Jonathan Chetwynd

just a nudge the Google Coral range peak at 4 Tops. surely that's enough..... and now they are available. tx by chance I grazed this implementation of MuGo by Google...

ah, great, please try Chinese rules, 7.0 komi as these are the settings for GoQuest! ~:

the most obvious immediate benefit might be if people created an issue here to link to their github repositories, when they have something to show? seems awkward, and only addresses...

Did anyone find a commercial purpose for the CoralMicro? Google does have it's limitations....

had you some code to share? I'm struggling with maskwren, examples in the wild are hard to find... https://projectf.io/posts/spram-ice40-fpga/ makes a start, but.... tx

I tried tf.io.decode_image & tf.io.decode_bmp, ie : img = tf.io.read_file('apple64.png') img = tf.io.decode_image(img, channels=0) tf.expand_dims(img, -1).shape.as_list() model_1 = Sequential() ----- without success: ValueError: could not broadcast input array from shape...

Clarification: img = img[:, :, np.newaxis] or img = np.expand_dims(img, axis=(0, -1)) are also similar, the tensorflow works fine, it's when one tries to use the .tflite file created that...

Thanks for the comment, However, not everyone (that includes me) compiles from one year to the next... Not sure I have ever coded in C++, and understanding when things don't...