Wasserzähler - Selfmade

[watcherkb]

@coyote:

Leider kämpfe ich momentan wieder mit Ausfall des ESP's, habe dann keine Verbindung mehr zum WLAN und weiß irgendwie nicht so ganz woran es liegt. Ich habe nichts geändert, mal läuft es 1-2 Wochen ohne Ausfall. Jetzt jeden Tag keine Verbindung mehr.

das hatte ich auch, konnte es auch nicht mehr in Gang kriegen...lief mal ne Stunde dann wieder offline. Hab dann vorgestern den Sketch angepasst und eine statische IP vergeben. Diese muss sich aber außerhalb deines DHCP Bereichs befinden. Siehe mein angepasster Sketch. Seit dem kein einziger Ausfall.

ESP32CAM_Server-GitHub.ino

[jomjol]

@pfried Anpassung des Kontrastes sollte eigentlich keinen Vorteil für die Erkennung mit Neuronalen Netzen bringen. Ich trainiere diese sowieso mit +/- 30% Helligkeitsänderungen, um dort nicht zu sensibel auf die Beleuchtung zu sein.

[coyote]

@watcherkb ok, werde ich mal ausprobieren.
Aber warum muss die IP außerhalb vom DHCP Bereich liegen?

[pfried]

@jomjol Kannst Du uns bitte die Ziffern von oben, wenn Du Zeit hast trainieren? Wäre Super!

[coyote]

@pfried habe Jomjol die Ziffern geschickt, wenn er Zeit hat schaut er es sich mal an. Diese Woche wird er aber wohl nicht mehr dazu kommen, sagt er.

[pfried]

@coyote Danke!

[watcherkb]

@coyote falls mal deine Camera offline ist, schnappt sich kein anderes Gerät mehr deine IP die du statisch vergeben hast.

[coyote]

@watcherkb achso jetzt hab ich es verstanden.
Sollte eigentlich nicht, da sie im Router auch statisch vergeben ist. Gerade mal geflasht, dann probier ich doch mal ob es besser wird

[pfried]

@jomjol Heute kam bei mir ein automatischer Update vom Raspberry (mache ich einmal im Monat):

Jetzt geht der Wasserzähler nicht mehr Fast wie bei Microsoft....

[jomjol]

@pfried Konnte den Fehler reproduzieren - sieht nach einem Problem mit einer Python 3.7 Library aus - vielleicht urllib. Kenne noch keine Lösung, habe jetzt aber einen nicht lauffähigen Raspi
Versuche noch immer ein Docke-Image für den Pi zu erzeugen, aber das Script läuft dort einfach nicht. Das wäre eine saubere Lösung.

[jomjol]

@pfried @coyote
Ich habe die analogen Ziffern gerade geteached - hat funktioniert. Implementierung in Docker und GitHub dauert noch etwas, daher schicke ich euch erstmal das h5-File. Ihr könnt es manuel in config/neuralnets kopieren und in der Config.ini entsprechend den Namen ändern. Dann habt ihr es schonmal vorab: Train_CNN_Digital-Readout_Version_4.1.0.h5

Ich habe von @watcherkb auch noch andere Zeiger bekommen. Ich versuche gerade, diese zusammen mit meinen zu teachen und dann beide Updates gemeinsam hochzuladen.

[coyote]

@jomjol prima, danke dir. Komme leider erst morgen zum Testen

[pfried]

@jomjol Vielen Dank! Aber leider, wie oben geschrieben, ist mein Raspberry nach dem Upgrade für den Wasserzähler unter Python3 tot....

[coyote]

@jomjol ich habe gerade das neue File eingefügt, sieht gut aus. Es wird jetzt die 8 erkannt und nicht mehr als 1 angezeigt. Der Rest wird sich zeigen, aber lief ja vorher schon recht gut. Danke dir

[watcherkb]

@coyote sag mal wie sehen jetzt deine Verbindungsausbrüche aus? Meiner lief ca. 3 Tage jetzt habe ich wieder Probleme. Muss ihn mal anschließen und monitoren was er für Probleme hat.

[coyote]

@watcherkb so ganz blicke ich noch nicht durch, läuft jetzt wieder 3 Tage ohne Probleme durch. Feste IP hat aber nichts gebracht, kurz nachdem ich das geänderte Program geladen habe, hatte ich wieder kurze Zeit später keine Verbindung mehr.
Was mir aber dabei aufgefallen ist, dass der parser Adapter nicht korrekt lief und keine Anfrage mehr gestellt hat, warum weiß ich noch nicht, da der Adapter grün war, aber im Log fehlte die korrekte Anfrage an den Wasserzähler.

Adapter, Container und ESP alles nochmal neu gestartet, seit dem läuft es ohne Probleme. Warten wir mal ab, werde weiter beobachten.

[Knallochse]

Also bei mir funktioniert die Erkennung mit den neuen Zahlen auch viel besser.
Die Neadle Erkennung spinnt nur manchmal.
Wird hier eigentlich nur nie Nadelstellung detektiert, oder spielen die Zahlen drumrum auch eine Rolle?
Toll wäre bei der Einrichtung ein Mittelpunkt (Kreuz) in der Roi.html als Einrichtungshilfe. Diesen Mittelpunkt könnte man zum einrichten über den Drehpunkt der Nadel platzieren.
Aber hiermit nochmals einen RIESIGEN Dank an @jomjol das du dein Projekt mit uns teilst

[Knallochse]

@coyote Das Problem mit dem Parser kenne ich auch (nach Änderungen im Parser - keine Aktualisierung) Konnte ich auch nur mit Neustarts beheben

[pfried]

@coyote @Knallochse
Ich denke wir haben hier alle dieselben Phänomene. Auch ich musste den Parser schon mehrmals wieder starten, damit er abfragt (obwohl er grün signalisierte).
Leider kann ich derzeit nicht mittesten, da mein RB PI 4 nach einem Upgrade nicht mehr den Server startet. Also derzeit NICHT upgraden, falls Ihr die Raspberry Version verwendet, bis jomjol den Grund dafür gefunden hat (leider reichen meine Kenntnisse dafür bei weitem nicht aus).

[mameier1234]

Hallo,

jetzt melde ich mich hier auch mal nach langem mitlesen...

Superspannendes Projekt...

Ich habe bis dato noch nix mit Arduino usw gemacht, habe es aber tatsächlich geschaft, dass die Cam funktioniert..

Nun habe ich mich am installieren der Software auf dem PI versucht... Erste Versuche auf einem bestehenden System liefen zwar durch, das Programm ließ sich dann aber nicht starten... (und nebenbei , habe ich durch die Updates am System auch meinen ebus zerstört.. läuft aber wieder ... gefährliches Halbwissen )

Dann dachte ich mir.. kein Problem.. ich habe ja hier noch einen jungfräulichen Pi4 rumliegen.. Aktuelles Image drauf und laut github Link für den Pi python usw. installiert... Es kamen bei der Installation keine offensichtlichen Fehlermeldungen...

Dann beim Start der Software:

pi@raspberrypi:~/water-meter-system-complete/code $ LD_PRELOAD=/usr/lib/arm-linux-gnueabihf/libatomic.so.1 python3 wasseruhr.py
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: compiletime version 3.4 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.5
  return f(*args, **kwds)
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: builtins.type size changed, may indicate binary incompatibility. Expected 432, got 412
  return f(*args, **kwds)
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
Traceback (most recent call last):
  File "wasseruhr.py", line 3, in <module>
    import lib.ZaehlerstandClass
  File "/home/pi/water-meter-system-complete/code/lib/ZaehlerstandClass.py", line 2, in <module>
    import lib.ReadAnalogNeedleClass
  File "/home/pi/water-meter-system-complete/code/lib/ReadAnalogNeedleClass.py", line 4, in <module>
    from PIL import Image
ImportError: No module named 'PIL'

Seltsam.. Dr. Google sagt: sudo pip3 install pillow .. hab ich gemacht...

Dann:

pi@raspberrypi:~/water-meter-system-complete/code $ LD_PRELOAD=/usr/lib/arm-linux-gnueabihf/libatomic.so.1 python3 wasseruhr.py
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: compiletime version 3.4 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.5
  return f(*args, **kwds)
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: builtins.type size changed, may indicate binary incompatibility. Expected 432, got 412
  return f(*args, **kwds)
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
Traceback (most recent call last):
  File "wasseruhr.py", line 3, in <module>
    import lib.ZaehlerstandClass
  File "/home/pi/water-meter-system-complete/code/lib/ZaehlerstandClass.py", line 2, in <module>
    import lib.ReadAnalogNeedleClass
  File "/home/pi/water-meter-system-complete/code/lib/ReadAnalogNeedleClass.py", line 8, in <module>
    import cv2
ImportError: No module named 'cv2'
pi@raspberrypi:~/water-meter-system-complete/code $ 

Dann: sudo pip3 install opencv-python

pi@raspberrypi:~/water-meter-system-complete/code $ LD_PRELOAD=/usr/lib/arm-linux-gnueabihf/libatomic.so.1 python3 wasseruhr.py
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: compiletime version 3.4 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.5
  return f(*args, **kwds)
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: builtins.type size changed, may indicate binary incompatibility. Expected 432, got 412
  return f(*args, **kwds)
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
Start Init Zaehlerstand
Traceback (most recent call last):
  File "wasseruhr.py", line 83, in <module>
    wasserzaehler = lib.ZaehlerstandClass.Zaehlerstand()
  File "/home/pi/water-meter-system-complete/code/lib/ZaehlerstandClass.py", line 18, in __init__
    self.readAnalogNeedle = lib.ReadAnalogNeedleClass.ReadAnalogNeedle()
  File "/home/pi/water-meter-system-complete/code/lib/ReadAnalogNeedleClass.py", line 34, in __init__
    self.model = load_model(self.model_file)
  File "/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/keras/saving/save.py", line 146, in load_model
    return hdf5_format.load_model_from_hdf5(filepath, custom_objects, compile)
  File "/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/keras/saving/hdf5_format.py", line 168, in load_model_from_hdf5
    raise ImportError('`load_model` requires h5py.')
ImportError: `load_model` requires h5py.
pi@raspberrypi:~/water-meter-system-complete/code $ 

Also .. wieder Google und sudo apt-get install libhdf5-dev

pi@raspberrypi:~/water-meter-system-complete/code $ LD_PRELOAD=/usr/lib/arm-linux-gnueabihf/libatomic.so.1 python3 wasseruhr.py
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: compiletime version 3.4 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.5
  return f(*args, **kwds)
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: builtins.type size changed, may indicate binary incompatibility. Expected 432, got 412
  return f(*args, **kwds)
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/pi/.local/lib/python3.5/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
Start Init Zaehlerstand
WARNING:tensorflow:From /home/pi/.local/lib/python3.5/site-packages/tensorflow/python/ops/init_ops.py:97: calling Zeros.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From /home/pi/.local/lib/python3.5/site-packages/tensorflow/python/ops/init_ops.py:97: calling Ones.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From /home/pi/.local/lib/python3.5/site-packages/tensorflow/python/ops/init_ops.py:97: calling GlorotUniform.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From /home/pi/.local/lib/python3.5/site-packages/tensorflow/python/ops/init_ops.py:1251: calling VarianceScaling.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
Analog Model Init Done
Digital Model Init Done
Digital Model Init Done
Traceback (most recent call last):
  File "wasseruhr.py", line 86, in <module>
    with socketserver.TCPServer(("", PORT), SimpleHTTPRequestHandler) as httpd:
AttributeError: __exit__
pi@raspberrypi:~/water-meter-system-complete/code $ 

Und jetzt weiss ich nicht mehr weiter ...

Edit... habe es gerade nochmal auf dem PI4 so versucht.. da kommt dann : Wasserzaehler is serving at port 3000

Sieht gut aus und ich werde jetzt erstmal weitertesten...