I ordered the Adafruit kit, and there was no guidance on:

• Assembling the hardware
• What's on the SD card (turns out, nothing, you need to install the Pi OS on it)

A summary that covered this, and a step-by-step list that linked to existing pages (installing the camera, connecting the fan, downloading the Pi OS) would help.

I also found it a little odd that while I had all this hardware, instead of setting it up I was launched right into using Lobe. Since the Pi updates and installations take so long to perform, it would be a better use of time to set up the Pi, start off the installations, and while that was happening downloading train Lobe. )Or better yet, learn about Lobe but then make use of a predefined Lobe model)

Where could we buy the same/a compatible (or "supported") kit from outside the US? From Adafruit or another vendor? I understand Adafruit maybe could offer international shipping, but intl shipping from a US-only company to EU is highly impractical and uneconomical (shipping fees + taxes + duties can easy double or triple the price, undercutting one of the primary reasons to buy a starter kit)

5.10.17-v7l+ #1421

~/lobe-adafruit-kit $ python3 -Xfaulthandler lobe-basic-prediction.py Predictions starting, to stop press "CTRL+C"
Fatal Python error: Segmentation fault

Current thread 0xb6f84ad0 (most recent call first):
File "/usr/local/lib/python3.7/dist-packages/tflite_runtime/interpreter.py", line 207 in init
File "/usr/local/lib/python3.7/dist-packages/lobe/backends/backend_tflite.py", line 25 in init
File "/usr/local/lib/python3.7/dist-packages/lobe/model/image_model.py", line 24 in load_from_signature
File "/usr/local/lib/python3.7/dist-packages/lobe/model/image_model.py", line 34 in load
File "lobe-basic-prediction.py", line 10 in main
File "lobe-basic-prediction.py", line 71 in
Segmentation fault

8. In terminal on the Pi, run the Python program lobe-basic-prediction.py
   Type the following commands:

Download File
Copy Code
cd ~
cd lobe-adafruit-kit
python3 lobe-basic-prediction.py

python lobe-basic-prediction.py
RuntimeError: module compiled against API version 0xf but this version of numpy is 0xd
Traceback (most recent call last):
File "/home/pi/lobe-adafruit-kit/lobe-basic-prediction.py", line 5, in
from lobe import ImageModel
File "/usr/local/lib/python3.9/dist-packages/lobe/init.py", line 2, in
from .model.image_model import ImageModel, VizEnum
File "/usr/local/lib/python3.9/dist-packages/lobe/model/image_model.py", line 8, in
from matplotlib import cm
File "/usr/local/lib/python3.9/dist-packages/matplotlib/init.py", line 109, in
from . import _api, _version, cbook, docstring, rcsetup
File "/usr/local/lib/python3.9/dist-packages/matplotlib/rcsetup.py", line 27, in
from matplotlib.colors import Colormap, is_color_like
File "/usr/local/lib/python3.9/dist-packages/matplotlib/colors.py", line 56, in
from matplotlib import _api, cbook, scale
File "/usr/local/lib/python3.9/dist-packages/matplotlib/scale.py", line 23, in
from matplotlib.ticker import (
File "/usr/local/lib/python3.9/dist-packages/matplotlib/ticker.py", line 136, in
from matplotlib import transforms as mtransforms
File "/usr/local/lib/python3.9/dist-packages/matplotlib/transforms.py", line 46, in
from matplotlib._path import (
ImportError: numpy.core.multiarray failed to import
pi@raspberrypi:~/lobe-adafruit-kit $ cd ~
cd lobe-adafruit-kit
python3 lobe-basic-prediction.py
RuntimeError: module compiled against API version 0xf but this versio

I was following the instructions on Adafruit's web site. At the point where I'm running

cd ~
cd lobe-adafruit-kit
python3 lobe-basic-prediction.py

I receive the TFliteImageModel object has no attribute lock
I ran some of the examples and at least one also did this.

Is there an outdated version of the TensorFlow model created that is not compatible?
Please let me know and thank you.

Predictions starting, to stop press "CTRL+C"
Traceback (most recent call last):
  File "lobe-basic-prediction.py", line 70, in <module>
    main()
  File "lobe-basic-prediction.py", line 37, in main
    result = model.predict(img)
  File "/usr/local/lib/python3.7/dist-packages/lobe/model/image_model.py", line 65, in predict
    results = self.backend.predict(image_array)
  File "/usr/local/lib/python3.7/dist-packages/lobe/backends/tflite/backend.py", line 59, in predict
    with self.lock:
AttributeError: 'TFLiteImageModel' object has no attribute 'lock'

The Lobe ML Kit comes with multiple pieces of hardware that need to be connected, but as far as I can tell, there are no assembly instructions. It would be helpful to have a quick assembly guide for anyone unfamiliar with connecting pieces of hardware together like this.

Lobe on Rasp Pi is reliant on PiCamera. PiCamera along with other camera apps like raspistill are not available on Rasp Pi Bullseye. I found this out after buying a Brain Craft/Lobe from Adafruit.