Related
I have problem with using .compile() after building a simple Sequential model with keras.
The error type I got:
TypeError: 'str' object is not callable
By the way, I run the code on Colab and it works. The problem is that the code doesn't work on my system, and I'm using anaconda Jupyter notebook.
the code:
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
model = keras.Sequential(
[
layers.Dense(2, activation="relu", name ="layer1"),
layers.Dense(3, activation="relu", name ="layer2"),
layers.Dense(4, name="layer3")
])
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/array_ops.py in zeros(shape, dtype, name)
2725 # Go through tensor shapes to get int64-if-needed semantics
-> 2726 shape = constant_op._tensor_shape_tensor_conversion_function(
2727 tensor_shape.TensorShape(shape))
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py in _tensor_shape_tensor_conversion_function(s, dtype, name, as_ref)
356 name = "shape_as_tensor"
--> 357 return constant(s_list, dtype=dtype, name=name)
358
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name)
261 """
--> 262 return _constant_impl(value, dtype, shape, name, verify_shape=False,
263 allow_broadcast=True)
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
270 if ctx.executing_eagerly():
--> 271 t = convert_to_eager_tensor(value, ctx, dtype)
272 if shape is None:
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
96
---> 97 return ops.EagerTensor(value, ctx.device_name(), dtype)
98
TypeError: 'str' object is not callable
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-107-3bc1e703d8ff> in <module>
----> 1 model.compile(loss=loss, optimizer=optim, metrics=metrics)
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, **kwargs)
327
328 self.optimizer = self._get_optimizer(optimizer)
--> 329 self.compiled_loss = compile_utils.LossesContainer(
330 loss, loss_weights, output_names=self.output_names)
331 self.compiled_metrics = compile_utils.MetricsContainer(
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/keras/engine/compile_utils.py in __init__(self, losses, loss_weights, output_names)
118 self._loss_weights = loss_weights
119 self._per_output_metrics = None # Per-output losses become metrics.
--> 120 self._loss_metric = metrics_mod.Mean(name='loss') # Total loss.
121 self._built = False
122
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/keras/metrics.py in __init__(self, name, dtype)
468 dtype: (Optional) data type of the metric result.
469 """
--> 470 super(Mean, self).__init__(
471 reduction=metrics_utils.Reduction.WEIGHTED_MEAN, name=name, dtype=dtype)
472
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/keras/metrics.py in __init__(self, reduction, name, dtype)
305 self.reduction = reduction
306 with ops.init_scope():
--> 307 self.total = self.add_weight(
308 'total', initializer=init_ops.zeros_initializer)
309 if reduction in [metrics_utils.Reduction.SUM_OVER_BATCH_SIZE,
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/keras/metrics.py in add_weight(self, name, shape, aggregation, synchronization, initializer, dtype)
274 synchronization = tf_variables.VariableSynchronization.ON_WRITE
275
--> 276 return super(Metric, self).add_weight(
277 name=name,
278 shape=shape,
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py in add_weight(self, name, shape, dtype, initializer, regularizer, trainable, constraint, partitioner, use_resource, synchronization, aggregation, **kwargs)
558 caching_device = None
559
--> 560 variable = self._add_variable_with_custom_getter(
561 name=name,
562 shape=shape,
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/training/tracking/base.py in _add_variable_with_custom_getter(self, name, shape, dtype, initializer, getter, overwrite, **kwargs_for_getter)
736 initializer = checkpoint_initializer
737 shape = None
--> 738 new_variable = getter(
739 name=name,
740 shape=shape,
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer_utils.py in make_variable(name, shape, dtype, initializer, trainable, caching_device, validate_shape, constraint, use_resource, collections, synchronization, aggregation, partitioner)
127 # can remove the V1.
128 variable_shape = tensor_shape.TensorShape(shape)
--> 129 return tf_variables.VariableV1(
130 initial_value=init_val,
131 name=name,
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/variables.py in __call__(cls, *args, **kwargs)
257 def __call__(cls, *args, **kwargs):
258 if cls is VariableV1:
--> 259 return cls._variable_v1_call(*args, **kwargs)
260 elif cls is Variable:
261 return cls._variable_v2_call(*args, **kwargs)
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/variables.py in _variable_v1_call(cls, initial_value, trainable, collections, validate_shape, caching_device, name, variable_def, dtype, expected_shape, import_scope, constraint, use_resource, synchronization, aggregation, shape)
203 if aggregation is None:
204 aggregation = VariableAggregation.NONE
--> 205 return previous_getter(
206 initial_value=initial_value,
207 trainable=trainable,
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/variables.py in getter(**kwargs)
64
65 def getter(**kwargs):
---> 66 return captured_getter(captured_previous, **kwargs)
67
68 return getter
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py in creator(next_creator, **kwargs)
2560 def creator(next_creator, **kwargs):
2561 _require_strategy_scope_strategy(strategy)
-> 2562 return next_creator(**kwargs)
2563
2564 self._var_creator_scope = variable_scope.variable_creator_scope(creator)
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/variables.py in <lambda>(**kwargs)
196 shape=None):
197 """Call on Variable class. Useful to force the signature."""
--> 198 previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
199 for _, getter in ops.get_default_graph()._variable_creator_stack: # pylint: disable=protected-access
200 previous_getter = _make_getter(getter, previous_getter)
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py in default_variable_creator(next_creator, **kwargs)
2582 if use_resource:
2583 distribute_strategy = kwargs.get("distribute_strategy", None)
-> 2584 return resource_variable_ops.ResourceVariable(
2585 initial_value=initial_value,
2586 trainable=trainable,
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/variables.py in __call__(cls, *args, **kwargs)
261 return cls._variable_v2_call(*args, **kwargs)
262 else:
--> 263 return super(VariableMetaclass, cls).__call__(*args, **kwargs)
264
265
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/resource_variable_ops.py in __init__(self, initial_value, trainable, collections, validate_shape, caching_device, name, dtype, variable_def, import_scope, constraint, distribute_strategy, synchronization, aggregation, shape)
1421 self._init_from_proto(variable_def, import_scope=import_scope)
1422 else:
-> 1423 self._init_from_args(
1424 initial_value=initial_value,
1425 trainable=trainable,
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/resource_variable_ops.py in _init_from_args(self, initial_value, trainable, collections, caching_device, name, dtype, constraint, synchronization, aggregation, distribute_strategy, shape)
1565 with ops.name_scope("Initializer"), device_context_manager(None):
1566 initial_value = ops.convert_to_tensor(
-> 1567 initial_value() if init_from_fn else initial_value,
1568 name="initial_value", dtype=dtype)
1569 if shape is not None:
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer_utils.py in <lambda>()
119 (type(init_ops.Initializer), type(init_ops_v2.Initializer))):
120 initializer = initializer()
--> 121 init_val = lambda: initializer(shape, dtype=dtype)
122 variable_dtype = dtype.base_dtype
123 if use_resource is None:
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/init_ops.py in __call__(self, shape, dtype, partition_info)
112 if dtype is None:
113 dtype = self.dtype
--> 114 return array_ops.zeros(shape, dtype)
115
116 def get_config(self):
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/array_ops.py in wrapped(*args, **kwargs)
2675
2676 def wrapped(*args, **kwargs):
-> 2677 tensor = fun(*args, **kwargs)
2678 tensor._is_zeros_tensor = True
2679 return tensor
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/ops/array_ops.py in zeros(shape, dtype, name)
2728 except (TypeError, ValueError):
2729 # Happens when shape is a list with tensor elements
-> 2730 shape = ops.convert_to_tensor(shape, dtype=dtypes.int32)
2731 if not shape._shape_tuple():
2732 shape = reshape(shape, [-1]) # Ensure it's a vector
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
1339
1340 if ret is None:
-> 1341 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1342
1343 if ret is NotImplemented:
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
320 as_ref=False):
321 _ = as_ref
--> 322 return constant(v, dtype=dtype, name=name)
323
324
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name)
260 ValueError: if called on a symbolic tensor.
261 """
--> 262 return _constant_impl(value, dtype, shape, name, verify_shape=False,
263 allow_broadcast=True)
264
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
269 ctx = context.context()
270 if ctx.executing_eagerly():
--> 271 t = convert_to_eager_tensor(value, ctx, dtype)
272 if shape is None:
273 return t
~/anaconda3/envs/tf-gpu/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
95 ctx.ensure_initialized()
96
---> 97 return ops.EagerTensor(value, ctx.device_name(), dtype)
98
99
TypeError: 'str' object is not callable
I have one working tensorflow RNN model (called my_model) and I save it using my_model.save("<dir_to_my_model>").
However, when I reload this model with
model = tf.keras.models.load_model("<dir_to_my_model>")
and run a few incremental learning epochs with
with tf.GradientTape() as tape:
logits = model(x_test_batch, training=True)
I got an error (very long, please see at the bottom).
But, if I save the weights of this model to a checkpoint using model.save_weights(), create a new model and load the weights using model.load_weights from that checkpoint. The code above could run successfully.
My question is why these 2 methods work differently and what should I do to make method 1 work?
InvalidArgumentError Traceback (most recent call last)
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py in get_attr(self, name)
2325 with c_api_util.tf_buffer() as buf:
-> 2326 c_api.TF_OperationGetAttrValueProto(self._c_op, name, buf)
2327 data = c_api.TF_GetBuffer(buf)
InvalidArgumentError: Operation 'StatefulPartitionedCall' has no attr named '_XlaCompile'.
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in _MaybeCompile(scope, op, func, grad_fn)
330 try:
--> 331 xla_compile = op.get_attr("_XlaCompile")
332 xla_separate_compiled_gradients = op.get_attr(
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py in get_attr(self, name)
2329 # Convert to ValueError for backwards compatibility.
-> 2330 raise ValueError(str(e))
2331 x = attr_value_pb2.AttrValue()
ValueError: Operation 'StatefulPartitionedCall' has no attr named '_XlaCompile'.
During handling of the above exception, another exception occurred:
InvalidArgumentError Traceback (most recent call last)
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py in get_attr(self, name)
2325 with c_api_util.tf_buffer() as buf:
-> 2326 c_api.TF_OperationGetAttrValueProto(self._c_op, name, buf)
2327 data = c_api.TF_GetBuffer(buf)
InvalidArgumentError: Operation 'StatefulPartitionedCall' has no attr named '_XlaCompile'.
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in _MaybeCompile(scope, op, func, grad_fn)
330 try:
--> 331 xla_compile = op.get_attr("_XlaCompile")
332 xla_separate_compiled_gradients = op.get_attr(
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py in get_attr(self, name)
2329 # Convert to ValueError for backwards compatibility.
-> 2330 raise ValueError(str(e))
2331 x = attr_value_pb2.AttrValue()
ValueError: Operation 'StatefulPartitionedCall' has no attr named '_XlaCompile'.
During handling of the above exception, another exception occurred:
LookupError Traceback (most recent call last)
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in _GradientsHelper(ys, xs, grad_ys, name, colocate_gradients_with_ops, gate_gradients, aggregation_method, stop_gradients, unconnected_gradients, src_graph)
606 try:
--> 607 grad_fn = ops.get_gradient_function(op)
608 except LookupError:
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py in get_gradient_function(op)
2494 op_type = op.type
-> 2495 return _gradient_registry.lookup(op_type)
2496
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/registry.py in lookup(self, name)
96 raise LookupError(
---> 97 "%s registry has no entry for: %s" % (self._name, name))
LookupError: gradient registry has no entry for: While
During handling of the above exception, another exception occurred:
LookupError Traceback (most recent call last)
<ipython-input-7-55225939f96a> in <module>
10 mode = 'DNN' if 'ANN' in m else 'RNN'
11 c_datasets = continual_dataset(datasets[i], mode=mode)
---> 12 res = learning_rate_test(continual_fine_tune, mname, c_datasets, lr_list=lrs)
13 dfs.append(res)
<ipython-input-5-f4d4cc64dc17> in learning_rate_test(continual_func, model_fname, c_datasets, epochs, lr_list, loss)
14 model.save_weights('Model/tmp')
15 model.load_weights('Model/tmp')
---> 16 test_predictions = continual_func(c_datasets, model, loss_fn, lr, epochs=e, save_model='')
17 test_predictions = (np.array(test_predictions) > 0.5).astype(int)
18 epoch_test_dict[e].append(np.sum(np.equal(y_test_list, test_predictions)) / len(y_test_list) * 100)
<ipython-input-4-9ae956b3e918> in continual_fine_tune(c_datasets, model, loss_fn, lr, epochs, save_model)
12 for e in range(epochs):
13 with tf.GradientTape() as tape:
---> 14 logits = model(x_test_batch, training=True)
15 loss_value = loss_fn(y_test_batch, logits)
16 grads = tape.gradient(loss_value, model.trainable_weights)
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
820 with base_layer_utils.autocast_context_manager(
821 self._compute_dtype):
--> 822 outputs = self.call(cast_inputs, *args, **kwargs)
823 self._handle_activity_regularization(inputs, outputs)
824 self._set_mask_metadata(inputs, outputs, input_masks)
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/sequential.py in call(self, inputs, training, mask)
265 if not self.built:
266 self._init_graph_network(self.inputs, self.outputs, name=self.name)
--> 267 return super(Sequential, self).call(inputs, training=training, mask=mask)
268
269 outputs = inputs # handle the corner case where self.layers is empty
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/network.py in call(self, inputs, training, mask)
715 return self._run_internal_graph(
716 inputs, training=training, mask=mask,
--> 717 convert_kwargs_to_constants=base_layer_utils.call_context().saving)
718
719 def compute_output_shape(self, input_shape):
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/network.py in _run_internal_graph(self, inputs, training, mask, convert_kwargs_to_constants)
889
890 # Compute outputs.
--> 891 output_tensors = layer(computed_tensors, **kwargs)
892
893 # Update tensor_dict.
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
820 with base_layer_utils.autocast_context_manager(
821 self._compute_dtype):
--> 822 outputs = self.call(cast_inputs, *args, **kwargs)
823 self._handle_activity_regularization(inputs, outputs)
824 self._set_mask_metadata(inputs, outputs, input_masks)
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/utils.py in return_outputs_and_add_losses(*args, **kwargs)
57 inputs = args[inputs_arg_index]
58 args = args[inputs_arg_index + 1:]
---> 59 outputs, losses = fn(inputs, *args, **kwargs)
60 layer.add_loss(losses, inputs)
61 return outputs
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/utils.py in wrap_with_training_arg(*args, **kwargs)
111 training,
112 lambda: replace_training_and_call(True),
--> 113 lambda: replace_training_and_call(False))
114
115 # Create arg spec for decorated function. If 'training' is not defined in the
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/utils/tf_utils.py in smart_cond(pred, true_fn, false_fn, name)
57 pred, true_fn=true_fn, false_fn=false_fn, name=name)
58 return smart_module.smart_cond(
---> 59 pred, true_fn=true_fn, false_fn=false_fn, name=name)
60
61
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/smart_cond.py in smart_cond(pred, true_fn, false_fn, name)
52 if pred_value is not None:
53 if pred_value:
---> 54 return true_fn()
55 else:
56 return false_fn()
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/utils.py in <lambda>()
110 return tf_utils.smart_cond(
111 training,
--> 112 lambda: replace_training_and_call(True),
113 lambda: replace_training_and_call(False))
114
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/utils.py in replace_training_and_call(training)
106 def replace_training_and_call(training):
107 set_training_arg(training, training_arg_index, args, kwargs)
--> 108 return wrapped_call(*args, **kwargs)
109
110 return tf_utils.smart_cond(
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in __call__(self, *args, **kwds)
566 xla_context.Exit()
567 else:
--> 568 result = self._call(*args, **kwds)
569
570 if tracing_count == self._get_tracing_count():
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _call(self, *args, **kwds)
604 # In this case we have not created variables on the first call. So we can
605 # run the first trace but we should fail if variables are created.
--> 606 results = self._stateful_fn(*args, **kwds)
607 if self._created_variables:
608 raise ValueError("Creating variables on a non-first call to a function"
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in __call__(self, *args, **kwargs)
2361 with self._lock:
2362 graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
-> 2363 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
2364
2365 #property
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _filtered_call(self, args, kwargs)
1609 if isinstance(t, (ops.Tensor,
1610 resource_variable_ops.BaseResourceVariable))),
-> 1611 self.captured_inputs)
1612
1613 def _call_flat(self, args, captured_inputs, cancellation_manager=None):
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1695 possible_gradient_type,
1696 executing_eagerly)
-> 1697 forward_function, args_with_tangents = forward_backward.forward()
1698 if executing_eagerly:
1699 flat_outputs = forward_function.call(
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in forward(self)
1421 """Builds or retrieves a forward function for this call."""
1422 forward_function = self._functions.forward(
-> 1423 self._inference_args, self._input_tangents)
1424 return forward_function, self._inference_args + self._input_tangents
1425
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in forward(self, inference_args, input_tangents)
1183 (self._forward, self._forward_graph, self._backward,
1184 self._forwardprop_output_indices, self._num_forwardprop_outputs) = (
-> 1185 self._forward_and_backward_functions(inference_args, input_tangents))
1186 return self._forward
1187
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _forward_and_backward_functions(self, inference_args, input_tangents)
1329 outputs = self._func_graph.outputs[:self._num_inference_outputs]
1330 return self._build_functions_for_outputs(
-> 1331 outputs, inference_args, input_tangents)
1332
1333
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _build_functions_for_outputs(self, outputs, inference_args, input_tangents)
888 self._func_graph.inputs,
889 grad_ys=gradients_wrt_outputs,
--> 890 src_graph=self._func_graph)
891
892 captures_from_forward = [
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in _GradientsHelper(ys, xs, grad_ys, name, colocate_gradients_with_ops, gate_gradients, aggregation_method, stop_gradients, unconnected_gradients, src_graph)
667 # functions.
668 in_grads = _MaybeCompile(grad_scope, op, func_call,
--> 669 lambda: grad_fn(op, *out_grads))
670 else:
671 # For function call ops, we add a 'SymbolicGradient'
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in _MaybeCompile(scope, op, func, grad_fn)
334 xla_scope = op.get_attr("_XlaScope").decode()
335 except ValueError:
--> 336 return grad_fn() # Exit early
337
338 if not xla_compile:
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in <lambda>()
667 # functions.
668 in_grads = _MaybeCompile(grad_scope, op, func_call,
--> 669 lambda: grad_fn(op, *out_grads))
670 else:
671 # For function call ops, we add a 'SymbolicGradient'
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _rewrite_forward_and_call_backward(self, op, *doutputs)
705 def _rewrite_forward_and_call_backward(self, op, *doutputs):
706 """Add outputs to the forward call and feed them to the grad function."""
--> 707 forward_function, backwards_function = self.forward_backward(len(doutputs))
708 if not backwards_function.outputs:
709 return backwards_function.structured_outputs
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in forward_backward(self, num_doutputs)
614 if forward_backward is not None:
615 return forward_backward
--> 616 forward, backward = self._construct_forward_backward(num_doutputs)
617 self._cached_function_pairs[num_doutputs] = (forward, backward)
618 return forward, backward
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _construct_forward_backward(self, num_doutputs)
662 args=[], kwargs={},
663 signature=signature,
--> 664 func_graph=backwards_graph)
665 backwards_graph_captures = backwards_graph.external_captures
666 captures_from_forward = [
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
976 converted_func)
977
--> 978 func_outputs = python_func(*func_args, **func_kwargs)
979
980 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _backprop_function(*grad_ys)
652 self._func_graph.inputs,
653 grad_ys=grad_ys,
--> 654 src_graph=self._func_graph)
655
656 with self._func_graph.as_default():
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in _GradientsHelper(ys, xs, grad_ys, name, colocate_gradients_with_ops, gate_gradients, aggregation_method, stop_gradients, unconnected_gradients, src_graph)
667 # functions.
668 in_grads = _MaybeCompile(grad_scope, op, func_call,
--> 669 lambda: grad_fn(op, *out_grads))
670 else:
671 # For function call ops, we add a 'SymbolicGradient'
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in _MaybeCompile(scope, op, func, grad_fn)
334 xla_scope = op.get_attr("_XlaScope").decode()
335 except ValueError:
--> 336 return grad_fn() # Exit early
337
338 if not xla_compile:
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in <lambda>()
667 # functions.
668 in_grads = _MaybeCompile(grad_scope, op, func_call,
--> 669 lambda: grad_fn(op, *out_grads))
670 else:
671 # For function call ops, we add a 'SymbolicGradient'
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _rewrite_forward_and_call_backward(self, op, *doutputs)
705 def _rewrite_forward_and_call_backward(self, op, *doutputs):
706 """Add outputs to the forward call and feed them to the grad function."""
--> 707 forward_function, backwards_function = self.forward_backward(len(doutputs))
708 if not backwards_function.outputs:
709 return backwards_function.structured_outputs
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in forward_backward(self, num_doutputs)
614 if forward_backward is not None:
615 return forward_backward
--> 616 forward, backward = self._construct_forward_backward(num_doutputs)
617 self._cached_function_pairs[num_doutputs] = (forward, backward)
618 return forward, backward
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _construct_forward_backward(self, num_doutputs)
662 args=[], kwargs={},
663 signature=signature,
--> 664 func_graph=backwards_graph)
665 backwards_graph_captures = backwards_graph.external_captures
666 captures_from_forward = [
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
976 converted_func)
977
--> 978 func_outputs = python_func(*func_args, **func_kwargs)
979
980 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _backprop_function(*grad_ys)
652 self._func_graph.inputs,
653 grad_ys=grad_ys,
--> 654 src_graph=self._func_graph)
655
656 with self._func_graph.as_default():
~/work/tf/lib/python3.7/site-packages/tensorflow_core/python/ops/gradients_util.py in _GradientsHelper(ys, xs, grad_ys, name, colocate_gradients_with_ops, gate_gradients, aggregation_method, stop_gradients, unconnected_gradients, src_graph)
621 raise LookupError(
622 "No gradient defined for operation '%s' (op type: %s)" %
--> 623 (op.name, op.type))
624 if loop_state:
625 loop_state.EnterGradWhileContext(op, before=False)
LookupError: No gradient defined for operation 'while' (op type: While)
I have run into that in the past. The following is how I save/load keras models.
Note that the architecture and the weights are separate.
#saving model
open('model_weights.h5', 'w').write(model.to_json())
model.save_weights('architecture.json', overwrite=True)
from tensorflow.keras.models import model_from_json
#loading model
model = model_from_json(open('architecture.json').read())
model.load_weights('model_weights.h5')
This is a mysterious error --to me-- that keeps propping up.
For a reproducible example, you can find the Jupyter Notebook here: https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/blob/master/Chapter5_LossFunctions/Ch5_LossFunctions_TFP.ipynb) -- Chapter 5 (Loss Functions).
Conveniently, in this example, the data are artificial and constructed on the fly.
The part of the code that creates the problem is the following (I am running tensorflow 2):
# Code for creating artificial "dummy" data
# This is a common strategy for testing our models
# before applying it to real-world data
num_data = 100
X_data = (0.025 * tfd.Normal(loc=0.,scale=1.).sample(sample_shape=num_data))
Y_data = (0.5 * X_data + 0.01 * tfd.Normal(loc=0.,scale=1.).sample(sample_shape=num_data))
tf_var_data = tf.nn.moments(X_data, axes=0)[1]
covar = tfp.stats.covariance(X_data,Y_data, sample_axis=0, event_axis=None)
ls_coef = covar / tf_var_data
[
X_data_, Y_data_, ls_coef_,
] = [
X_data.numpy(), Y_data.numpy(), ls_coef.numpy(),
]
ls_intercept_ = Y_data_.mean() - ls_coef_ * X_data_.mean()
obs_stdev = tf.sqrt(
tf.reduce_mean(tf.math.squared_difference(Y_data_, tf.reduce_mean(Y_data_, axis=0)),
axis=0))
# Let's define the log probability of the bayesian regression function
def finance_posterior_log_prob(X_data_, Y_data_, alpha, beta, sigma):
"""
Our posterior log probability, as a function of states
Args:
alpha_: scalar, taken from state of the HMC
beta_: scalar, taken from state of the HMC
sigma_: scalar, the standard deviation of , taken from state of the HMC
Returns:
Scalar sum of log probabilities
Closure over: Y_data, X_data
"""
rv_std = tfd.Uniform(name="std", low=0., high=100.)
rv_beta = tfd.Normal(name="beta", loc=0., scale=100.)
rv_alpha = tfd.Normal(name="alpha", loc=0., scale=100.)
mean = alpha + beta * X_data_
rv_observed = tfd.Normal(name="obs", loc=mean, scale=sigma)
return (
rv_alpha.log_prob(alpha)
+ rv_beta.log_prob(beta)
+ rv_std.log_prob(sigma)
+ tf.reduce_sum(rv_observed.log_prob(Y_data_))
)
number_of_steps = 30000
burnin = 5000
# Set the chain's start state.
initial_chain_state = [
tf.cast(1.,dtype=tf.float32) * tf.ones([], name='init_alpha', dtype=tf.float32),
tf.cast(0.01,dtype=tf.float32) * tf.ones([], name='init_beta', dtype=tf.float32),
tf.cast(obs_stdev,dtype=tf.float32) * tf.ones([], name='init_sigma', dtype=tf.float32)
]
# Since HMC operates over unconstrained space, we need to transform the
# samples so they live in real-space.
# Beta and sigma are 100x and 10x of alpha, approximately, so apply Affine scalar bijector
# to multiply the unconstrained beta and sigma by 100x and 10x to get back to
# the problem space
unconstraining_bijectors = [
tfp.bijectors.Identity(), #alpha
tfp.bijectors.Shift(100.), #beta
tfp.bijectors.Scale(10.), #sigma
]
# Define a closure over our joint_log_prob.
unnormalized_posterior_log_prob = lambda *args: finance_posterior_log_prob(X_data_, Y_data_, *args)
step_size = 0.5
# Defining the HMC
kernel=tfp.mcmc.TransformedTransitionKernel(
inner_kernel=tfp.mcmc.HamiltonianMonteCarlo(
target_log_prob_fn=unnormalized_posterior_log_prob,
num_leapfrog_steps=2,
step_size=step_size,
state_gradients_are_stopped=True),
bijector=unconstraining_bijectors)
kernel = tfp.mcmc.SimpleStepSizeAdaptation(
inner_kernel=kernel, num_adaptation_steps=int(burnin * 0.8))
# Sampling from the chain.
[
alpha,
beta,
sigma
], kernel_results = tfp.mcmc.sample_chain(
num_results = number_of_steps,
num_burnin_steps = burnin,
current_state=initial_chain_state,
kernel=kernel,
name='HMC_sampling'
)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-63-b2e46a99062a> in <module>
21 current_state=initial_chain_state,
22 kernel=kernel,
---> 23 name='HMC_sampling'
24 )
25
~\Anaconda3\envs\tf2\lib\site-packages\tensorflow_probability\python\mcmc\sample.py in sample_chain(num_results, current_state, previous_kernel_results, kernel, num_burnin_steps, num_steps_between_results, trace_fn, return_final_kernel_results, parallel_iterations, name)
357 trace_fn(*state_and_results)),
358 # pylint: enable=g-long-lambda
--> 359 parallel_iterations=parallel_iterations)
360
361 if return_final_kernel_results:
~\Anaconda3\envs\tf2\lib\site-packages\tensorflow_probability\python\mcmc\internal\util.py in trace_scan(loop_fn, initial_state, elems, trace_fn, parallel_iterations, name)
393 body=_body,
394 loop_vars=(0, initial_state, trace_arrays),
--> 395 parallel_iterations=parallel_iterations)
396
397 stacked_trace = tf.nest.map_structure(lambda x: x.stack(), trace_arrays)
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\util\deprecation.py in new_func(*args, **kwargs)
572 func.__module__, arg_name, arg_value, 'in a future version'
573 if date is None else ('after %s' % date), instructions)
--> 574 return func(*args, **kwargs)
575
576 doc = _add_deprecated_arg_value_notice_to_docstring(
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\ops\control_flow_ops.py in while_loop_v2(cond, body, loop_vars, shape_invariants, parallel_iterations, back_prop, swap_memory, maximum_iterations, name)
2489 name=name,
2490 maximum_iterations=maximum_iterations,
-> 2491 return_same_structure=True)
2492
2493
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\ops\control_flow_ops.py in while_loop(cond, body, loop_vars, shape_invariants, parallel_iterations, back_prop, swap_memory, name, maximum_iterations, return_same_structure)
2725 list(loop_vars))
2726 while cond(*loop_vars):
-> 2727 loop_vars = body(*loop_vars)
2728 if try_to_pack and not isinstance(loop_vars, (list, _basetuple)):
2729 packed = True
~\Anaconda3\envs\tf2\lib\site-packages\tensorflow_probability\python\mcmc\internal\util.py in _body(i, state, trace_arrays)
382
383 def _body(i, state, trace_arrays):
--> 384 state = loop_fn(state, elems_array.read(i))
385 trace_arrays = tf.nest.pack_sequence_as(trace_arrays, [
386 a.write(i, v) for a, v in zip(
~\Anaconda3\envs\tf2\lib\site-packages\tensorflow_probability\python\mcmc\sample.py in _trace_scan_fn(state_and_results, num_steps)
341 body_fn=kernel.one_step,
342 initial_loop_vars=list(state_and_results),
--> 343 parallel_iterations=parallel_iterations)
344 return next_state, current_kernel_results
345
~\Anaconda3\envs\tf2\lib\site-packages\tensorflow_probability\python\mcmc\internal\util.py in smart_for_loop(loop_num_iter, body_fn, initial_loop_vars, parallel_iterations, name)
315 body=lambda i, *args: [i + 1] + list(body_fn(*args)),
316 loop_vars=[np.int32(0)] + initial_loop_vars,
--> 317 parallel_iterations=parallel_iterations
318 )[1:]
319 result = initial_loop_vars
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\util\deprecation.py in new_func(*args, **kwargs)
572 func.__module__, arg_name, arg_value, 'in a future version'
573 if date is None else ('after %s' % date), instructions)
--> 574 return func(*args, **kwargs)
575
576 doc = _add_deprecated_arg_value_notice_to_docstring(
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\ops\control_flow_ops.py in while_loop_v2(cond, body, loop_vars, shape_invariants, parallel_iterations, back_prop, swap_memory, maximum_iterations, name)
2489 name=name,
2490 maximum_iterations=maximum_iterations,
-> 2491 return_same_structure=True)
2492
2493
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\ops\control_flow_ops.py in while_loop(cond, body, loop_vars, shape_invariants, parallel_iterations, back_prop, swap_memory, name, maximum_iterations, return_same_structure)
2725 list(loop_vars))
2726 while cond(*loop_vars):
-> 2727 loop_vars = body(*loop_vars)
2728 if try_to_pack and not isinstance(loop_vars, (list, _basetuple)):
2729 packed = True
~\Anaconda3\envs\tf2\lib\site-packages\tensorflow_probability\python\mcmc\internal\util.py in <lambda>(i, *args)
313 return tf.while_loop(
314 cond=lambda i, *args: i < loop_num_iter,
--> 315 body=lambda i, *args: [i + 1] + list(body_fn(*args)),
316 loop_vars=[np.int32(0)] + initial_loop_vars,
317 parallel_iterations=parallel_iterations
~\Anaconda3\envs\tf2\lib\site-packages\tensorflow_probability\python\mcmc\simple_step_size_adaptation.py in one_step(self, current_state, previous_kernel_results)
378 reduced_log_accept_prob = reduce_logmeanexp(
379 log_accept_prob,
--> 380 axis=prefer_static.range(num_reduce_dims))
381 # reduced_log_accept_prob must broadcast into step_size_part on the
382 # left, so we do an additional reduction over dimensions where their
~\Anaconda3\envs\tf2\lib\site-packages\tensorflow_probability\python\math\generic.py in reduce_logmeanexp(input_tensor, axis, keepdims, name)
109 lse = tf.reduce_logsumexp(input_tensor, axis=axis, keepdims=keepdims)
110 n = prefer_static.size(input_tensor) // prefer_static.size(lse)
--> 111 log_n = tf.math.log(tf.cast(n, lse.dtype))
112 return lse - log_n
113
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\util\dispatch.py in wrapper(*args, **kwargs)
178 """Call target, and fall back on dispatchers if there is a TypeError."""
179 try:
--> 180 return target(*args, **kwargs)
181 except (TypeError, ValueError):
182 # Note: convert_to_eager_tensor currently raises a ValueError, not a
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\ops\math_ops.py in cast(x, dtype, name)
746 # allows some conversions that cast() can't do, e.g. casting numbers to
747 # strings.
--> 748 x = ops.convert_to_tensor(x, name="x")
749 if x.dtype.base_dtype != base_type:
750 x = gen_math_ops.cast(x, base_type, name=name)
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\framework\ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
1348
1349 if ret is None:
-> 1350 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1351
1352 if ret is NotImplemented:
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\framework\tensor_conversion_registry.py in _default_conversion_function(***failed resolving arguments***)
50 def _default_conversion_function(value, dtype, name, as_ref):
51 del as_ref # Unused.
---> 52 return constant_op.constant(value, dtype, name=name)
53
54
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\framework\constant_op.py in constant(value, dtype, shape, name)
256 """
257 return _constant_impl(value, dtype, shape, name, verify_shape=False,
--> 258 allow_broadcast=True)
259
260
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\framework\constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
264 ctx = context.context()
265 if ctx.executing_eagerly():
--> 266 t = convert_to_eager_tensor(value, ctx, dtype)
267 if shape is None:
268 return t
~\AppData\Roaming\Python\Python37\site-packages\tensorflow_core\python\framework\constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
94 dtype = dtypes.as_dtype(dtype).as_datatype_enum
95 ctx.ensure_initialized()
---> 96 return ops.EagerTensor(value, ctx.device_name, dtype)
97
98
ValueError: Failed to convert a NumPy array to a Tensor (Unsupported numpy type: NPY_INT).
problem seems to come from
kernel = tfp.mcmc.SimpleStepSizeAdaptation(
inner_kernel=kernel, num_adaptation_steps=int(burnin * 0.8))
in another similar example, I got same error. if you skip this line, it works.
I am trying to create a custom Numba Type. I am having issues boxing and unboxing Numba Numpy Arrays to a Native Numpy Arrays.
I have searched online for similar issues and followed the documentation example to the best of my ability. (https://numba.pydata.org/numba-doc/latest/extending/interval-example.html).
I have tried to interpret (https://github.com/numba/numba/blob/master/numba/targets/boxing.py) but it is quite difficult. Therefore, I think I might be doing something small wrong.
Below is my current attempt at including a Numpy array in my custom type.
import numpy as np
from numba import types, cgutils
from numba.extending import typeof_impl, type_callable, models
from numba.extending import register_model, make_attribute_wrapper, overload_attribute
from numba.extending import lower_builtin, unbox, NativeValue, box
class BMatrix(object):
"""
A empty wrapper for a Binary Matrix
"""
def __init__(self, m, n, row_index):#, col_index):
self.m = m
self.n = n
self.row_index = row_index
# self.col_i = col_index
def __repr__(self):
return 'BMatrix(%d, %d)' % (self.m, self.n)
#property
def shape(self):
return (self.m, self.n)
class BMatrixType(types.Type):
def __init__(self):
super(BMatrixType, self).__init__(name='BMatrix')
bmatrix_type = BMatrixType()
#typeof_impl.register(BMatrix)
def typeof_index(val, c):
return bmatrix_type
#type_callable(BMatrix)
def type_bmatrix(context):
def typer(m, n, row_index):
if (isinstance(m, types.Integer)
and isinstance(n, types.Integer)
and isinstance(row_index, nb.types.Array)):
# and isinstance(col_index, nb.types.Array)):
return bmatrix_type
return typer
#register_model(BMatrixType)
class BMatrixModel(models.StructModel):
def __init__(self, dmm, fe_type):
members = [
('m', types.int64),
('n', types.int64),
('row_index', types.Array(types.int64, 1, 'C'))
]
models.StructModel.__init__(self, dmm, fe_type, members)
make_attribute_wrapper(BMatrixType, 'm', 'm')
make_attribute_wrapper(BMatrixType, 'n', 'n')
make_attribute_wrapper(BMatrixType, 'row_index', 'row_index')
#overload_attribute(BMatrixType, "shape")
def get_shape(bmatrix):
def getter(bmatrix):
return (bmatrix.m, bmatrix.n)
return getter
#lower_builtin(BMatrix, types.Integer, types.Integer, types.Array) #nb.types.Array, #nb.types.Array)
def impl_bmatrix(context, builder, sig, args):
typ = sig.return_type
m, n, row_index = args
bmatrix = cgutils.create_struct_proxy(typ)(context, builder)
bmatrix.m = m
bmatrix.n = n
bmatrix.row_index = row_index
return bmatrix._getvalue()
#unbox(BMatrixType)
def unbox_bmatrix(typ, obj, c):
"""
Convert a BMatrixType object to a native interval structure.
"""
m_obj = c.pyapi.object_getattr_string(obj, "m")
n_obj = c.pyapi.object_getattr_string(obj, "n")
row_index_obj = c.pyapi.object_getattr_string(obj, "row_index")
BMatrix = cgutils.create_struct_proxy(typ)(c.context, c.builder)
BMatrix.m = c.pyapi.long_as_longlong(m_obj)
BMatrix.n = c.pyapi.long_as_longlong(n_obj)
BMatrix.row_index = nb.targets.boxing.unbox_array(types.Array(types.int64, 1, 'C'),
row_index_obj, c)
c.pyapi.decref(m_obj)
c.pyapi.decref(n_obj)
c.pyapi.decref(row_index_obj)
is_error = cgutils.is_not_null(c.builder, c.pyapi.err_occurred())
return NativeValue(BMatrix._getvalue(), is_error=is_error)
#box(BMatrixType)
def box_bmatrix(typ, val, c):
"""
Convert a native bmatrix structure to an BMatrix object.
"""
Bmatrix = cgutils.create_struct_proxy(typ)(c.context, c.builder, value=val)
m_obj = c.pyapi.long_from_longlong(Bmatrix.m)
n_obj = c.pyapi.long_from_longlong(Bmatrix.n)
row_index_obj = nb.targets.boxing.box_array(types.Array(types.int64, 1, 'C'),
Bmatrix.row_index, c)
class_obj = c.pyapi.unserialize(c.pyapi.serialize_object(Bmatrix))
res = c.pyapi.call_function_objargs(class_obj, (m_obj, n_obj))
c.pyapi.decref(m_obj)
c.pyapi.decref(n_obj)
c.pyapi.decref(row_index_obj)
c.pyapi.decref(class_obj)
return res
Test Cases (The error Tracebacks are absolutely massive for test_2 and test_3).
#nb.jit(nopython=True)
def test_1(): #Runs
x = BMatrix(10, 10, np.array([10,10,10]))
def test_2(): #Errors
x = BMatrix(10, 10, np.array([10,10,10]))
#nb.jit(nopython=True)
def _test_2(y):
return y
return _test_2(x)
#nb.jit(nopython=True)
def test_3(): #Errors
return BMatrix(10, 10, np.array([10,10,10]))
#nb.jit(nopython=True)
def test_4():
return BMatrix(10, 10, np.array([10,10,10])).row_index
These are the error when I run the test cases
test_1() #Runs
test_2()
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-52-0f6d1bdba40b> in <module>
----> 1 test_2()
<ipython-input-51-60141c9792c1> in test_2()
9 return y
10
---> 11 return _test_2(x)
12 #nb.jit(nopython=True)
13 def test_3():
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in _compile_for_args(self, *args, **kws)
368 e.patch_message(''.join(e.args) + help_msg)
369 # ignore the FULL_TRACEBACKS config, this needs reporting!
--> 370 raise e
371
372 def inspect_llvm(self, signature=None):
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in _compile_for_args(self, *args, **kws)
325 argtypes.append(self.typeof_pyval(a))
326 try:
--> 327 return self.compile(tuple(argtypes))
328 except errors.TypingError as e:
329 # Intercept typing error that may be due to an argument
//anaconda3/lib/python3.7/site-packages/numba/compiler_lock.py in _acquire_compile_lock(*args, **kwargs)
30 def _acquire_compile_lock(*args, **kwargs):
31 with self:
---> 32 return func(*args, **kwargs)
33 return _acquire_compile_lock
34
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in compile(self, sig)
657
658 self._cache_misses[sig] += 1
--> 659 cres = self._compiler.compile(args, return_type)
660 self.add_overload(cres)
661 self._cache.save_overload(sig, cres)
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in compile(self, args, return_type)
81 args=args, return_type=return_type,
82 flags=flags, locals=self.locals,
---> 83 pipeline_class=self.pipeline_class)
84 # Check typing error if object mode is used
85 if cres.typing_error is not None and not flags.enable_pyobject:
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in compile_extra(typingctx, targetctx, func, args, return_type, flags, locals, library, pipeline_class)
953 pipeline = pipeline_class(typingctx, targetctx, library,
954 args, return_type, flags, locals)
--> 955 return pipeline.compile_extra(func)
956
957
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in compile_extra(self, func)
375 self.lifted = ()
376 self.lifted_from = None
--> 377 return self._compile_bytecode()
378
379 def compile_ir(self, func_ir, lifted=(), lifted_from=None):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _compile_bytecode(self)
884 """
885 assert self.func_ir is None
--> 886 return self._compile_core()
887
888 def _compile_ir(self):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _compile_core(self)
871 self.define_pipelines(pm)
872 pm.finalize()
--> 873 res = pm.run(self.status)
874 if res is not None:
875 # Early pipeline completion
//anaconda3/lib/python3.7/site-packages/numba/compiler_lock.py in _acquire_compile_lock(*args, **kwargs)
30 def _acquire_compile_lock(*args, **kwargs):
31 with self:
---> 32 return func(*args, **kwargs)
33 return _acquire_compile_lock
34
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in run(self, status)
252 # No more fallback pipelines?
253 if is_final_pipeline:
--> 254 raise patched_exception
255 # Go to next fallback pipeline
256 else:
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in run(self, status)
243 try:
244 event("-- %s" % stage_name)
--> 245 stage()
246 except _EarlyPipelineCompletion as e:
247 return e.result
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in stage_nopython_backend(self)
745 """
746 lowerfn = self.backend_nopython_mode
--> 747 self._backend(lowerfn, objectmode=False)
748
749 def stage_compile_interp_mode(self):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _backend(self, lowerfn, objectmode)
685 self.library.enable_object_caching()
686
--> 687 lowered = lowerfn()
688 signature = typing.signature(self.return_type, *self.args)
689 self.cr = compile_result(
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in backend_nopython_mode(self)
672 self.calltypes,
673 self.flags,
--> 674 self.metadata)
675
676 def _backend(self, lowerfn, objectmode):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in native_lowering_stage(targetctx, library, interp, typemap, restype, calltypes, flags, metadata)
1124 lower.lower()
1125 if not flags.no_cpython_wrapper:
-> 1126 lower.create_cpython_wrapper(flags.release_gil)
1127 env = lower.env
1128 call_helper = lower.call_helper
//anaconda3/lib/python3.7/site-packages/numba/lowering.py in create_cpython_wrapper(self, release_gil)
269 self.context.create_cpython_wrapper(self.library, self.fndesc,
270 self.env, self.call_helper,
--> 271 release_gil=release_gil)
272
273 def setup_function(self, fndesc):
//anaconda3/lib/python3.7/site-packages/numba/targets/cpu.py in create_cpython_wrapper(self, library, fndesc, env, call_helper, release_gil)
155 fndesc, env, call_helper=call_helper,
156 release_gil=release_gil)
--> 157 builder.build()
158 library.add_ir_module(wrapper_module)
159
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in build(self)
120
121 api = self.context.get_python_api(builder)
--> 122 self.build_wrapper(api, builder, closure, args, kws)
123
124 return wrapper, api
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in build_wrapper(self, api, builder, closure, args, kws)
153 innerargs.append(None)
154 else:
--> 155 val = cleanup_manager.add_arg(builder.load(obj), ty)
156 innerargs.append(val)
157
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in add_arg(self, obj, ty)
30 """
31 # Unbox argument
---> 32 native = self.api.to_native_value(ty, obj)
33
34 # If an error occurred, go to the cleanup block for the previous argument.
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in to_native_value(self, typ, obj)
1423 impl = _unboxers.lookup(typ.__class__, unbox_unsupported)
1424 c = _UnboxContext(self.context, self.builder, self)
-> 1425 return impl(typ, obj, c)
1426
1427 def from_native_return(self, typ, val, env_manager):
<ipython-input-45-d8ac5afde794> in unbox_bmatrix(typ, obj, c)
85 BMatrix.n = c.pyapi.long_as_longlong(n_obj)
86 BMatrix.row_index = nb.targets.boxing.unbox_array(types.Array(types.int64, 1, 'C'),
---> 87 row_index_obj, c)
88 c.pyapi.decref(m_obj)
89 c.pyapi.decref(n_obj)
//anaconda3/lib/python3.7/site-packages/numba/cgutils.py in __setattr__(self, field, value)
162 if field.startswith('_'):
163 return super(_StructProxy, self).__setattr__(field, value)
--> 164 self[self._datamodel.get_field_position(field)] = value
165
166 def __getitem__(self, index):
//anaconda3/lib/python3.7/site-packages/numba/cgutils.py in __setitem__(self, index, value)
177 ptr = self._get_ptr_by_index(index)
178 value = self._cast_member_from_value(index, value)
--> 179 if value.type != ptr.type.pointee:
180 if (is_pointer(value.type) and is_pointer(ptr.type.pointee)
181 and value.type.pointee == ptr.type.pointee.pointee):
AttributeError: Failed in nopython mode pipeline (step: nopython mode backend)
'NativeValue' object has no attribute 'type'
test_3()
KeyError Traceback (most recent call last)
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in serialize_object(self, obj)
1403 try:
-> 1404 gv = self.module.__serialized[obj]
1405 except KeyError:
KeyError: <numba.cgutils.ValueStructProxy_BMatrix object at 0x11e693f28>
During handling of the above exception, another exception occurred:
PicklingError Traceback (most recent call last)
<ipython-input-53-8d78c7c0acee> in <module>
----> 1 test_3()
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in _compile_for_args(self, *args, **kws)
368 e.patch_message(''.join(e.args) + help_msg)
369 # ignore the FULL_TRACEBACKS config, this needs reporting!
--> 370 raise e
371
372 def inspect_llvm(self, signature=None):
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in _compile_for_args(self, *args, **kws)
325 argtypes.append(self.typeof_pyval(a))
326 try:
--> 327 return self.compile(tuple(argtypes))
328 except errors.TypingError as e:
329 # Intercept typing error that may be due to an argument
//anaconda3/lib/python3.7/site-packages/numba/compiler_lock.py in _acquire_compile_lock(*args, **kwargs)
30 def _acquire_compile_lock(*args, **kwargs):
31 with self:
---> 32 return func(*args, **kwargs)
33 return _acquire_compile_lock
34
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in compile(self, sig)
657
658 self._cache_misses[sig] += 1
--> 659 cres = self._compiler.compile(args, return_type)
660 self.add_overload(cres)
661 self._cache.save_overload(sig, cres)
//anaconda3/lib/python3.7/site-packages/numba/dispatcher.py in compile(self, args, return_type)
81 args=args, return_type=return_type,
82 flags=flags, locals=self.locals,
---> 83 pipeline_class=self.pipeline_class)
84 # Check typing error if object mode is used
85 if cres.typing_error is not None and not flags.enable_pyobject:
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in compile_extra(typingctx, targetctx, func, args, return_type, flags, locals, library, pipeline_class)
953 pipeline = pipeline_class(typingctx, targetctx, library,
954 args, return_type, flags, locals)
--> 955 return pipeline.compile_extra(func)
956
957
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in compile_extra(self, func)
375 self.lifted = ()
376 self.lifted_from = None
--> 377 return self._compile_bytecode()
378
379 def compile_ir(self, func_ir, lifted=(), lifted_from=None):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _compile_bytecode(self)
884 """
885 assert self.func_ir is None
--> 886 return self._compile_core()
887
888 def _compile_ir(self):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _compile_core(self)
871 self.define_pipelines(pm)
872 pm.finalize()
--> 873 res = pm.run(self.status)
874 if res is not None:
875 # Early pipeline completion
//anaconda3/lib/python3.7/site-packages/numba/compiler_lock.py in _acquire_compile_lock(*args, **kwargs)
30 def _acquire_compile_lock(*args, **kwargs):
31 with self:
---> 32 return func(*args, **kwargs)
33 return _acquire_compile_lock
34
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in run(self, status)
252 # No more fallback pipelines?
253 if is_final_pipeline:
--> 254 raise patched_exception
255 # Go to next fallback pipeline
256 else:
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in run(self, status)
243 try:
244 event("-- %s" % stage_name)
--> 245 stage()
246 except _EarlyPipelineCompletion as e:
247 return e.result
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in stage_nopython_backend(self)
745 """
746 lowerfn = self.backend_nopython_mode
--> 747 self._backend(lowerfn, objectmode=False)
748
749 def stage_compile_interp_mode(self):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in _backend(self, lowerfn, objectmode)
685 self.library.enable_object_caching()
686
--> 687 lowered = lowerfn()
688 signature = typing.signature(self.return_type, *self.args)
689 self.cr = compile_result(
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in backend_nopython_mode(self)
672 self.calltypes,
673 self.flags,
--> 674 self.metadata)
675
676 def _backend(self, lowerfn, objectmode):
//anaconda3/lib/python3.7/site-packages/numba/compiler.py in native_lowering_stage(targetctx, library, interp, typemap, restype, calltypes, flags, metadata)
1124 lower.lower()
1125 if not flags.no_cpython_wrapper:
-> 1126 lower.create_cpython_wrapper(flags.release_gil)
1127 env = lower.env
1128 call_helper = lower.call_helper
//anaconda3/lib/python3.7/site-packages/numba/lowering.py in create_cpython_wrapper(self, release_gil)
269 self.context.create_cpython_wrapper(self.library, self.fndesc,
270 self.env, self.call_helper,
--> 271 release_gil=release_gil)
272
273 def setup_function(self, fndesc):
//anaconda3/lib/python3.7/site-packages/numba/targets/cpu.py in create_cpython_wrapper(self, library, fndesc, env, call_helper, release_gil)
155 fndesc, env, call_helper=call_helper,
156 release_gil=release_gil)
--> 157 builder.build()
158 library.add_ir_module(wrapper_module)
159
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in build(self)
120
121 api = self.context.get_python_api(builder)
--> 122 self.build_wrapper(api, builder, closure, args, kws)
123
124 return wrapper, api
//anaconda3/lib/python3.7/site-packages/numba/callwrapper.py in build_wrapper(self, api, builder, closure, args, kws)
174
175 retty = self._simplified_return_type()
--> 176 obj = api.from_native_return(retty, retval, env_manager)
177 builder.ret(obj)
178
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in from_native_return(self, typ, val, env_manager)
1429 "prevented the return of " \
1430 "optional value"
-> 1431 out = self.from_native_value(typ, val, env_manager)
1432 return out
1433
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in from_native_value(self, typ, val, env_manager)
1443
1444 c = _BoxContext(self.context, self.builder, self, env_manager)
-> 1445 return impl(typ, val, c)
1446
1447 def reflect_native_value(self, typ, val, env_manager=None):
<ipython-input-45-d8ac5afde794> in box_bmatrix(typ, val, c)
104 Bmatrix.row_index, c)
105
--> 106 class_obj = c.pyapi.unserialize(c.pyapi.serialize_object(Bmatrix))
107 res = c.pyapi.call_function_objargs(class_obj, (m_obj, n_obj))
108 c.pyapi.decref(m_obj)
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in serialize_object(self, obj)
1404 gv = self.module.__serialized[obj]
1405 except KeyError:
-> 1406 struct = self.serialize_uncached(obj)
1407 name = ".const.picklebuf.%s" % (id(obj) if config.DIFF_IR == 0 else "DIFF_IR")
1408 gv = self.context.insert_unique_const(self.module, name, struct)
//anaconda3/lib/python3.7/site-packages/numba/pythonapi.py in serialize_uncached(self, obj)
1383 """
1384 # First make the array constant
-> 1385 data = pickle.dumps(obj, protocol=-1)
1386 assert len(data) < 2**31
1387 name = ".const.pickledata.%s" % (id(obj) if config.DIFF_IR == 0 else "DIFF_IR")
PicklingError: Failed in nopython mode pipeline (step: nopython mode backend)
Can't pickle <class 'numba.cgutils.ValueStructProxy_BMatrix'>: attribute lookup ValueStructProxy_BMatrix on numba.cgutils failed
test_4() #Runs Wrong
array([-2387225703656530210, -2387225703656530210, -2387225703656530210])
unbox_array returns a NativeValue. Inside NativeValue is the actual value which is what you want to assign to row_index. So, just add ".value" to the end of the following line to extract the value from the NativeValue.
BMatrix.row_index = nb.targets.boxing.unbox_array(types.Array(types.int64, 1, 'C'), row_index_obj, c)
I was creating a custom layer based off the NALU paper, but when testing my code in Google Colab (tensorflow version 1.10.0) I got a type error. This did not hapen in my local Jupyter notebook(tensorflow cpu version 1.8.0).
The type error appears to occurring when adding a weight in the build function of Layer. When adding the weight a type error occurs when code tries to divide the Dimension by a float. I thought this might be an error with how Keras handles arguments, so I dropped the initializer. Even without the initializer, it is not possible to add a weight to the layer. I got the structure of my code from tensorflow's keras tutorial and I am wondering if there is anything that I need to do in order to update my code to work with the most recent version of tensorflow.
TypeError Traceback (most recent call last)
<ipython-input-7-55fb94a8f3b1> in <module>()
82 y_test = x_test[:, 0] * x_test[:, 1]
83
---> 84 model = nalu_model()
85
86 model.compile(optimizer='RMSProp',
<ipython-input-7-55fb94a8f3b1> in nalu_model()
48 def nalu_model():
49 inp = tf.keras.layers.Input(shape=(2,))
---> 50 out = NALU(1)(inp)
51
52 model = tf.keras.models.Model(inputs=inp, outputs=out)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
726 if all(hasattr(x, 'shape') for x in input_list):
727 input_shapes = nest.map_structure(lambda x: x.shape, inputs)
--> 728 self.build(input_shapes)
729 self.built = True
730
<ipython-input-7-55fb94a8f3b1> in build(self, input_shape)
9 shape = tf.TensorShape((input_shape[1], self.num_outputs))
10 get = tf.keras.initializers.get
---> 11 self.W_ = self.add_variable("W_", shape=shape, initializer=get('glorot_uniform'))
12 self.M_ = self.add_variable("M_", shape=shape, initializer=get('glorot_uniform'))
13 self.GAM = self.add_variable("GAM", shape=shape, initializer=get('glorot_uniform')) # Gate add & multiply
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in add_variable(self, *args, **kwargs)
459 def add_variable(self, *args, **kwargs):
460 """Alias for `add_weight`."""
--> 461 return self.add_weight(*args, **kwargs)
462
463 def add_weight(self,
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in add_weight(self, name, shape, dtype, initializer, regularizer, trainable, constraint, partitioner, use_resource, synchronization, aggregation, getter)
563 use_resource=use_resource,
564 synchronization=synchronization,
--> 565 aggregation=aggregation)
566
567 if regularizer is not None:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/checkpointable/base.py in _add_variable_with_custom_getter(self, name, shape, dtype, initializer, getter, overwrite, **kwargs_for_getter)
533 new_variable = getter(
534 name=name, shape=shape, dtype=dtype, initializer=initializer,
--> 535 **kwargs_for_getter)
536
537 # If we set an initializer and the variable processed it, tracking will not
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in make_variable(name, shape, dtype, initializer, partition_info, trainable, caching_device, validate_shape, constraint, use_resource, synchronization, aggregation, partitioner)
1916 use_resource=use_resource,
1917 synchronization=synchronization,
-> 1918 aggregation=aggregation)
1919 return v
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variable_scope.py in variable(initial_value, trainable, collections, validate_shape, caching_device, name, dtype, constraint, use_resource, synchronization, aggregation)
2441 use_resource=use_resource,
2442 synchronization=synchronization,
-> 2443 aggregation=aggregation)
2444
2445
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variable_scope.py in <lambda>(**kwargs)
2423 synchronization=VariableSynchronization.AUTO,
2424 aggregation=VariableAggregation.NONE):
-> 2425 previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
2426 for getter in ops.get_default_graph()._variable_creator_stack: # pylint: disable=protected-access
2427 previous_getter = _make_getter(getter, previous_getter)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variable_scope.py in default_variable_creator(next_creator, **kwargs)
2393 collections=collections, validate_shape=validate_shape,
2394 caching_device=caching_device, name=name, dtype=dtype,
-> 2395 constraint=constraint)
2396 elif not use_resource and context.executing_eagerly():
2397 raise RuntimeError(
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py in __init__(self, initial_value, trainable, collections, validate_shape, caching_device, name, dtype, variable_def, import_scope, constraint)
310 name=name,
311 dtype=dtype,
--> 312 constraint=constraint)
313
314 # pylint: disable=unused-argument
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py in _init_from_args(self, initial_value, trainable, collections, validate_shape, caching_device, name, dtype, constraint)
415 with ops.name_scope("Initializer"), ops.device(None):
416 initial_value = ops.convert_to_tensor(
--> 417 initial_value(), name="initial_value", dtype=dtype)
418 self._handle = _eager_safe_variable_handle(
419 shape=initial_value.get_shape(),
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in <lambda>()
1901 initializer = initializer(dtype=dtype)
1902 init_val = lambda: initializer( # pylint: disable=g-long-lambda
-> 1903 shape, dtype=dtype, partition_info=partition_info)
1904 variable_dtype = dtype.base_dtype
1905 if use_resource is None:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py in __call__(self, shape, dtype, partition_info)
474 scale /= max(1., fan_out)
475 else:
--> 476 scale /= max(1., (fan_in + fan_out) / 2.)
477 if self.distribution == "normal" or self.distribution == "truncated_normal":
478 # constant taken from scipy.stats.truncnorm.std(a=-2, b=2, loc=0., scale=1.)
TypeError: unsupported operand type(s) for /: 'Dimension' and 'float'
Code:
https://gist.github.com/Carliceiv/0b68fe0d9f2a9fc9a1b901e8a722f6cd
The stacktrace indicates that somewhere in the code a Dimension value is given as n argument where you usually expect an integer/float.
I think that this might be caused by this line
shape = tf.TensorShape((input_shape[1], self.num_outputs))
please try to change it to
shape = (input_shape[1], self.num_outputs)
Edit: As pointed out in the comments, this is not working of input_shape is a Dimension object and not an int. To solve this, use this modification:
shape = tf.TensorShape((input_shape[1], self.num_outputs)).as_list()
This will at first create a new TensorShape which is able to deal with the Dimension data type and then convert this to a list of integers.