import tensorflow as tf

class QuantConv2DTransposed(tf.keras.layers.Layer):
  def build(self, input shape):
    self.kernel = self.add weight("kernel", [3, 3, input shape[-1], 24])

  def call(self, inputs):
    filters = tf.quantization.fake quant with min max vars per channel(
      self.kernel, -3.0 * tf.ones([24]), 3.0 * tf.ones([24]), narrow range=True
    )
    filters = tf.transpose(filters, (0, 1, 3, 2))
    return tf.nn.conv2d transpose(inputs, filters, [*inputs.shape[:-1], 24], 1)

inp = tf.keras.Input(shape=(6, 8, 48), batch size=1)
x = tf.quantization.fake quant with min max vars(inp, -3.0, 3.0, narrow range=True)
x = QuantConv2DTransposed()(x)
x = tf.quantization.fake quant with min max vars(x, -3.0, 3.0, narrow range=True)

model = tf.keras.Model(inp, x)

model.save("/tmp/testing")
converter = tf.lite.TFLiteConverter.from saved model("/tmp/testing")
converter.optimizations = [tf.lite.Optimize.DEFAULT]

# terminated by signal SIGSEGV (Address boundary error)
tflite model = converter.convert()