prgumd / evdodgenet Goto Github PK
View Code? Open in Web Editor NEWEVDodgeNet: Deep Dynamic Obstacle Dodging with event cameras
Home Page: http://prg.cs.umd.edu/EVDodgeNet
License: BSD 3-Clause "New" or "Revised" License
EVDodgeNet: Deep Dynamic Obstacle Dodging with event cameras
Home Page: http://prg.cs.umd.edu/EVDodgeNet
License: BSD 3-Clause "New" or "Revised" License
Hello. While trying to understand the EVSegNet code you provided, I have seen that the RunEVSegNet.py and TrainEVSegNet.py scripts have a function named "SetupAll" where certain files named "DirNames.txt" and "Train.txt" are trying to be read, like the following:
EVDodgeNet/code/EVSegNet/RunEVSegNet.py
Lines 60 to 62 in 0b6f6a0
Checking the dataset from https://drive.google.com/open?id=1pJSVXtRlTU4_b-I8oakoZtl1ChcG0OiQ and also checking the dataset structure desciption in https://github.com/prgumd/EVDodgeNet/wiki/Access-Data-Set-Using-ROS-Python, I could not find any file named "DirNames.txt" or "Train.txt". What am I missing here, can you guide me on this?
Hello. The following code line:
EVDodgeNet/code/EVSegNet/RunEVSegNet.py
Line 291 in 0b6f6a0
produces a "NameError" since "global name 'tu' is not defined".
I have download your dataset on https://github.com/prgumd/EVDodgeNet/wiki/Access-Data-Set-Using-ROS-Python.
But when I wanted to run your code, I encountered the following problems.
Follow the guide, I run the code about EVDeblurNet, but IOError(can't find DirNames.txt)
Then I found that this file was generate in DataParseUnsrack.py, but print(CurrReadPath + 'events' + os.sep + '*.png')
is not in your provided dataset.
I'm not sure whether my idea is correct. I would appreciate your reply.
There is something wrong in the dataset you supplied , because there is no downfacing rosbag .what's more, could you tell me the input and output of deblurnet and homography net.I can not understand the wiki instruction.
I am trying to read pretrained model files but I got error and could not load any of them.
This is just an example of one of pretrained models. I tried every one of them.
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.DataLossError: Unable to open table file EVDodgeNet/code/HomographyNetUnsup/Checkpoints/HomographySUSL1LR1e-4/199model.ckpt.data-00000-of-00001: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
[[node save/RestoreV2 (defined at /drone/EVDodgeNet/code/HomographyNetUnsup/RunEVHomographyNet.py:277) ]]
Original stack trace for u'save/RestoreV2':
File "/drone/EVDodgeNet/code/HomographyNetUnsup/RunEVHomographyNet.py", line 378, in <module>
main()
File "/drone/EVDodgeNet/code/HomographyNetUnsup/RunEVHomographyNet.py", line 375, in main
TestOperation(PatchPH, I1PH, I2PH, PatchSize, ModelPath, ReadPath, WritePath, TrainNames, NumTrainSamples, CropType)
File "/drone/EVDodgeNet/code/HomographyNetUnsup/RunEVHomographyNet.py", line 277, in TestOperation
Saver = tf.train.Saver()
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 825, in __init__
self.build()
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 837, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 875, in _build
build_restore=build_restore)
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 508, in _build_internal
restore_sequentially, reshape)
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 328, in _AddRestoreOps
restore_sequentially)
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 575, in bulk_restore
return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1696, in restore_v2
name=name)
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
op_def=op_def)
File "/miniconda3/envs/tf14/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2005, in __init__
self._traceback = tf_stack.extract_stack()
Hello,
I need your dataset and code to compare your paper with my work. When will you release them?
Thanks.
Hello, thanks for your work.
I am trying to use the EVSegNet code you provided. There is a syntax error in the following part of the code:
EVDodgeNet/code/EVSegNet/RunEVSegNet.py
Lines 280 to 283 in 0b6f6a0
Specifically, lines 281 and 282 should be switched.
Hello. I found out that your code also depends on scikit-image package, which is missing in dependencies list at https://github.com/prgumd/EVDodgeNet/wiki/RunningCode#dependencies , so you may consider adding it there.
Thanks again for your work.
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.