bob issueshttps://gitlab.idiap.ch/groups/bob/-/issues2020-03-10T16:10:40Zhttps://gitlab.idiap.ch/bob/bob.bio.base/-/issues/132`numpy.testing.decorators.setastest` is no longer available in the latest `nu...2020-03-10T16:10:40ZManuel Günthersiebenkopf@googlemail.com`numpy.testing.decorators.setastest` is no longer available in the latest `numpy 1.18`Updating to `numpy` version 1.18 breaks this package as the import https://gitlab.idiap.ch/bob/bob.bio.base/blob/33b527af1418dff1812e2613d91f55b6e8ee61c8/bob/bio/base/database/database.py#L8 fails.
Workarounds:
1. Use `numpy` version 1....Updating to `numpy` version 1.18 breaks this package as the import https://gitlab.idiap.ch/bob/bob.bio.base/blob/33b527af1418dff1812e2613d91f55b6e8ee61c8/bob/bio/base/database/database.py#L8 fails.
Workarounds:
1. Use `numpy` version 1.17
2. Remove this import and its later use.
I have currently no solution how to replace the functionality of `numpy.testing.decorators.setastest`, though.Amir MOHAMMADIAmir MOHAMMADIhttps://gitlab.idiap.ch/bob/bob.bio.face/-/issues/34Failure with MTCNN when face is not found2020-03-09T16:16:16ZAnjith GEORGEanjith.george@idiap.chFailure with MTCNN when face is not foundThere is a key error, when face is not detected. The problem is this line
`https://gitlab.idiap.ch/bob/bob.bio.face/blob/master/bob/bio/face/annotator/bobipmtcnn.py#L29`There is a key error, when face is not detected. The problem is this line
`https://gitlab.idiap.ch/bob/bob.bio.face/blob/master/bob/bio/face/annotator/bobipmtcnn.py#L29`Amir MOHAMMADIAmir MOHAMMADIhttps://gitlab.idiap.ch/bob/bob.pipelines/-/issues/4Implement checkpointable processors2020-03-09T15:49:22ZAmir MOHAMMADIImplement checkpointable processorsCheckpointable process can be integrated with the Sample class and automaticall cache/save their results.Checkpointable process can be integrated with the Sample class and automaticall cache/save their results.https://gitlab.idiap.ch/bob/bob/-/issues/259new release2020-03-09T10:50:49ZAmir MOHAMMADInew releaseI am going to do a new release soon.
Here is a list of tasks that I think are worth tackling before the release:
* [x] Move the installation instruction to `bob/docs` which should fix #246
* [x] Update installation instructions to ta...I am going to do a new release soon.
Here is a list of tasks that I think are worth tackling before the release:
* [x] Move the installation instruction to `bob/docs` which should fix #246
* [x] Update installation instructions to talk about the archive channel
* [x] https://gitlab.idiap.ch/bob/bob.bio.video/merge_requests/40
* [x] https://gitlab.idiap.ch/bob/bob.db.swan/issues/2
* [x] https://gitlab.idiap.ch/bob/bob.db.siw/issues/1
* [x] https://gitlab.idiap.ch/bob/bob.db.ldhf/issues/2
* [x] https://gitlab.idiap.ch/bob/bob.bio.face_ongoing/merge_requests/5
* [x] bob.bio.htface mac builds, see https://gitlab.idiap.ch/bob/bob.bio.htface/commit/d970f521feaae4b99420026dfc8df58c1774aa0c
* [x] https://gitlab.idiap.ch/bob/bob/issues/260
* [x] https://gitlab.idiap.ch/bob/bob.db.swan/issues/3Amir MOHAMMADIAmir MOHAMMADIhttps://gitlab.idiap.ch/bob/bob/-/issues/246New installation instructions are required2020-03-09T10:50:20ZAmir MOHAMMADINew installation instructions are requiredSee: https://www.anaconda.com/blog/developer-blog/conda-configuration-engine-power-users/
for per environment configurations.
The new packages are in the new channel: https://www.idiap.ch/software/bob/conda/label/main/See: https://www.anaconda.com/blog/developer-blog/conda-configuration-engine-power-users/
for per environment configurations.
The new packages are in the new channel: https://www.idiap.ch/software/bob/conda/label/main/Conda-based CIAmir MOHAMMADIAmir MOHAMMADIhttps://gitlab.idiap.ch/bob/bob.paper.pad_mccnns_swirdiff/-/issues/2Branches2020-03-09T08:20:30ZAnjith GEORGEanjith.george@idiap.chBranchesNow that the revision is submitted, we can use `bob.db.hqwmca` for all further experiments is it?.
And can you merge the branch to master if the configs are final.Now that the revision is submitted, we can use `bob.db.hqwmca` for all further experiments is it?.
And can you merge the branch to master if the configs are final.Guillaume HEUSCHGuillaume HEUSCHhttps://gitlab.idiap.ch/bob/bob/-/issues/253Basic question2020-03-02T16:15:18ZTiago de Freitas PereiraBasic questionHey guys, basic question here.
Since now bob is composed by all our software stack if I do:
```
conda install bob=4.0.1
```
what should I have?
I've done it and I don't have any bob package in it.
Is this the right behaviour?
ThanksHey guys, basic question here.
Since now bob is composed by all our software stack if I do:
```
conda install bob=4.0.1
```
what should I have?
I've done it and I don't have any bob package in it.
Is this the right behaviour?
Thankshttps://gitlab.idiap.ch/bob/bob.pipelines/-/issues/2Using scikit learn pipelines with Dask2020-03-02T14:00:48ZTiago de Freitas PereiraUsing scikit learn pipelines with DaskOpening this issue just as a note for posterity.
Today I've done an exercise using scikit-learn pipelines and dask https://ml.dask.org/compose.html
We could leverage from the scikit-api and benefit from its caching mechanism too.
You c...Opening this issue just as a note for posterity.
Today I've done an exercise using scikit-learn pipelines and dask https://ml.dask.org/compose.html
We could leverage from the scikit-api and benefit from its caching mechanism too.
You can check the small snipped below how I use it (I made an adaptor to transform our algorithms in scikit-estimators).
Two things to be observed. I couldn't use the `cache` since most of our stuff is C++ based (not picklable).
And since things are not picklable, I made a very shitty job with the adaptor in order to integrate it with Dask as you can see in code.
In order to have the instance creation of Bob objects in the Worker (like @andre.anjos is doing with the SampleLoader (probably for the same reason (there's another reason for that too))), the method `fit` creates the Bob object and returns itself.
I think the current design is cleaner. I will give up this one.
ping @amohammadi
```python
from sklearn.pipeline import Pipeline
# Local client
import dask.bag
from dask.distributed import Client, LocalCluster
import bob.bio.base
import bob.bio.face
import numpy
cache_dir = "./cache"
from sklearn.base import BaseEstimator
class Scikit2BobEstimator(BaseEstimator):
"""
Base class to adapt from bob algorithms to scikit estimators
Check here for more info:
https://scikit-learn.org/stable/modules/generated/sklearn.base.BaseEstimator.html
"""
def __init__(self, bob_object):
self.bob_class = bob_object
def fit(self, X, y, **kwargs):
self.bob_object = self.bob_class(**kwargs)
return self
def transform(self, X, **kwargs):
"""
Here `X` can be our samples where the annotations can be shipped.
"""
annotations = {"leye": (10, 10), "reye": (20, 10)}
return [self.bob_object(x, annotations=annotations) for x in X]
### Starting the client
cluster = LocalCluster(nanny=False, processes=False, n_workers=1, threads_per_worker=1)
cluster.scale_up(1)
client = Client(cluster)
####### PREPROCESSOR #########
# Using face crop
CROPPED_IMAGE_HEIGHT = 80
CROPPED_IMAGE_WIDTH = CROPPED_IMAGE_HEIGHT * 4 // 5
## eye positions for frontal images
RIGHT_EYE_POS = (CROPPED_IMAGE_HEIGHT // 5, CROPPED_IMAGE_WIDTH // 4 - 1)
LEFT_EYE_POS = (CROPPED_IMAGE_HEIGHT // 5, CROPPED_IMAGE_WIDTH // 4 * 3)
import functools
preprocessor = Scikit2BobEstimator(
functools.partial(
bob.bio.face.preprocessor.FaceCrop,
cropped_image_size=(CROPPED_IMAGE_HEIGHT, CROPPED_IMAGE_WIDTH),
cropped_positions={"leye": LEFT_EYE_POS, "reye": RIGHT_EYE_POS},
)
)
### EXTRACTOR #######
extractor = Scikit2BobEstimator(bob.bio.base.extractor.Linearize)
estimators = [("preprocess", preprocessor), ("extractor", extractor)]
#### HERE I COULD CACHE IT #####
# pipeline = Pipeline(estimators, memory=cache_dir)
pipeline = Pipeline(estimators)
X = [numpy.random.rand(3, 100, 100) for _ in range(100)]
db = dask.bag.from_sequence(X)
db = db.map_partitions(pipeline.fit_transform)
print(db.compute(scheduler=client))
client.shutdown()
```https://gitlab.idiap.ch/bob/bob.bio.base/-/issues/125vstack_features is not optimized2020-02-27T09:22:42ZSaeed SARFJOOvstack_features is not optimizedI checked the time for loading data via `vstack_features` and directly from `bob.io.base.HDF5File`. Direct loading was 19.3 times faster than `vstack_features`. The code for testing is shown below:
``` python
import functools
import nump...I checked the time for loading data via `vstack_features` and directly from `bob.io.base.HDF5File`. Direct loading was 19.3 times faster than `vstack_features`. The code for testing is shown below:
``` python
import functools
import numpy as np
import time
import bob.bio.gmm.script.verify_ivector
import bob.bio.base
from bob.bio.gmm import tools, algorithm
from bob.bio.base import tools as base_tools
from bob.bio.gmm.script.verify_ivector import parse_arguments, execute
from bob.bio.gmm.tools.utils import read_feature
from bob.bio.base.utils.io import vstack_features
from bob.bio.base.tools.FileSelector import FileSelector
command_line_parameters = None
args = parse_arguments(command_line_parameters)
fs = FileSelector.instance()
limit_files = 100
reader = functools.partial(read_feature, args.extractor)
training_list = fs.training_list('extracted', 'train_projector')
training_list = training_list[:limit_files]
t1 = time.time()
data = vstack_features(reader, training_list, allow_missing_files=True)
t2 = time.time()
print('vstack time: ' + str(t2-t1))
t3 = time.time()
data2 = []
for i in range(len(training_list)):
f = bob.io.base.HDF5File(training_list[i])
data2.append(f.read('array'))
data2 = np.array(data2)
t4 = time.time()
print('direct time: ' + str(t4-t3))
```
and the output is:
```
vstack time: 5.793696880340576
direct time: 0.30901122093200684
```
Even for caching I tested them separately and the result was the same.https://gitlab.idiap.ch/bob/nightlies/-/issues/57Nighlies are failing2020-02-19T11:36:39ZTiago de Freitas PereiraNighlies are failingHey guys,
Building bob/bob fails on nightlies with that very nice and useless log trace (full of conflicts) https://gitlab.idiap.ch/bob/bob.nightlies/-/jobs/189669/raw.
This is similar to what was happening here, https://gitlab.idiap.ch...Hey guys,
Building bob/bob fails on nightlies with that very nice and useless log trace (full of conflicts) https://gitlab.idiap.ch/bob/bob.nightlies/-/jobs/189669/raw.
This is similar to what was happening here, https://gitlab.idiap.ch/bob/bob.devtools/issues/46.
Any ideas?
Batl project is suffering from the same issue.
https://gitlab.idiap.ch/batl/batl.pad.idiap/pipelines/37505
thanks
ping @ageorgehttps://gitlab.idiap.ch/bob/bob.devtools/-/issues/46Conda package resolution seems broken2020-02-19T07:09:51ZAndré AnjosConda package resolution seems brokenNot sure when it started, but we are currently facing package resolution problems in several places.
Examples:
* https://gitlab.idiap.ch/bob/bob.learn.tensorflow/pipelines/35806
* https://gitlab.idiap.ch/bob/bob.learn.em/pipelines/3587...Not sure when it started, but we are currently facing package resolution problems in several places.
Examples:
* https://gitlab.idiap.ch/bob/bob.learn.tensorflow/pipelines/35806
* https://gitlab.idiap.ch/bob/bob.learn.em/pipelines/35872
The only thing we noticed was a change in the patch version of conda-build.
Could this be problem?
@amohammadi: any clues?André AnjosAndré Anjoshttps://gitlab.idiap.ch/bob/bob.devtools/-/issues/49Automatically add bob.devtools to the output of bdt gitlab changelog2020-02-18T16:44:20ZAmir MOHAMMADIAutomatically add bob.devtools to the output of bdt gitlab changelogSince successful release of packages is based on releasing bob.devtools first, it makes sense to add it to the output of changelog always.Since successful release of packages is based on releasing bob.devtools first, it makes sense to add it to the output of changelog always.Amir MOHAMMADIAmir MOHAMMADIhttps://gitlab.idiap.ch/bob/bob.devtools/-/issues/29Update Bob metapackage release instructions2020-02-18T16:44:19ZTiago de Freitas PereiraUpdate Bob metapackage release instructionsHi,
I'm trying to release a new version of Bob, but I'm having an issue with the release script.
What this suppose to mean?
https://gitlab.idiap.ch/bob/bob.devtools/blob/51878163c8925664fb85ee945e5d663e44b6e828/bob/devtools/release.py#...Hi,
I'm trying to release a new version of Bob, but I'm having an issue with the release script.
What this suppose to mean?
https://gitlab.idiap.ch/bob/bob.devtools/blob/51878163c8925664fb85ee945e5d663e44b6e828/bob/devtools/release.py#L571
Why `../../bob/README`; I don't get it.
Can someone shine a light on me? ping @andre.anjos
thanksAmir MOHAMMADIAmir MOHAMMADIhttps://gitlab.idiap.ch/bob/nightlies/-/issues/56Nightlies failing2020-02-18T11:18:47ZTiago de Freitas PereiraNightlies failingJust posting this for the records.
For some reason our runners were paused and this was making our CI stuck.
I just resumed them to make them work againJust posting this for the records.
For some reason our runners were paused and this was making our CI stuck.
I just resumed them to make them work againhttps://gitlab.idiap.ch/bob/bob.devtools/-/issues/45Add bob.devtools to bob/docs2020-02-18T08:08:31ZAmir MOHAMMADIAdd bob.devtools to bob/docsAndré AnjosAndré Anjoshttps://gitlab.idiap.ch/bob/bob.devtools/-/issues/50Pipelines fail when tagging a private package2020-02-17T17:11:09ZAmir MOHAMMADIPipelines fail when tagging a private packageSee https://gitlab.idiap.ch/bob/bob.db.hkpu/-/jobs/188846See https://gitlab.idiap.ch/bob/bob.db.hkpu/-/jobs/188846https://gitlab.idiap.ch/bob/nightlies/-/issues/5523H nightlies2020-02-14T16:15:23ZTiago de Freitas Pereira23H nightliesIt's been 2 days that our nightlies are failing due to timeout on MACOSX only.
If you look at the execution time of the 2 macos pipelines, we can observe that we didn't even reached half of the builds.
Furthermore, we even haven't touch...It's been 2 days that our nightlies are failing due to timeout on MACOSX only.
If you look at the execution time of the 2 macos pipelines, we can observe that we didn't even reached half of the builds.
Furthermore, we even haven't touched the complicated one (bob.learn.tensorflow)
```
Pipeline 35218, Job 180560
--------------------------------------------- ------------------- -------
None 2019-11-05 21:25:36 2.53m
bob/bob.buildout@master (1/120 2019-11-05 21:28:12 2.93m
bob/bob.extension@master (2/120 2019-11-05 21:31:08 10.93m
bob/bob.blitz@master (3/120 2019-11-05 21:42:04 24.75m
bob/bob.core@master (4/120 2019-11-05 22:06:49 21.05m
bob/bob.io.base@master (5/120 2019-11-05 22:27:52 23.18m
bob/bob.math@master (6/120 2019-11-05 22:51:03 20.73m
bob/bob.measure@master (7/120 2019-11-05 23:11:47 20.17m
bob/bob.io.image@master (8/120 2019-11-05 23:31:57 23.32m
bob/bob.db.base@master (9/120 2019-11-05 23:55:16 9.63m
bob/bob.io.video@master (10/120 2019-11-06 00:04:54 19.5m
bob/bob.io.matlab@master (11/120 2019-11-06 00:24:25 16.25m
bob/bob.io.audio@master (12/120 2019-11-06 00:40:40 18.8m
bob/bob.sp@master (13/120 2019-11-06 00:59:28 21.05m
bob/bob.ap@master (14/120 2019-11-06 01:20:31 23.63m
bob/bob.ip.base@master (15/120 2019-11-06 01:44:09 27.58m
bob/bob.ip.color@master (16/120 2019-11-06 02:11:45 21.07m
bob/bob.ip.draw@master (17/120 2019-11-06 02:32:49 14.52m
bob/bob.ip.gabor@master (18/120 2019-11-06 02:47:20 26.23m
bob/bob.learn.activation@master (19/120 2019-11-06 03:13:34 42.62m
bob/bob.learn.libsvm@master (20/120 2019-11-06 03:56:11 37.23m
bob/bob.learn.linear@master (21/120 2019-11-06 04:33:25 25.92m
bob/bob.learn.mlp@master (22/120 2019-11-06 04:59:20 23.62m
bob/bob.learn.boosting@master (23/120 2019-11-06 05:22:57 25.97m
bob/bob.db.iris@master (24/120 2019-11-06 05:48:55 12.45m
bob/bob.learn.em@master (25/120 2019-11-06 06:01:22 39.33m
bob/bob.db.wine@master (26/120 2019-11-06 06:40:42 14.5m
bob/bob.db.mnist@master (27/120 2019-11-06 06:55:12 15.38m
bob/bob.db.atnt@master (28/120 2019-11-06 07:10:35 16.35m
bob/bob.ip.facedetect@master (29/120 2019-11-06 07:26:57 25.1m
bob/bob.ip.optflow.hornschunck@master (30/120 2019-11-06 07:52:03 16.87m
bob/bob.ip.optflow.liu@master (31/120 2019-11-06 08:08:55 20.65m
bob/bob.ip.flandmark@master (32/120 2019-11-06 08:29:36 20.85m
bob/gridtk@master (33/120 2019-11-06 08:50:28 6.33m
bob/bob.ip.qualitymeasure@master (34/120 2019-11-06 08:56:48 26.6m
bob/bob.ip.skincolorfilter@master (35/120 2019-11-06 09:23:25 11.12m
bob/bob.ip.facelandmarks@master (36/120 2019-11-06 09:34:32 38.65m
bob/bob.ip.dlib@master (37/120 2019-11-06 10:13:38 30.73m
bob/bob.ip.mtcnn@master (38/120 2019-11-06 10:44:22 0.13m
bob/bob.db.arface@master (39/120 2019-11-06 10:44:30 16.68m
bob/bob.db.asvspoof@master (40/120 2019-11-06 11:01:11 37.3m
bob/bob.db.asvspoof2017@master (41/120 2019-11-06 11:38:29 8.77m
bob/bob.db.atvskeystroke@master (42/120 2019-11-06 11:47:15 15.73m
bob/bob.db.avspoof@master (43/120 2019-11-06 12:02:59 45.68m
bob/bob.db.banca@master (44/120 2019-11-06 12:48:40 14.55m
bob/bob.db.biosecure@master (45/120 2019-11-06 13:03:13 21.38m
bob/bob.db.biosecurid.face@master (46/120 2019-11-06 13:24:36 20.22m
bob/bob.db.casia_fasd@master (47/120 2019-11-06 13:44:49 22.15m
bob/bob.db.casme2@master (48/120 2019-11-06 14:06:58 25.47m
bob/bob.db.caspeal@master (49/120 2019-11-06 14:32:26 24.87m
bob/bob.db.cohface@master (50/120 2019-11-06 14:57:18 30.25m
bob/bob.db.frgc@master (51/120 2019-11-06 15:27:34 25.25m
bob/bob.db.gbu@master (52/120 2019-11-06 15:52:49 22.43m
bob/bob.db.hci_tagging@master (53/120 2019-11-06 16:15:15 112.58m
bob/bob.db.ijba@master (54/120 2019-11-06 18:08:05 43.1m
bob/bob.db.ijbc@master (55/120 2019-11-06 18:51:13 0.28m
--------------------------------------------- ------------------- -------
Pipeline 35218, Job 180561
--------------------------------------------- ------------------- -------
None 2019-11-05 21:25:36 2.53m
bob/bob.buildout@master (1/120 2019-11-05 21:28:12 2.93m
bob/bob.extension@master (2/120 2019-11-05 21:31:08 10.92m
bob/bob.blitz@master (3/120 2019-11-05 21:42:04 24.75m
bob/bob.core@master (4/120 2019-11-05 22:06:49 21.05m
bob/bob.io.base@master (5/120 2019-11-05 22:27:52 23.25m
bob/bob.math@master (6/120 2019-11-05 22:51:07 20.67m
bob/bob.measure@master (7/120 2019-11-05 23:11:47 20.17m
bob/bob.io.image@master (8/120 2019-11-05 23:31:57 23.32m
bob/bob.db.base@master (9/120 2019-11-05 23:55:16 9.63m
bob/bob.io.video@master (10/120 2019-11-06 00:04:54 19.5m
bob/bob.io.matlab@master (11/120 2019-11-06 00:24:25 16.25m
bob/bob.io.audio@master (12/120 2019-11-06 00:40:40 18.8m
bob/bob.sp@master (13/120 2019-11-06 00:59:28 22.02m
bob/bob.ap@master (14/120 2019-11-06 01:21:29 22.68m
bob/bob.ip.base@master (15/120 2019-11-06 01:44:10 27.57m
bob/bob.ip.color@master (16/120 2019-11-06 02:11:45 21.2m
bob/bob.ip.draw@master (17/120 2019-11-06 02:32:57 15.22m
bob/bob.ip.gabor@master (18/120 2019-11-06 02:48:10 25.72m
bob/bob.learn.activation@master (19/120 2019-11-06 03:13:53 42.3m
bob/bob.learn.libsvm@master (20/120 2019-11-06 03:56:11 37.23m
bob/bob.learn.linear@master (21/120 2019-11-06 04:33:25 25.92m
bob/bob.learn.mlp@master (22/120 2019-11-06 04:59:20 28.83m
bob/bob.learn.boosting@master (23/120 2019-11-06 05:28:10 29.77m
bob/bob.db.iris@master (24/120 2019-11-06 05:57:58 13.22m
bob/bob.learn.em@master (25/120 2019-11-06 06:11:11 36.6m
bob/bob.db.wine@master (26/120 2019-11-06 06:47:47 15.0m
bob/bob.db.mnist@master (27/120 2019-11-06 07:02:47 15.55m
bob/bob.db.atnt@master (28/120 2019-11-06 07:18:21 12.62m
bob/bob.ip.facedetect@master (29/120 2019-11-06 07:31:00 27.82m
bob/bob.ip.optflow.hornschunck@master (30/120 2019-11-06 07:58:49 20.27m
bob/bob.ip.optflow.liu@master (31/120 2019-11-06 08:19:05 20.5m
bob/bob.ip.flandmark@master (32/120 2019-11-06 08:39:37 23.73m
bob/gridtk@master (33/120 2019-11-06 09:03:21 4.33m
bob/bob.ip.qualitymeasure@master (34/120 2019-11-06 09:07:41 28.5m
bob/bob.ip.skincolorfilter@master (35/120 2019-11-06 09:36:13 22.1m
bob/bob.ip.facelandmarks@master (36/120 2019-11-06 09:58:19 36.07m
bob/bob.ip.dlib@master (37/120 2019-11-06 10:34:30 33.27m
bob/bob.ip.mtcnn@master (38/120 2019-11-06 11:07:46 0.1m
bob/bob.db.arface@master (39/120 2019-11-06 11:07:52 15.88m
bob/bob.db.asvspoof@master (40/120 2019-11-06 11:23:45 23.02m
bob/bob.db.asvspoof2017@master (41/120 2019-11-06 11:46:47 16.05m
bob/bob.db.atvskeystroke@master (42/120 2019-11-06 12:02:50 20.17m
bob/bob.db.avspoof@master (43/120 2019-11-06 12:23:01 25.8m
bob/bob.db.banca@master (44/120 2019-11-06 12:48:49 14.4m
bob/bob.db.biosecure@master (45/120 2019-11-06 13:03:13 21.35m
bob/bob.db.biosecurid.face@master (46/120 2019-11-06 13:24:34 20.25m
bob/bob.db.casia_fasd@master (47/120 2019-11-06 13:44:49 21.93m
bob/bob.db.casme2@master (48/120 2019-11-06 14:06:45 25.67m
bob/bob.db.caspeal@master (49/120 2019-11-06 14:32:26 24.87m
bob/bob.db.cohface@master (50/120 2019-11-06 14:57:18 30.12m
bob/bob.db.frgc@master (51/120 2019-11-06 15:27:26 25.38m
bob/bob.db.gbu@master (52/120 2019-11-06 15:52:49 22.43m
bob/bob.db.hci_tagging@master (53/120 2019-11-06 16:15:15 112.58m
bob/bob.db.ijba@master (54/120 2019-11-06 18:08:05 43.1m
bob/bob.db.ijbc@master (55/120 2019-11-06 18:51:13 0.28m
--------------------------------------------- ------------------- -------
Pipeline 35218, Job 180562
```https://gitlab.idiap.ch/bob/bob.pad.face/-/issues/33Remove dependencies with caffe2020-02-14T16:15:23ZTiago de Freitas PereiraRemove dependencies with caffeHi guys, is it doable, in the short term, to remove the dependencies with caffe in this package?
As far as I know, this package uses the face detection and annotations from `bob.ip.mtcnn`.
@heusch mentioned that this could be replaced b...Hi guys, is it doable, in the short term, to remove the dependencies with caffe in this package?
As far as I know, this package uses the face detection and annotations from `bob.ip.mtcnn`.
@heusch mentioned that this could be replaced by a tensorflow implementation of mtcnn.
Is this doable?
ping https://gitlab.idiap.ch/bob/bob.nightlies/commit/0777c2b4548254e7663fd522ffc5500c3373c37e#note_48670
thankshttps://gitlab.idiap.ch/bob/bob.measure/-/issues/61absolute numbers for errors are wrong2020-02-14T16:15:23ZGuillaume HEUSCHabsolute numbers for errors are wrongHi @amohammadi,
As already pointed in the mailing-list (https://groups.google.com/forum/#!topic/bob-devel/RXsX2kgjs1M), the numbers of misclassified and total examples are wrong. Here's an illustration:
```
============== ============...Hi @amohammadi,
As already pointed in the mailing-list (https://groups.google.com/forum/#!topic/bob-devel/RXsX2kgjs1M), the numbers of misclassified and total examples are wrong. Here's an illustration:
```
============== =============== ================
.. Development Evaluation
============== =============== ================
APCER (attack) 7.7% 13.1%
APCER 7.7% 13.1%
BPCER 1.0% 9.7%
ACER 4.3% 11.4%
FTA 0.7% 0.6%
FPR 7.7% (451/1321) 13.1% (749/1571)
FNR 1.0% (13/5880) 9.7% (153/5729)
HTER 4.3% 11.4%
FAR 7.6% 13.0%
FRR 1.7% 10.3%
PRECISION 0.7 0.7
RECALL 1.0 0.9
F1_SCORE 0.8 0.8
```
When you look at FPR on Evaluation set for instance, 749/1571 * 100 = 47.1, which is different from 13.1%. Actually, the total number of examples have been swapped, since 749/5729 * 100 = 13.1 and 153/1571 * 100 = 9.7Amir MOHAMMADIAmir MOHAMMADIhttps://gitlab.idiap.ch/bob/bob.db.casiasurf/-/issues/4Database not available anymore ?2020-02-14T16:15:23ZGuillaume HEUSCHDatabase not available anymore ?Guillaume HEUSCHGuillaume HEUSCH