marc56k / electricitymetercam Goto Github PK

hello
I try to train my customized model and put it in the esp32
My model architecture is same as yours, but the size can't fit in the esp32.
And than I try to change other architecture to reduce the size of model.
After reduce the size, it can flash into esp32, but I still get the error
Could you help me?

i = tf.keras.layers.Input(shape=(28, 28, 1))
x = tf.keras.layers.Conv2D(filters=16, kernel_size=(3, 3), activation="relu")(i)
x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)
x = tf.keras.layers.Dropout(0.5)(x)
x = tf.keras.layers.Conv2D(filters=32, kernel_size=(3, 3), activation="relu")(x)
x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)
x = tf.keras.layers.Dropout(0.5)(x)
x = tf.keras.layers.Conv2D(filters=32, kernel_size=(3, 3), activation="relu")(x)
x = tf.keras.layers.Flatten()(x)
x = tf.keras.layers.Dense(64, activation="relu")(x)
x = tf.keras.layers.Dropout(0.5)(x)
x = tf.keras.layers.Dense(10, activation="softmax")(x)
model = tf.keras.Model(inputs=i, outputs=x)
model.compile(optimizer="rmsprop",
              loss="categorical_crossentropy",
              metrics=["accuracy"])
model.summary()

error i got

abort() was called at PC 0x400d6cee on core 1

Backtrace:0x400838d1:0x3ffb23700x4008ec89:0x3ffb2390 0x400948e5:0x3ffb23b0 0x400d6cee:0x3ffb2430 0x400e7933:0x3ffb2490 0x400e7ae5:0x3ffb2530 0x400e819b:0x3ffb25f0 0x400e66f7:0x3ffb2670 0x400d39d2:0x3ffb2690 0x400d560e:0x3ffb2700 0x400d571e:0x3ffb2760 0x400d5ad2:0x3ffb27f0 0x400efd91:0x3ffb2820

Hey, I like this project. I would love to give try. Would you be so kind and help me how to instal this into a esp32cam? Which file is the main one? Should i install it over Arduino IDE or esp flasher tool? What variables should be added before instal? (Wifi credentials etc.) thank you Jan