I'm trying to prepare training data with this detail :
ArcGIS Pro 2.4.2
inRaster = "E:\Work\ArcDL\Base\MANADO_FIX.tif" (raster 8bit unsigned, thematic, with nodata=0)
out_folder = "E:\Work\ArcDL\gtg6"
in_training = "E:\Work\ArcDL\Experiment_BuildFoot_2\MyProject\Shape\House.shp" (shp that has Classvalue, Classname, RED, GREEN, BLUE field)
image_chip_format = "TIFF"
tile_size_x = "256"
tile_size_y = "256"
stride_x="128"
stride_y="128"
output_nofeature_tiles="ONLY_TILES_WITH_FEATURES"
metadata_format="Labeled_Tiles"
start_index = 0
classvalue_field = "Classvalue"
buffer_radius = 1
in_mask_polygons = "E:\Work\ArcDL\Experiment_BuildFoot_2\MyProject\Shape\Mask.shp"
rotation_angle = 0
I run my prepare data syntax just like this :
data = prepare_data('gtg6')
But I always ended up in this kind of error for labeled_tiles metadata format, there's no further explanation and I cant use the data for training since data.show_batch() will result in OSError: -2
Any solution?
Thanks in advance.
Solved! Go to Solution.
Thank you, I've been struggling for weeks in these prepare data thing... I don't have problem with pascal VOC or Classified Tiles metadata format from before.
Can you try install pillow again
pip uninstall pillow
and then install it again using
pip install pillow
AFAIK it's installed by using "conda install -c pytorch -c fastai fastai=1.0.39 pytorch=1.0.0 torchvision" but to be sured I created new environment again and installed required moduls using above command as sugested and test prepare_data() command again and stil it resulted in error.
Here's my environment clone from default environment of ArcGIS pro before running above command :
arcgis==1.6.1
asn1crypto==0.24.0
atomicwrites==1.3.0
attrs==19.1.0
backcall==0.1.0
bleach==3.1.0
certifi==2019.3.9
cffi==1.12.2
cftime==1.0.0b1
chardet==3.0.4
colorama==0.4.1
cryptography==2.6.1
cycler==0.10.0
decorator==4.4.0
defusedxml==0.5.0
despatch==0.1.0
entrypoints==0.3
et-xmlfile==1.0.1
fastcache==1.0.2
future==0.17.1
h5py==2.9.0
html5lib==1.0.1
idna==2.8
ipykernel==5.1.0
ipython==7.4.0
ipython-genutils==0.2.0
ipywidgets==7.4.2
jdcal==1.4
jedi==0.13.3
Jinja2==2.10.1
jsonschema==3.0.1
jupyter-client==5.2.4
jupyter-console==6.0.0
jupyter-core==4.4.0
jupyterlab==0.35.4
jupyterlab-server==0.2.0
keyring==19.0.1
kiwisolver==1.0.1
MarkupSafe==1.1.1
matplotlib==3.0.3
mistune==0.8.4
mkl-fft==1.0.10
mkl-random==1.0.2
more-itertools==6.0.0
mpmath==1.1.0
nbconvert==5.4.1
nbformat==4.4.0
netCDF4==1.5.0.1
nose==1.3.7
notebook==5.7.8
numexpr==2.6.9
numpy==1.16.2
openpyxl==2.6.1
pandas==0.24.2
pandocfilters==1.4.2
parso==0.3.4
pickleshare==0.7.5
pluggy==0.9.0
prometheus-client==0.6.0
prompt-toolkit==2.0.9
py==1.8.0
pycparser==2.19
Pygments==2.3.1
pyOpenSSL==19.0.0
pyparsing==2.4.0
pyrsistent==0.14.11
pyshp==1.2.12
PySocks==1.6.8
pytest==4.4.0
python-dateutil==2.8.0
pytz==2018.9
pywin32-ctypes==0.2.0
pywinpty==0.5
pyzmq==18.0.0
requests==2.21.0
scipy==1.2.1
Send2Trash==1.5.0
simplegeneric==0.8.1
six==1.12.0
sympy==1.3
terminado==0.8.1
testpath==0.4.2
tornado==6.0.2
traitlets==4.3.2
urllib3==1.24.1
wcwidth==0.1.7
webencodings==0.5.1
widgetsnbextension==3.4.2
win-inet-pton==1.1.0
wincertstore==0.2
winkerberos==0.7.0
x86cpu==0.4
xlrd==1.2.0
xlwt==1.3.0
and here's my environment after running above command :
arcgis==1.6.2
asn1crypto==1.2.0
atomicwrites==1.3.0
attrs==19.3.0
backcall==0.1.0
bleach==3.1.0
blis==0.2.4
Bottleneck==1.3.1
certifi==2019.11.28
cffi==1.13.2
cftime==1.0.0b1
chardet==3.0.4
colorama==0.4.1
cryptography==2.8
cycler==0.10.0
cymem==2.0.2
dataclasses==0.6
decorator==4.4.1
defusedxml==0.6.0
despatch==0.1.0
entrypoints==0.3
et-xmlfile==1.0.1
fastai==1.0.39
fastcache==1.1.0
fastprogress==0.1.22
future==0.18.2
h5py==2.9.0
html5lib==1.0.1
idna==2.8
importlib-metadata==1.1.0
ipykernel==5.1.3
ipython==7.9.0
ipython-genutils==0.2.0
ipywidgets==7.5.1
jdcal==1.4.1
jedi==0.15.1
Jinja2==2.10.3
json5==0.8.5
jsonschema==3.2.0
jupyter-client==5.3.4
jupyter-console==5.2.0
jupyter-core==4.6.1
jupyterlab==1.2.3
jupyterlab-server==1.0.6
keyring==19.2.0
kiwisolver==1.1.0
MarkupSafe==1.1.1
matplotlib==3.0.3
mistune==0.8.4
mkl-fft==1.0.12
mkl-random==1.0.2
more-itertools==7.2.0
mpmath==1.1.0
murmurhash==1.0.2
nb-conda==2.2.1
nb-conda-kernels==2.2.2
nbconvert==5.6.1
nbformat==4.4.0
netCDF4==1.5.0.1
nose==1.3.7
notebook==6.0.2
numexpr==2.6.9
numpy==1.16.2
olefile==0.46
openpyxl==3.0.2
packaging==19.2
pandas==0.25.3
pandocfilters==1.4.2
parso==0.5.1
pickleshare==0.7.5
Pillow==6.2.1
plac==0.9.6
pluggy==0.13.1
preshed==2.0.1
prometheus-client==0.6.0
prompt-toolkit==3.0.2
py==1.8.0
pycparser==2.19
Pygments==2.5.2
pyOpenSSL==19.1.0
pyparsing==2.4.5
pyrsistent==0.15.6
pyshp==1.2.12
PySocks==1.7.1
pytest==5.3.1
python-dateutil==2.8.1
pytz==2019.3
pywin32==223
pywin32-ctypes==0.2.0
pywinpty==0.5.5
PyYAML==3.12
pyzmq==18.1.0
requests==2.22.0
scipy==1.2.1
Send2Trash==1.5.0
simplegeneric==0.8.1
six==1.13.0
spacy==2.1.8
srsly==0.1.0
sympy==1.4
terminado==0.8.3
testpath==0.4.4
thinc==7.0.8
torch==1.0.0
torchvision==0.2.2
tornado==6.0.3
tqdm==4.40.0
traitlets==4.3.3
typing==3.6.4
urllib3==1.24.2
wasabi==0.2.2
wcwidth==0.1.7
webencodings==0.5.1
widgetsnbextension==3.5.1
win-inet-pton==1.1.0
wincertstore==0.2
winkerberos==0.7.0
x86cpu==0.4
xlrd==1.2.0
xlwt==1.3.0
zipp==0.6.0
it seems the pillow were installed by command above using conda install, and this is what changed :
anything wrong with my setup or I missed something?
Thanks in advance.
To verify your pillow installation try to load an exported image chip directly using the following code
from PIL import Image
Image.open(image_path)
it should give a similar output as below
Now it seems to make sense, it resulted in an error :
so what should I do ? in another side I need this conda install -c pytorch -c fastai fastai=1.0.39 pytorch=1.0.0 torchvision command to prepare_data()
One more thing, it can read normal image png, but it won't work from image created from export training data
Can you uninstall pillow
pip uninstall pillow
and then install it again using
pip install pillow
If still you are not able to read the image please attach the image here.
Okay, now I can read the Image from export training data but it leaves some error and I'm afraid it will cause something wrong later :
image successfully read :
should I run :
conda install -c fastai nvidia-ml-py3
since I'm using GPU for this
Big Data Manado we can ignore this warning for now.
Ok, Thank you for your help.