Comments (16)
Did you run python download_data.py --kitti_url URL_YOU_RETRIEVED
? This should download and prepare all data.
from multinet.
yeah I used python download_data.py --kitti_url URL_YOU_RETRIEVED
to retrieve data. And it said all done. the problem showed up when try to use train.py. And I tracked the error line to KittiSeg.json
found the URL is empty.
from multinet.
This message comes, when no folder data_road
cannot be found. Can you check whether there is a folder data_road
in RUNS
or $TV_DIR_RUNS
?
from multinet.
my data_road is in MultiNet/DATA
, is it supposed to be in RUNS/
?
from multinet.
No, sry it should be in DATA
. Is there a dir data_road
?
from multinet.
yep. there is.
ubuntu@ip-172-30-5-78:~/didicompetetion/Hao/MultiNet/DATA$ ls
data_road data_road.zip KittiBox vgg16.npy
from multinet.
And I after I put the URL manually, new error occurred:
2017-03-21 14:58:42,749 INFO Initialize training folder
2017-03-21 14:58:42,749 INFO f: <open file u'/home/ubuntu/didicompetetion/Hao/MultiNet/hypes/../submodules/KittiSeg/hypes/KittiSeg.json', mode 'r' at 0x7fa81a9dd540>
Traceback (most recent call last):
File "train.py", line 615, in <module>
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 44, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train.py", line 594, in main
subhypes, submodules, subgraph, tv_sess = build_united_model(hypes)
File "train.py", line 512, in build_united_model
subhypes[model] = json.load(f)
File "/usr/lib/python2.7/json/__init__.py", line 291, in load
**kw)
File "/usr/lib/python2.7/json/__init__.py", line 339, in loads
return _default_decoder.decode(s)
File "/usr/lib/python2.7/json/decoder.py", line 364, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/usr/lib/python2.7/json/decoder.py", line 380, in raw_decode
obj, end = self.scan_once(s, idx)
ValueError: Expecting property name: line 17 column 5 (char 544)
It seems the URL is not readable?
from multinet.
The code tries to download the data in kitti_seg_input. All files seams to be there. The routine should be skipped at this : line
Can you check, why if os.path.exists(vgg_weights) and os.path.exists(kitti_road_dir)
returns false? Is data_dir
set correctly?
from multinet.
Hi, I think I found the issue. Can you try using commit c1612e3 and run training again?
from multinet.
no, still not working
2017-03-21 15:18:19,534 INFO Initialize training folder
2017-03-21 15:18:19,534 INFO f: <open file u'/home/ubuntu/didicompetetion/Hao/MultiNet/hypes/../submodules/KittiSeg/hypes/KittiSeg.json', mode 'r' at 0x7f112a85d540>
Traceback (most recent call last):
File "train.py", line 616, in <module>
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 44, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train.py", line 595, in main
subhypes, submodules, subgraph, tv_sess = build_united_model(hypes)
File "train.py", line 513, in build_united_model
subhypes[model] = json.load(f)
File "/usr/lib/python2.7/json/__init__.py", line 291, in load
**kw)
File "/usr/lib/python2.7/json/__init__.py", line 339, in loads
return _default_decoder.decode(s)
File "/usr/lib/python2.7/json/decoder.py", line 364, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/usr/lib/python2.7/json/decoder.py", line 380, in raw_decode
obj, end = self.scan_once(s, idx)
ValueError: Expecting property name: line 17 column 5 (char 544)
from multinet.
Can you checkout the unmodified hype? It should work without setting the kitti_url.
The quoted issue indicates that your hype does not follow the .json
specification (Forgot using quotes when pasting the kitti url?).
from multinet.
yeah that error fixed! but another one showed up.. lol
Traceback (most recent call last):
File "train.py", line 618, in <module>
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 44, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train.py", line 597, in main
subhypes, submodules, subgraph, tv_sess = build_united_model(hypes)
File "train.py", line 537, in build_united_model
first_iter)
File "train.py", line 133, in build_training_graph
decoded_logits = objective.decoder(hypes, logits, train=True)
File "/home/ubuntu/didicompetetion/Hao/MultiNet/submodules/KittiSeg/hypes/../decoder/kitti_multiloss.py", line 48, in decoder
decoded_logits['logits'] = logits['fcn_logits']
KeyError: 'fcn_logits'
And it happened after running several layers.
from multinet.
This looks as if you are using an old version of KittiSeg. Try updating all submodules by running:
git pull
git submodule update --recursive
from multinet.
yeah fixed after review #10. One question, it asked like this:
ERROR File '/home/ubuntu/didicompetetion/Hao/MultiNet/hypes/../DATA/weights/vgg16.npy' not found. Download it from ftp://mi.eng.cam.ac.uk/pub/mttt2/models/vgg16.npy
ERROR File '/home/ubuntu/didicompetetion/Hao/MultiNet/hypes/../DATA/vgg16.npy' not found. Download it from ftp://mi.eng.cam.ac.uk/pub/mttt2/models/vgg16.npy
So I just put vgg16.npy
both in DATA/
and DATA/weights/
, that makes me confused.
from multinet.
Yeah, the different submodules read the data from different location. Should properly fix this. For now you can avoid downloading it twice by creating a symlink ln -s weights/vgg16.npy vgg16.npy
or vice versa.
from multinet.
cool, Ill close this issue, thanks for helping me! :)
from multinet.
Related Issues (20)
- No module named 'annolist' HOT 1
- How does Detection/Decoder module work?
- The ftp link to download the vgg16.npy file isn't accessible HOT 1
- About download_data.py HOT 4
- How to train with other models, like resNet, YOLO, SqueezeNet?
- I do not understand the number in paper.(Convolution and concatenated) HOT 2
- AssertionError assert(image_height >= shape[0]) in demo.py
- request for updating the codes HOT 3
- A question
- some errors when do test
- train multinet2.json out of memory seriously
- Does the codes update to v2 now?
- how to trian my dataset on Multinet3 HOT 1
- terminate called after throwing an instance of 'std::bad_alloc'
- ResourceExhaustedError (see above for traceback): OOM when allocating tensor of shape [7,7,512,4096] and type float [[Node: fc6/weights/Adam/Initializer/zeros = Const[dtype=DT_FLOAT, value=Tensor<type: float shape: [7,7,512,4 096] values: [[[0 0 0]]]...>, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]] HOT 1
- subprocess.CalledProcessError: Command returned non-zero exit status -11 HOT 1
- The kitti download url is not accessible now, can not finish running download_data.py HOT 3
- About training HOT 1
- trained model HOT 1
- /bin/bash: makecython++:command not found
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from multinet.