Error in energy estimation for AveragePooling2D layers

[RatkoFri]

Greetings, I am trying to quantize the network for the KWS application using DS CNN. The network is described here (LINK)(lines from 85 to 141).

When running AutoQKeras, It shows an error on energy estimation for Average2D pooling layers:

Traceback (most recent call last): File "/home/auto_qk.py", line 180, in autoqk = AutoQKeras(model, metrics=[keras.metrics.SparseCategoricalAccuracy()], custom_objects=custom_objects, **run_config) File "/usr/local/lib/python3.8/dist-packages/qkeras/autoqkeras/autoqkeras_internal.py", line 831, in init self.hypermodel = AutoQKHyperModel( File "/usr/local/lib/python3.8/dist-packages/qkeras/autoqkeras/autoqkeras_internal.py", line 125, in init self.reference_size = self.target.get_reference(model) File "/usr/local/lib/python3.8/dist-packages/qkeras/autoqkeras/forgiving_metrics/forgiving_energy.py", line 121, in get_reference energy_dict = q.pe( File "/usr/local/lib/python3.8/dist-packages/qkeras/qtools/run_qtools.py", line 85, in pe energy_dict = qenergy.energy_estimate( File "/usr/local/lib/python3.8/dist-packages/qkeras/qtools/qenergy/qenergy.py", line 302, in energy_estimate add_energy = OP[get_op_type(accumulator.output)]["add"]( AttributeError: 'NoneType' object has no attribute 'output'

When I remove the Average2D pooling layer, the AutoQKeras does not produce the error. I tried to set quant parameters for AveragePooling, but no luck.

Code for AutoQKeras:

AutoQkeras start

# set quantization configs 

quantization_config = {
    "kernel": {
            "binary": 1,
            "stochastic_binary": 1,
            "ternary": 2,
            "stochastic_ternary": 2,
            "quantized_bits(2,0,1,1,alpha=\"auto_po2\")": 2,
            "quantized_bits(3,0,1,1,alpha=\"auto_po2\")": 3,
            "quantized_bits(4,0,1,1,alpha=\"auto_po2\")": 4,
            "quantized_bits(3,0,1,1,alpha=\"auto_po2\")": 5,
            "quantized_bits(4,0,1,1,alpha=\"auto_po2\")": 6
    },
    "bias": {
            "quantized_bits(2,0,1,1,alpha=\"auto_po2\")": 2,
            "quantized_bits(3,0,1,1,alpha=\"auto_po2\")": 3,
            "quantized_bits(4,0,1,1,alpha=\"auto_po2\")": 4,
            "quantized_bits(3,0,1,1,alpha=\"auto_po2\")": 5,
            "quantized_bits(4,0,1,1,alpha=\"auto_po2\")": 6
    },
    "activation": {
            "binary": 1,
            "ternary": 2,
            "quantized_bits(2,0,1,1,alpha=\"auto_po2\")": 2,
            "quantized_bits(3,0,1,1,alpha=\"auto_po2\")": 3,
            "quantized_bits(4,0,1,1,alpha=\"auto_po2\")": 4,
            "quantized_bits(3,0,1,1,alpha=\"auto_po2\")": 5,
            "quantized_bits(4,0,1,1,alpha=\"auto_po2\")": 6
    },
    "linear": {
            "binary": 1,
            "ternary": 2,
            "quantized_bits(2,0,1,1,alpha=\"auto_po2\")": 2,
            "quantized_bits(3,0,1,1,alpha=\"auto_po2\")": 3,
            "quantized_bits(4,0,1,1,alpha=\"auto_po2\")": 4,
            "quantized_bits(3,0,1,1,alpha=\"auto_po2\")": 5,
            "quantized_bits(4,0,1,1,alpha=\"auto_po2\")": 6
    }
}

# define limits 
limit = {
    "Dense": [4, 4, 4],
    "Conv2D": [4, 4, 4],
    "DepthwiseConv2D": [4, 4, 4],
    "Activation": [4],
    "AveragePooling2D":  [4, 4, 4],
    "BatchNormalization": [],
    "Dense":[],
}

# define goal (delta = forgiving factor lets put at 8% like in tutorial )

goal = {
    "type": "energy",
    "params": {
        "delta_p": 8.0,
        "delta_n": 8.0,
        "rate": 2.0,
        "stress": 1.0,
        "process": "horowitz",
        "parameters_on_memory": ["sram", "sram"],
        "activations_on_memory": ["sram", "sram"],
        "rd_wr_on_io": [False, False],
        "min_sram_size": [0, 0],
        "source_quantizers": ["int8"],
        "reference_internal": "int8",
        "reference_accumulator": "int32"
        }
}

# SOME RUN CONFIGS

run_config = {
    "output_dir": Flags.bg_path + "auto_qk_dump",
    "goal": goal,
    "quantization_config": quantization_config,
    "learning_rate_optimizer": False,
    "transfer_weights": False,
    "mode": "random",
    "seed": 42,
    "limit": limit,
    "tune_filters": "layer",
    "tune_filters_exceptions": "^dense",
    # first layer is input, layer two layers are softmax and flatten
    "layer_indexes": range(1, len(model.layers)-1),
    "max_trials": 20
    }


# Start autoQkeras 

model.summary()
model.compile(
    #optimizer=keras.optimizers.RMSprop(learning_rate=args.learning_rate),  # Optimizer
    optimizer=keras.optimizers.Adam(learning_rate=Flags.learning_rate),  # Optimizer
    # Loss function to minimize
    loss=keras.losses.SparseCategoricalCrossentropy(),
    # List of metrics to monitor
    metrics=[keras.metrics.SparseCategoricalAccuracy()],
)   
#model = keras.models.load_model(Flags.saved_model_path)

custom_objects = {}
autoqk = AutoQKeras(model, metrics=[keras.metrics.SparseCategoricalAccuracy()], custom_objects=custom_objects, **run_config)
autoqk.fit(ds_train, validation_data=ds_val, epochs=Flags.epochs, callbacks=callbacks)

qmodel = autoqk.get_best_model()
model.save_weights(Flags.bg_path + "auto_qk_dump/","qmodel.h5")
### AutoQkeras stop