-24 14:42:25 +02:00
a0f43fa0c0
Nvidia Apex for FP16 calculations
...
Included Compatibility with the Nvidia's Apex library, which can do Floating Point16 calculations. This gives significant speedup in training. This code has been tested on a single RTX2070. If the Nvidia Apex library is not found the code should run as normal.
To install Apex: https://github.com/NVIDIA/apex#quick-start
Known bugs:
-Does not work with adam parameter
-Gradient overflow keeps happening at the start, however it automatically reduces loss scale to 8192 after which this notification disappears
examples:
Loading: https://i.imgur.com/3nZROJz.png
Training: https://i.imgur.com/Q2w52m7.png
2019-07-23 15:51:26 +02:00
40a4100df6
update data_filtering
2019-07-17 05:41:34 +00:00
f551679a0a
update data_filtering
2019-07-17 05:34:10 +00:00
ea3e322de9
Update README.md
2019-07-16 22:28:08 +09:00
dd18436360
--data_filtering_off
2019-07-16 10:04:20 +00:00
c3e07b538a
fix minor
2019-07-16 03:30:44 +00:00
f15051a493
add data_filtering mode
2019-07-15 05:33:37 +00:00
Baek JeongHun
