Error when running run_sample_training_pipeline.sh

[Testbild]

Hi @matpalm ,
that is an awesome project you have here. I struggle a bit to get it running. I did the following (on my windows 11 machine):

create a virtual environment with python -m venv
install the requirements.txt in the virtual environement
run the run_sample_training_pipeline.sh

The labeling tool opens and works fine with the sample images from you. When it then comes to the materialise_label_db.py the following error appears:

So I tried to manually install skimage as it was reported missing. Then it said install scikit-image instead of skimage, but that is already satisfied.

(beeProject) C:\Users\Chrizzl\Documents\ObjectDetection\BeeProject\bnn>pip install skimage
Collecting skimage
  Downloading skimage-0.0.tar.gz (757 bytes)
  Preparing metadata (setup.py) ... error
  ERROR: Command errored out with exit status 1:
   command: 'C:\Users\Chrizzl\Documents\ObjectDetection\BeeProject\beeProject\Scripts\python.exe' -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'C:\\Users\\Chrizzl\\AppData\\Local\\Temp\\pip-install-pu5o48n4\\skimage_31623e2a30784bacaced383f1d540476\\setup.py'"'"'; __file__='"'"'C:\\Users\\Chrizzl\\AppData\\Local\\Temp\\pip-install-pu5o48n4\\skimage_31623e2a30784bacaced383f1d540476\\setup.py'"'"';f = getattr(tokenize, '"'"'open'"'"', open)(__file__) if os.path.exists(__file__) else io.StringIO('"'"'from setuptools import setup; setup()'"'"');code = f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' egg_info --egg-base 'C:\Users\Chrizzl\AppData\Local\Temp\pip-pip-egg-info-6acej1f8'
       cwd: C:\Users\Chrizzl\AppData\Local\Temp\pip-install-pu5o48n4\skimage_31623e2a30784bacaced383f1d540476\
  Complete output (3 lines):

  *** Please install the `scikit-image` package (instead of `skimage`) ***

  ----------------------------------------
WARNING: Discarding https://files.pythonhosted.org/packages/3b/ee/edbfa69ba7b7d9726e634bfbeefd04b5a1764e9e74867ec916113eeaf4a1/skimage-0.0.tar.gz#sha256=6c96a11d9deea68489c9b80b38fad1dcdab582c36d4fa093b99b24a3b30c38ec (from https://pypi.org/simple/skimage/). Command errored out with exit status 1: python setup.py egg_info Check the logs for full command output.
ERROR: Could not find a version that satisfies the requirement skimage (from versions: 0.0)
ERROR: No matching distribution found for skimage

(beeProject) C:\Users\Chrizzl\Documents\ObjectDetection\BeeProject\bnn>pip install scikit-image
Requirement already satisfied: scikit-image in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (0.18.3)
Requirement already satisfied: tifffile>=2019.7.26 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from scikit-image) (2021.11.2)
Requirement already satisfied: PyWavelets>=1.1.1 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from scikit-image) (1.2.0)
Requirement already satisfied: numpy>=1.16.5 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from scikit-image) (1.21.4)
Requirement already satisfied: scipy>=1.0.1 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from scikit-image) (1.7.2)
Requirement already satisfied: imageio>=2.3.0 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from scikit-image) (2.10.3)
Requirement already satisfied: pillow!=7.1.0,!=7.1.1,>=4.3.0 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from scikit-image) (8.4.0)
Requirement already satisfied: matplotlib!=3.0.0,>=2.0.0 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from scikit-image) (3.4.3)
Requirement already satisfied: networkx>=2.0 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from scikit-image) (2.6.3)
Requirement already satisfied: python-dateutil>=2.7 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from matplotlib!=3.0.0,>=2.0.0->scikit-image) (2.8.2)
Requirement already satisfied: pyparsing>=2.2.1 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from matplotlib!=3.0.0,>=2.0.0->scikit-image) (3.0.5)
Requirement already satisfied: cycler>=0.10 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from matplotlib!=3.0.0,>=2.0.0->scikit-image) (0.11.0)
Requirement already satisfied: kiwisolver>=1.0.1 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from matplotlib!=3.0.0,>=2.0.0->scikit-image) (1.3.2)
Requirement already satisfied: six>=1.5 in c:\users\chrizzl\documents\objectdetection\beeproject\beeproject\lib\site-packages (from python-dateutil>=2.7->matplotlib!=3.0.0,>=2.0.0->scikit-image) (1.16.0)

Hence the script stops and I cannot start the training. I feel like I am doing something rather obvious wrong. Maybe you can help me here.

Best regards and thank you!

[matpalm]

hmm. not sure sorry. it's been quite awhile since i've run this code so if skimage has been replaced with scikit-image i'd propbably see into the same thing myself now :(

[Testbild]

Ok I see. I think it is still correct to say

import skimage

but the pip install has to be scikit-image.

You do not have a docker container by any chance that has the versions of tensorflow and so on that you used when this was made that I could run?

EDIT: and did you run this project on linux or windows?

[matpalm]

i don't sorry, and the tensorflow version is a really good point, a number of things have changed in TF so i'd be unsure if it all runs...

…

On Thu, 11 Nov 2021 at 23:22, Testbild ***@***.***> wrote: Ok I see. I think it is still correct to say import skimage but the pip install has to be scikit-image. You do not have a docker container by any chance that has the versions of tensorflow and so on that you used when this was made that I could run? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#28 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAAFILNPD7OVCJGEKR7QUHLULOYRZANCNFSM5HYIS64Q> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.

[Testbild]

Do you by any chance remember the TF version that you used? I would assume TF1.x if I had to guess. Would be really nice, as we do have a real problem where we have to count bees 😄

[matpalm]

the version running on the rasp pi was 1.6; for training i would have been using whatever was current at the time as a side note; this kind of project is exactly what i'm working on now as a day job now, so if you'd like to join the conversation at https://forum.edgeimpulse.com/t/pollen-on-bees-legs-baskets-detection/1730 (or start a new forum conversation) we'll love to hear about your requirements so we can build the features out to support you

…

On Fri, 12 Nov 2021 at 06:31, Testbild ***@***.***> wrote: Do you by any chance remember the TF version that you used? I would assume TF1.x if I had to guess. Would be really nice, as we do have a real problem where we have to count bees 😄 — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#28 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAAFILP7SC2HWOUKNOLSEO3ULQKYVANCNFSM5HYIS64Q> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.

[Testbild]

Hi,
sorry for the late reply. Do you have an E-Mail, where I can contact you?

I mainly do this for educational purposes, but maybe there is a chance to come together.

[Testbild]

Also I think I figured out the issue. The versions from the requirements.txt were mostly too new.

I created a conda environment with python 3.7 and installed the correct version (well versions with which the script runs through).

conda create -n beeProjectConda python=3.7

pillow
python-utils
scipy
scikit-learn
scikit-image
tensorflow==1.15
tensorflow-gpu==1.15
pyyaml==5.4.1
numpy==1.16.5
pywavelets==1.1.1
matplotlib==3.1.0

Is it normal, that there are no detection on the predicted images with only the 2 steps of training?

Thanks and best regards

[matpalm]

a forum post describing your use case will be your best bet, i'm not going to work on this project outside porting it to edge impulse

…

On Wed, 17 Nov 2021 at 21:35, Testbild ***@***.***> wrote: Hi, sorry for the late reply. Do you have an E-Mail, where I can contact you? I mainly do this for educational purposes, but maybe there is a chance to come together. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#28 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAAFILI42KUGKFSNDQ2BYY3UMOAQPANCNFSM5HYIS64Q> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.

[matpalm]

yes it'll very likely take more than two steps. there is something coming through so it's hooked up!

…

On Wed, 17 Nov 2021 at 22:31, Testbild ***@***.***> wrote: Also I think I figured out the issue. The versions from the requirements.txt were mostly too new. I created a conda environment with python 3.7 and installed the correct version (well versions with which the script runs through). conda create -n beeProjectConda python=3.7 pillow python-utils scipy scikit-learn scikit-image tensorflow==1.15 tensorflow-gpu==1.15 pyyaml==5.4.1 numpy==1.16.5 pywavelets==1.1.1 matplotlib==3.1.0 Is it normal, that there are no detection on the predicted images with only the 2 steps of training? [image: 20180208_074854 jpg] <https://user-images.githubusercontent.com/9366108/142192709-755ff1b5-6d11-438e-9740-bbad83ec6599.png> [image: 20180210_121423 jpg] <https://user-images.githubusercontent.com/9366108/142192724-782f9641-46da-4b6b-832c-d3e9884be1bd.png> Thanks and best regards — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#28 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAAFILPTJN7FIW7V2VDILXTUMOHCVANCNFSM5HYIS64Q> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.