akosiorek / hart Goto Github PK
View Code? Open in Web Editor NEWHierarchical Attentive Recurrent Tracking
License: GNU General Public License v3.0
Hierarchical Attentive Recurrent Tracking
License: GNU General Public License v3.0
how to run tensorboard in the checkpoints folder to visualise training progres?
thanks
Hi,
I'm using tensorflow 1.2.1 an i get the following error:
`ImportErrorTraceback (most recent call last)
in ()
9 from hart.data.kitti.tools import get_data
10 from hart.model import util
---> 11 from hart.model.attention_ops import FixedStdAttention
12 from hart.model.eval_tools import log_norm, log_ratios, log_values, make_expr_logger
13 from hart.model.tracker import HierarchicalAttentiveRecurrentTracker as HART
/home/wscuser/notebooks/hart/hart/model/attention_ops.py in ()
22 import numpy as np
23 import tensorflow as tf
---> 24 from tensorflow.contrib.rnn.python.ops.core_rnn_cell_impl import LSTMCell
25 from tensorflow.python.ops.rnn_cell_impl import _RNNCell as RNNCell
26 from tensorflow.python.util import nest
ImportError: No module named core_rnn_cell_impl`
can the appearance attention replaced by saliency detetion?
what is the appearance attention?
Hi,
Have you done an experiment on the OTB or VOT dataset?
Hi! when I ready to run train_hart_kitti.py script, there is a wrong msg "No module named 'component'
".The whole code is as below:
Traceback (most recent call last):
File "../hart/scripts/train_hart_kitti.py", line 34, in <module>
from hart.data.kitti.tools import get_data
File "../hart/scripts/../hart/data/kitti/tools.py", line 28, in <module>
import neurocity as nct
File "../hart/scripts/../neurocity/__init__.py", line 22, in <module>
from component.model.base import train_mode,test_mode,mode
ImportError: No module named 'component'
I wonder whether you use the saliency in this paper,and it means what is the difference between the saliency and the attentive? I want to apply the saliency to the tracking
could you offer the pytorch code?
thanks
why only track the small car , not the left big car?
We are trying to run your code on another dataset with diffrenet dimension images, however, we get wrong bounding boxes. we are assuming you scale down and/or change coordinates of the bounding boxes in the labels, would you please explain how did you use bounding boxes coordinates?
Also, when you use the kitti datset the bounding boxes coordinates seems to be decimal, wuold you please explain how you read them?
Thank you so much.
where is the result when I run scripts/demo.ipynb?I found nothing
thanks
Hi,
I have a problem running the demo:
ImportError Traceback (most recent call last)
in ()
7
8 from hart.data import disp
----> 9 from hart.data.kitti.tools import get_data
10 from hart.model import util
11 from hart.model.attention_ops import FixedStdAttention
C:\Program Files\Anaconda3\Lib\site-packages\hart\hart\data\kitti\tools.py in ()
26 import tensorflow as tf
27
---> 28 import neurocity as nct
29 from neurocity.data import store
30 from neurocity.data import tools as data_tools
C:\Program Files\Anaconda3\Lib\site-packages\hart\neurocity_init_.py in ()
20 ########################################################################################
21
---> 22 from component.model.base import train_mode, test_mode, mode
23 from component import loss, layer
24 from component.model.model import Model
C:\Program Files\Anaconda3\Lib\site-packages\hart\neurocity\component_init_.py in ()
23
24 import tensorflow as tf
---> 25 from layer import Layer
26 from model.model import Model
27
C:\Program Files\Anaconda3\Lib\site-packages\hart\neurocity\component\layer.py in ()
26 import numpy as np
27
---> 28 from neurocity.component.model import base
29
30
C:\Program Files\Anaconda3\Lib\site-packages\hart\neurocity\component_init_.py in ()
23
24 import tensorflow as tf
---> 25 from layer import Layer
26 from model.model import Model
27
ImportError: cannot import name 'Layer'
Hello,
I met an error when running the training script. The error is below. I added the code to print out the value of len(v) and len(self).
/neurocity/data/store.py", line 87, in reset_data
assert len(v) == len(self), (len(v), len(self))
AssertionError: (1, 0)
Thanks!
--img_dir=path/to/image/folder means the training folder in the data_tracking_image_2?
get the error:
Traceback (most recent call last):
File "/home/cbl/PycharmProjects/hart-master/scripts/train_hart_kitti.py", line 141, in
truncated_threshold=1., occluded_threshold=1, reverse=True, mirror=True)
File "/home/cbl/PycharmProjects/hart-master/scripts/../hart/data/kitti/tools.py", line 475, in get_data
truncated_threshold=truncated_threshold, occluded_threshold=occluded_threshold)
File "/home/cbl/PycharmProjects/hart-master/scripts/../hart/data/kitti/parser.py", line 226, in init
img_folder_or_paths = self._get_img_paths()
File "/home/cbl/PycharmProjects/hart-master/scripts/../hart/data/kitti/parser.py", line 252, in _get_img_paths
folders = sorted(folders, key=lambda x: int(os.path.basename(x).split('.')[0]))
File "/home/cbl/PycharmProjects/hart-master/scripts/../hart/data/kitti/parser.py", line 252, in
folders = sorted(folders, key=lambda x: int(os.path.basename(x).split('.')[0]))
ValueError: invalid literal for int() with base 10: 'training'
('parser=', ArgumentParser(prog='train_hart_kitti.py', usage=None, description=None, version=None, formatter_class=<class 'argparse.HelpFormatter'>, conflict_handler='error', add_help=True))
('args.img_dir=', '/home/cbl/PycharmProjects/hart-master/KITTI_resize/data_tracking_image_2')
('args.label_dir=', '/home/cbl/PycharmProjects/hart-master/KITTI_resize/data_tracking_label_2')
('args.alexnet_dir=', '/home/cbl/PycharmProjects/hart-master/checkpoints')
could you give the example of the img_folder, label_folder, train_fraction, img_size?
I think my path is wrong
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.