def make_test_params():
cp = MultipleLayersParams()
cp.compute_reconstruction = True
cp.conv_classes = ConvLayer
cp.sp_buffer_size = 6000
cp.sp_batch_size = 4000
cp.learning_rate = 0.02
cp.cluster_boost_threshold = 1000
cp.max_encountered_seqs = 10000
cp.max_frequent_seqs = 1000
cp.seq_length = 4
cp.seq_lookahead = 1
cp.num_conv_layers = 1
cp.n_cluster_centers = 400
cp.rf_size = (8, 8)
cp.rf_stride = (8, 8)
tp = MultipleLayersParams()
tp.n_cluster_centers = 250
tp.sp_buffer_size = 4000
tp.sp_batch_size = 500
tp.learning_rate = 0.2
tp.cluster_boost_threshold = 1000
tp.compute_reconstruction = True
common_params = {
'conv_layers_params': cp,
'top_layer_params': tp,
'image_size': SeDatasetSize.SIZE_64,
'class_filter': [1, 2, 3],
'noise_amp': 0.0,
'model_seed': None,
'baseline_seed': None
}
changing_params = [{
'conv_layers_params': cp.change(learning_rate=0.1)
}, {
'conv_layers_params': cp.change(learning_rate=0.2),
'top_layer_params': tp.change(learning_rate=0.1)
}, {
'conv_layers_params': cp.change(learning_rate=0.3)
}]
params = ExperimentTemplateBase.add_common_params(changing_params,
common_params)
return params, common_params, changing_params
def test_change_params():
default_params = MultipleLayersParams()
default_params.learning_rate = 0.997
default_params.n_cluster_centers = [2, 3]
default_params.seq_length = 5
sequence = [{
'conv_layers_params':
default_params.change(n_cluster_centers=[1, 2])
}, {
'conv_layers_params':
default_params.change(n_cluster_centers=[1, 2, 3], learning_rate=0.11)
}]
assert default_params.n_cluster_centers == [2, 3]
assert sequence[0]['conv_layers_params'].n_cluster_centers == [1, 2]
assert sequence[1]['conv_layers_params'].n_cluster_centers == [1, 2, 3]
assert sequence[0]['conv_layers_params'].learning_rate == 0.997
assert sequence[1]['conv_layers_params'].learning_rate == 0.11
def test_empty_change():
a = MultipleLayersParams()
a.learning_rate = 0.345
a.n_cluster_centers = [1, 2, 3]
b = a.change()
assert b.learning_rate == a.learning_rate
assert a.n_cluster_centers == b.n_cluster_centers
b.learning_rate = 0.1
a.n_cluster_centers = [1, 2]
assert b.learning_rate != a.learning_rate
assert a.n_cluster_centers != b.n_cluster_centers
def multiple_runs_lr_example(args, debug: bool = False):
name = "example_multiple_runs"
default_conv = MultipleLayersParams()
default_conv.compute_reconstruction = True
default_conv.conv_classes = [ConvLayer, SpConvLayer]
default_conv.num_conv_layers = 2
default_conv.rf_stride = (8, 8)
default_conv.rf_size = (8, 8)
tp = MultipleLayersParams()
tp.n_cluster_centers = 250
params = [{
'conv_layers_params': default_conv.change(learning_rate=0.1)
}, {
'conv_layers_params': default_conv.change(learning_rate=0.2),
'top_layer_params': tp.change(learning_rate=0.11)
}, {
'conv_layers_params': default_conv.change(learning_rate=0.3)
}]
common_params = {
'top_layer_params': tp,
'image_size': SeDatasetSize.SIZE_64,
'noise_amp': 0.0,
'model_seed': None,
'baseline_seed': None
}
# merge the params and common params
p = ExperimentTemplateBase.add_common_params(params, common_params)
run_measurement(name, p, args, debug=debug)
def good_one_layer_config_for_four_objects() -> List[Dict[str, Any]]:
"""A topology which might achieve 100% SE accuracy on 4 objects"""
cp = MultipleLayersParams()
cp.compute_reconstruction = False
cp.conv_classes = ConvLayer
cp.sp_buffer_size = 6000
cp.sp_batch_size = 4000
cp.learning_rate = 0.1
cp.cluster_boost_threshold = 1000
cp.max_encountered_seqs = 2000
cp.max_frequent_seqs = 1000
cp.seq_lookahead = 1
cp.seq_length = 5
cp.n_cluster_centers = 200
cp.rf_size = (8, 8)
cp.rf_stride = (8, 8)
cp.num_conv_layers = 1
tp = MultipleLayersParams()
tp.n_cluster_centers = 150
tp.sp_buffer_size = 3000
tp.sp_batch_size = 2000
tp.learning_rate = 0.15
tp.cluster_boost_threshold = 1000
tp.compute_reconstruction = True
cf_easy = [1, 2, 3, 4]
size = SeDatasetSize.SIZE_64
size_int = (size.value, size.value, 3)
params = [
{
'se_group': {'class_filter': cf_easy,
'image_size': size},
'model': {'conv_layers_params': cp.change(opp=0.5),
'top_layer_params': tp,
'image_size': size_int}
}
]
return params
def run_opp(args, num_conv_layers: int, exp_params, top_cc: int = 150):
name = f"OPP-influence_num_cc{top_cc}"
cp = MultipleLayersParams()
cp.compute_reconstruction = False
cp.conv_classes = ConvLayer
cp.sp_buffer_size = 6000
cp.sp_batch_size = 1500 # original 4000
cp.learning_rate = 0.10001
cp.cluster_boost_threshold = 1000
cp.max_encountered_seqs = 2000
cp.max_frequent_seqs = 1000
cp.seq_lookahead = 1
cp.seq_length = 4 # note: might use also 5 (as in older experiments)
if num_conv_layers == 2:
cp.n_cluster_centers = [100, 230]
cp.rf_size = [(8, 8), (4, 4)]
cp.rf_stride = [(8, 8), (1, 1)]
cp.num_conv_layers = 2
else:
cp.n_cluster_centers = 200
cp.rf_size = (8, 8)
cp.rf_stride = (8, 8)
cp.num_conv_layers = 1
tp = MultipleLayersParams()
tp.n_cluster_centers = top_cc
tp.sp_buffer_size = 3000
tp.sp_batch_size = 1500 #
tp.learning_rate = 0.15
tp.cluster_boost_threshold = 1000
tp.compute_reconstruction = True
cf_easy = [1, 2, 3, 4]
size = SeDatasetSize.SIZE_64
size_int = (size.value, size.value, 3)
params = [
{
'se_group': {'class_filter': cf_easy,
'image_size': size},
'model': {'conv_layers_params': cp.change(opp=0),
'top_layer_params': tp,
'image_size': size_int}
},
{
'se_group': {'class_filter': cf_easy,
'image_size': size},
'model': {'conv_layers_params': cp.change(opp=0.05),
'top_layer_params': tp,
'image_size': size_int}
},
{
'se_group': {'class_filter': cf_easy,
'image_size': size},
'model': {'conv_layers_params': cp.change(opp=0.5),
'top_layer_params': tp,
'image_size': size_int}
},
{
'se_group': {'class_filter': cf_easy,
'image_size': size},
'model': {'conv_layers_params': cp.change(opp=0.95),
'top_layer_params': tp,
'image_size': size_int}
},
{
'se_group': {'class_filter': cf_easy,
'image_size': size},
'model': {'conv_layers_params': cp.change(opp=1),
'top_layer_params': tp,
'image_size': size_int}
},
# {
# 'se_group': {'class_filter': cf_easy,
# 'image_size': size},
# 'model': {'conv_layers_params': cp.change(opp=0.3),
# 'top_layer_params': tp,
# 'image_size': size_int}
# },
# {
# 'se_group': {'class_filter': cf_easy,
# 'image_size': size},
# 'model': {'conv_layers_params': cp.change(opp=0.7),
# 'top_layer_params': tp,
# 'image_size': size_int}
# }
]
exp_params.experiment_params.num_layers = num_conv_layers + 1 # needs to be there
run_measurement(name, params, args, exp_params)
def run_rf_size(args, exp_params, opp: float = 1.0):
name = "rf_size"
cp = MultipleLayersParams()
cp.compute_reconstruction = False
cp.conv_classes = ConvLayer
cp.sp_buffer_size = 6000
cp.sp_batch_size = 4000
cp.learning_rate = 0.1
cp.cluster_boost_threshold = 1000
cp.max_encountered_seqs = 2000
cp.max_frequent_seqs = 1000
cp.seq_lookahead = 1
cp.seq_length = 5
cp.opp = opp
cp.n_cluster_centers = 200
cp.rf_size = (8, 8)
cp.rf_stride = (8, 8)
cp.num_conv_layers = 1
tp = MultipleLayersParams()
tp.n_cluster_centers = 150
tp.sp_buffer_size = 3000
tp.sp_batch_size = 2000
tp.learning_rate = 0.15
tp.cluster_boost_threshold = 1000
tp.compute_reconstruction = True
cf_easy = [1, 2, 3, 4]
size = SeDatasetSize.SIZE_64
size_int = (size.value, size.value, 3)
params = [
{
'se_group': {'class_filter': cf_easy,
'image_size': size},
'model': {'conv_layers_params': cp.change(rf_stride=([(8, 8)])),
'top_layer_params': tp,
'image_size': size_int}
},
{
'se_group': {'class_filter': cf_easy,
'image_size': size},
'model': {'conv_layers_params': cp.change(rf_stride=([(4, 4)])),
'top_layer_params': tp,
'image_size': size_int}
},
{
'se_group': {'class_filter': cf_easy,
'image_size': size},
'model': {'conv_layers_params': cp.change(rf_stride=([(2, 2)])),
'top_layer_params': tp,
'image_size': size_int}
},
]
exp_params.experiment_params.num_layers = 2 # needs to be there
run_measurement(name, params, args, exp_params)
params = [{
'se_group': {
'class_filter': cf_easy
},
'model': {
'conv_layers_params': cp,
'top_layer_params': tp
}
}, {
'se_group': {
'class_filter': cf_easy
},
'model': {
'conv_layers_params':
cp.change(learning_rate=0.7,
sp_batch_size=30,
n_cluster_centers=300),
'top_layer_params':
tp.change(learning_rate=0.7,
sp_batch_size=15,
n_cluster_centers=200)
}
}]
# TODO merging common params not supported yeat
common_params = [{
'conv_layers_params': cp,
'top_layer_params': tp,
'image_size': SeDatasetSize.SIZE_64,
'class_filter': cf_easy,
'model_seed': None,
