Comments (10)
raphaeljolivet
commented on July 17, 2024
6
Ok, so finally, I am able to have it work.
In summary :
- I need to use python2.7
- I had to downgrade to older version of numpy (1.15) because Skimage is incompatible with last version
- I had to download inception from the source, because installing it from pip does not include inception_model. I just copied it in the project folder, added a couple of init.py and added
.to thePYTHONPATH
For information here is a frozen requirement.txt :
numpy==1.15.4
tensorflow==1.12.0
scikit-image==0.14.1
matplotlib==2.2.3
pandas==0.23.4
from deepsolar.
raphaeljolivet
commented on July 17, 2024
2
Please update requirement.txt and README accordingly.
from deepsolar.
raphaeljolivet
commented on July 17, 2024
2
Hi,
Look at my fork here:
https://github.com/raphaeljolivet/DeepSolar
I have been able to run the classification script, by integrating directly the inception library and with the dependencies listed in requirements.txt
Please note that I have simplified the usage of test_classification here, it does not require the generate_data_list.py anymore. Please refer to the header of test_classificiation.py for usage.
from deepsolar.
CoolSciGuy
commented on July 17, 2024
Hi @raphaeljolivet, were you able to download training and eval sets?
from deepsolar.
raphaeljolivet
commented on July 17, 2024
Yes I did.
…-------- Message d'origine --------
On 8 févr. 2019 15:37, CoolSciGuy a écrit :
Hi ***@***.***(https://github.com/raphaeljolivet), were you able to download training and eval sets?
—
You are receiving this because you were mentioned.
Reply to this email directly, [view it on GitHub](#7 (comment)), or [mute the thread](https://github.com/notifications/unsubscribe-auth/ABJVwGQ4cpzy_JqKEpdaDcmdnMyFFLLeks5vLYu-gaJpZM4aEEVd).
from deepsolar.
CoolSciGuy
commented on July 17, 2024
Yes I did.
…
-------- Message d'origine -------- On 8 févr. 2019 15:37, CoolSciGuy a écrit :
Hi @.***(https://github.com/raphaeljolivet), were you able to download training and eval sets? — You are receiving this because you were mentioned. Reply to this email directly, [view it on GitHub](#7 (comment)), or mute the thread.
Thanks for responding, did you follow instructions as suggested by developer? I am having no luck.
from deepsolar.
sassej
commented on July 17, 2024
I am getting this error:
$ python train_classification.py --fine_tune=True
Training set built. Size: 366467
Traceback (most recent call last):
File "train_classification.py", line 262, in
train()
File "train_classification.py", line 117, in train
scope=None)
File "/Users/sassej/DeepSolar/inception_model.py", line 84, in inference
with slim.arg_scope([slim.ops.conv2d, slim.ops.fc], weight_decay=0.00004):
AttributeError: 'module' object has no attribute 'arg_scope'
from deepsolar.
namgivu
commented on July 17, 2024
I tried your fork and cannot get install -r requirements.txt working
I'm using python 2.7.18 virtualenv thru pyenv
namgivu@localhost:~/code/b/deepsonar/zref/raphaeljolivet-DeepSolar
$ ./.venv/bin/python -m pip install -r requirements.txt
DEPRECATION: Python 2.7 reached the end of its life on January 1st, 2020. Please upgrade your Python as Python 2.7 is no longer maintained. pip 21.0 will drop support for Python 2.7 in January 2021. More details about Python 2 support in pip can be found at https://pip.pypa.io/en/latest/development/release-process/#python-2-support pip 21.0 will remove support for this functionality.
Collecting numpy==1.15.4
Using cached numpy-1.15.4-cp27-cp27mu-manylinux1_x86_64.whl (13.8 MB)
Collecting tensorflow==1.12.0
Using cached tensorflow-1.12.0-cp27-cp27mu-manylinux1_x86_64.whl (83.1 MB)
Collecting scikit-image==0.14.1
Using cached scikit_image-0.14.1-cp27-cp27mu-manylinux1_x86_64.whl (25.4 MB)
Collecting matplotlib==2.2.3
Using cached matplotlib-2.2.3-cp27-cp27mu-manylinux1_x86_64.whl (12.6 MB)
Collecting pandas==0.23.4
Using cached pandas-0.23.4-cp27-cp27mu-manylinux1_x86_64.whl (8.9 MB)
Collecting fiona
Downloading Fiona-1.8.20.tar.gz (1.3 MB)
|████████████████████████████████| 1.3 MB 1.6 MB/s
ERROR: Command errored out with exit status 1:
command: /home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/tmp/pip-install-okL5YE/fiona/setup.py'"'"'; __file__='"'"'/tmp/pip-install-okL5YE/fiona/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' egg_info --egg-base /tmp/pip-pip-egg-info-Codbjh
cwd: /tmp/pip-install-okL5YE/fiona/
Complete output (2 lines):
Failed to get options via gdal-config: [Errno 2] No such file or directory
A GDAL API version must be specified. Provide a path to gdal-config using a GDAL_CONFIG environment variable or use a GDAL_VERSION environment variable.
----------------------------------------
ERROR: Command errored out with exit status 1: python setup.py egg_info Check the logs for full command output.
removing two lines in the requirements.txt below to get it thru
fiona
opencv-python
numpy==1.15.4
tensorflow==1.12.0
scikit-image==0.14.1
matplotlib==2.2.3
pandas==0.23.4
# fiona
# opencv-python
shapely
pyproj
progressbar2==3.39.2
from deepsolar.
namgivu
commented on July 17, 2024
I have succeeded running the train classification with your fork version - great thanks for the fix for inception
./.venv/bin/python train_classification.py --fine_tune=False
Though I got the error
ValueError: Dimension 3 in both shapes must be equal, but are 96 and 32. Shapes are [32,35,35,96] and [32,35,35,32].
From merging shape 2 with other shapes. for 'inception_v3/mixed_35x35x256a/concat/concat_dim' (op: 'Pack') with input shapes: [32,35,35,64], [32,35,35,64], [32,35,35,96], [32,35,35,32].
Would be higly appreciated as you would help to have a look.
In full as below
namgivu@localhost:~/code/b/deepsonar/DeepSolar/zref/raphaeljolivet-DeepSolar
$ ll
total 88
drwxrwxr-x 6 namgivu namgivu 4096 Jun 4 12:45 ./
drwxrwxr-x 4 namgivu namgivu 4096 Jun 4 09:56 ../
-rw-rw-r-- 1 namgivu namgivu 8196 Jun 4 09:56 .DS_Store
-rwxrwxr-x 1 namgivu namgivu 2725 Jun 4 09:56 generate_data_list.py*
drwxrwxr-x 8 namgivu namgivu 4096 Jun 4 09:56 .git/
drwxrwxr-x 3 namgivu namgivu 4096 Jun 4 10:36 .idea/
drwxrwxr-x 4 namgivu namgivu 4096 Jun 4 09:56 inception/
-rwxrwxr-x 1 namgivu namgivu 0 Jun 4 09:56 __init__.py*
-rw-rw-r-- 1 namgivu namgivu 7 Jun 4 09:56 .python-version
-rw-rw-r-- 1 namgivu namgivu 2893 Jun 4 09:56 README.md
-rw-rw-r-- 1 namgivu namgivu 147 Jun 4 10:06 requirements.txt
lrwxrwxrwx 1 namgivu namgivu 42 Jun 4 12:45 SPI_eval -> /media/namgivu/Elements/deepsonar/SPI_eval
-rwxrwxr-x 1 namgivu namgivu 3004 Jun 4 09:56 test_classification.py*
-rwxrwxr-x 1 namgivu namgivu 10541 Jun 4 09:56 test_segmentation.py*
-rwxrwxr-x 1 namgivu namgivu 10551 Jun 4 09:56 train_classification.py*
-rwxrwxr-x 1 namgivu namgivu 8087 Jun 4 09:56 train_segmentation.py*
drwxrwxr-x 6 namgivu namgivu 4096 Jun 4 10:07 .venv/
namgivu@localhost:~/code/b/deepsonar/DeepSolar/zref/raphaeljolivet-DeepSolar
$ ll
total 88
drwxrwxr-x 6 namgivu namgivu 4096 Jun 4 12:45 ./
drwxrwxr-x 4 namgivu namgivu 4096 Jun 4 09:56 ../
-rw-rw-r-- 1 namgivu namgivu 8196 Jun 4 09:56 .DS_Store
-rwxrwxr-x 1 namgivu namgivu 2725 Jun 4 09:56 generate_data_list.py*
drwxrwxr-x 8 namgivu namgivu 4096 Jun 4 09:56 .git/
drwxrwxr-x 3 namgivu namgivu 4096 Jun 4 10:36 .idea/
drwxrwxr-x 4 namgivu namgivu 4096 Jun 4 09:56 inception/
-rwxrwxr-x 1 namgivu namgivu 0 Jun 4 09:56 __init__.py*
-rw-rw-r-- 1 namgivu namgivu 7 Jun 4 09:56 .python-version
-rw-rw-r-- 1 namgivu namgivu 2893 Jun 4 09:56 README.md
-rw-rw-r-- 1 namgivu namgivu 147 Jun 4 10:06 requirements.txt
lrwxrwxrwx 1 namgivu namgivu 42 Jun 4 12:45 SPI_eval -> /media/namgivu/Elements/deepsonar/SPI_eval/
-rwxrwxr-x 1 namgivu namgivu 3004 Jun 4 09:56 test_classification.py*
-rwxrwxr-x 1 namgivu namgivu 10541 Jun 4 09:56 test_segmentation.py*
-rwxrwxr-x 1 namgivu namgivu 10551 Jun 4 09:56 train_classification.py*
-rwxrwxr-x 1 namgivu namgivu 8087 Jun 4 09:56 train_segmentation.py*
drwxrwxr-x 6 namgivu namgivu 4096 Jun 4 10:07 .venv/
namgivu@localhost:~/code/b/deepsonar/DeepSolar/zref/raphaeljolivet-DeepSolar
$ ./.venv/bin/python train_classification.py --fine_tune=False
Traceback (most recent call last):
File "train_classification.py", line 264, in <module>
train()
File "train_classification.py", line 83, in train
raise EnvironmentError('Data list not existed. Please run generate_data_list.py first.')
EnvironmentError: Data list not existed. Please run generate_data_list.py first.
namgivu@localhost:~/code/b/deepsonar/DeepSolar/zref/raphaeljolivet-DeepSolar
$ ./.venv/bin/python generate_data_list.py
Train set list done. # positive samples: 0 # negative samples: 0
Validation set list done. # positive samples: 0 # negative samples: 0
Test set list done. # positive samples: 1221 # negative samples: 92279
namgivu@localhost:~/code/b/deepsonar/DeepSolar/zref/raphaeljolivet-DeepSolar
$ ./.venv/bin/python train_classification.py --fine_tune=False
Training set built. Size: 0
Traceback (most recent call last):
File "train_classification.py", line 264, in <module>
train()
File "train_classification.py", line 119, in train
scope=None)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/inception/inception_model.py", line 95, in inference
scope=scope)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/inception/slim/inception_model.py", line 126, in inception_v3
net = tf.concat(3, [branch1x1, branch5x5, branch3x3dbl, branch_pool])
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1121, in concat
dtype=dtypes.int32).get_shape().assert_is_compatible_with(
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1050, in convert_to_tensor
as_ref=False)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1146, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 971, in _autopacking_conversion_function
return _autopacking_helper(v, dtype, name or "packed")
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 923, in _autopacking_helper
return gen_array_ops.pack(elems_as_tensors, name=scope)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 4875, in pack
"Pack", values=values, axis=axis, name=name)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1792, in __init__
control_input_ops)
File "/home/namgivu/code/b/deepsonar/zref/raphaeljolivet-DeepSolar/.venv/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1631, in _create_c_op
raise ValueError(str(e))
ValueError: Dimension 3 in both shapes must be equal, but are 96 and 32. Shapes are [32,35,35,96] and [32,35,35,32].
From merging shape 2 with other shapes. for 'inception_v3/mixed_35x35x256a/concat/concat_dim' (op: 'Pack') with input shapes: [32,35,35,64], [32,35,35,64], [32,35,35,96], [32,35,35,32].
from deepsolar.
namgivu
commented on July 17, 2024
Hi @raphaeljolivet,
May you have free time, please have a look at the error here[(https://github.com//issues/7#issuecomment-854381647). Thanks a lot!
from deepsolar.
Related Issues (17)
- Dataset release HOT 4
- Segmentation before Classification? HOT 2
- error in test classification script HOT 9
- Low Recall Rate on the test set. HOT 3
- KeyError: 'r '
- TensorFlow SavedModels
- What's the image resolution?
- ImportError: No module named inception HOT 5
- generating the data list
- Link for inception Library HOT 1
- circles in example image seem a bit off HOT 2
- How must the satellite images look like? HOT 8
- Data Dictionary HOT 2
- License?
- Train and Eval Set not available HOT 21
- Access Denied for Training and Evaluation Dataset HOT 1
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 deepsolar.