Develop Reference

Tensorflow: Shape must be at least rank 3 but is rank 2

I am training a bilstm model for text classification and running into the following error
ValueError: Shape must be at least rank 3 but is rank 2 for '{{node
bidirectional_5/forward_lstm_6/lstm_cell_17/BiasAdd}} =
BiasAdd[T=DT_HALF,
data_format="NCHW"](bidirectional_5/forward_lstm_6/lstm_cell_17/MatMul,
bidirectional_5/forward_lstm_6/lstm_cell_17/split_1)' with input
shapes: [?,200], [200].
This is the code I am using
output_dim = 200
dropout = 0.2
recurrent_dropout = 0.2
lstm_units = 128
n_tags = 26
num_dense_neurons = 20
classifier_activation = time_activation = 'tanh'
learning_rate = 0.003
merge_mode = 'concat'
activation = 'softmax'
max_length = 20
model = Sequential()
# Add Embedding layer
e = Embedding(input_dim= 340862, output_dim=output_dim,
weights=[weight_matrix],
input_length=max_length, trainable=False)
model.add(e)
# Add bidirectional LSTM
b = Bidirectional(LSTM(units=output_dim, return_sequences=True, dropout=dropout, recurrent_dropout=recurrent_dropout), merge_mode = merge_mode)
model.add(b)
# Add LSTM
model.add(LSTM(units=lstm_units, return_sequences=True, dropout=dropout, recurrent_dropout=recurrent_dropout))
# Add timeDistributed Layer
model.add(TimeDistributed(Dense(n_tags, activation=time_activation)))
model.add(Flatten())
model.add(Dense(num_dense_neurons, activation=classifier_activation))
model.add(Dense(n_tags,activation='softmax'))
#Optimiser
adam = Adam(learning_rate=learning_rate, beta_1=0.9, beta_2=0.999)
# Compile model
model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=[f1_score])
model.summary()
The weight_matrix I am passing to the embedding layer is of shape (340862, 200)
Both keras and tensorflow versions are 2.6.0. I am running this on AWS Sagemaker. Not sure why this is happening.
Full error
InvalidArgumentError Traceback (most recent call last)
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs, op_def)
1879 try:
-> 1880 c_op = pywrap_tf_session.TF_FinishOperation(op_desc)
1881 except errors.InvalidArgumentError as e:
InvalidArgumentError: Shape must be at least rank 3 but is rank 2 for '{{node bidirectional_6/forward_lstm_7/lstm_cell_20/BiasAdd}} = BiasAdd[T=DT_HALF, data_format="NCHW"](bidirectional_6/forward_lstm_7/lstm_cell_20/MatMul, bidirectional_6/forward_lstm_7/lstm_cell_20/split_1)' with input shapes: [?,200], [200].
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-88-ddcbc617161c> in <module>
20 # Add bidirectional LSTM
21 b = Bidirectional(LSTM(units=output_dim, return_sequences=True, dropout=dropout, recurrent_dropout=recurrent_dropout), merge_mode = merge_mode)
---> 22 model.add(b)
23 # Add LSTM
24 model.add(LSTM(units=lstm_units, return_sequences=True, dropout=dropout, recurrent_dropout=recurrent_dropout))
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
528 self._self_setattr_tracking = False # pylint: disable=protected-access
529 try:
--> 530 result = method(self, *args, **kwargs)
531 finally:
532 self._self_setattr_tracking = previous_value # pylint: disable=protected-access
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/engine/sequential.py in add(self, layer)
215 # If the model is being built continuously on top of an input layer:
216 # refresh its output.
--> 217 output_tensor = layer(self.outputs[0])
218 if len(tf.nest.flatten(output_tensor)) != 1:
219 raise ValueError(SINGLE_LAYER_OUTPUT_ERROR_MSG)
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/layers/wrappers.py in __call__(self, inputs, initial_state, constants, **kwargs)
581
582 if initial_state is None and constants is None:
--> 583 return super(Bidirectional, self).__call__(inputs, **kwargs)
584
585 # Applies the same workaround as in `RNN.__call__`
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
975 if _in_functional_construction_mode(self, inputs, args, kwargs, input_list):
976 return self._functional_construction_call(inputs, args, kwargs,
--> 977 input_list)
978
979 # Maintains info about the `Layer.call` stack.
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/engine/base_layer.py in _functional_construction_call(self, inputs, args, kwargs, input_list)
1113 # Check input assumptions set after layer building, e.g. input shape.
1114 outputs = self._keras_tensor_symbolic_call(
-> 1115 inputs, input_masks, args, kwargs)
1116
1117 if outputs is None:
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/engine/base_layer.py in _keras_tensor_symbolic_call(self, inputs, input_masks, args, kwargs)
846 return tf.nest.map_structure(keras_tensor.KerasTensor, output_signature)
847 else:
--> 848 return self._infer_output_signature(inputs, args, kwargs, input_masks)
849
850 def _infer_output_signature(self, inputs, args, kwargs, input_masks):
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/engine/base_layer.py in _infer_output_signature(self, inputs, args, kwargs, input_masks)
886 self._maybe_build(inputs)
887 inputs = self._maybe_cast_inputs(inputs)
--> 888 outputs = call_fn(inputs, *args, **kwargs)
889
890 self._handle_activity_regularization(inputs, outputs)
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/layers/wrappers.py in call(self, inputs, training, mask, initial_state, constants)
697
698 y = self.forward_layer(forward_inputs,
--> 699 initial_state=forward_state, **kwargs)
700 y_rev = self.backward_layer(backward_inputs,
701 initial_state=backward_state, **kwargs)
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/layers/recurrent.py in __call__(self, inputs, initial_state, constants, **kwargs)
657
658 if initial_state is None and constants is None:
--> 659 return super(RNN, self).__call__(inputs, **kwargs)
660
661 # If any of `initial_state` or `constants` are specified and are Keras
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
1035 with autocast_variable.enable_auto_cast_variables(
1036 self._compute_dtype_object):
-> 1037 outputs = call_fn(inputs, *args, **kwargs)
1038
1039 if self._activity_regularizer:
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/layers/recurrent_v2.py in call(self, inputs, mask, training, initial_state)
1165 input_length=row_lengths if row_lengths is not None else timesteps,
1166 time_major=self.time_major,
-> 1167 zero_output_for_mask=self.zero_output_for_mask)
1168 runtime = _runtime(_RUNTIME_UNKNOWN)
1169 else:
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
204 """Call target, and fall back on dispatchers if there is a TypeError."""
205 try:
--> 206 return target(*args, **kwargs)
207 except (TypeError, ValueError):
208 # Note: convert_to_eager_tensor currently raises a ValueError, not a
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/backend.py in rnn(step_function, inputs, initial_states, go_backwards, mask, constants, unroll, input_length, time_major, zero_output_for_mask)
4353 # the value is discarded.
4354 output_time_zero, _ = step_function(
-> 4355 input_time_zero, tuple(initial_states) + tuple(constants))
4356 output_ta = tuple(
4357 tf.TensorArray(
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/layers/recurrent_v2.py in step(inputs, states)
1153
1154 def step(inputs, states):
-> 1155 return self.cell(inputs, states, **kwargs)
1156
1157 last_output, outputs, states = backend.rnn(
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
1035 with autocast_variable.enable_auto_cast_variables(
1036 self._compute_dtype_object):
-> 1037 outputs = call_fn(inputs, *args, **kwargs)
1038
1039 if self._activity_regularizer:
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/layers/recurrent.py in call(self, inputs, states, training)
2440 b_i, b_f, b_c, b_o = tf.split(
2441 self.bias, num_or_size_splits=4, axis=0)
-> 2442 x_i = backend.bias_add(x_i, b_i)
2443 x_f = backend.bias_add(x_f, b_f)
2444 x_c = backend.bias_add(x_c, b_c)
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
204 """Call target, and fall back on dispatchers if there is a TypeError."""
205 try:
--> 206 return target(*args, **kwargs)
207 except (TypeError, ValueError):
208 # Note: convert_to_eager_tensor currently raises a ValueError, not a
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/keras/backend.py in bias_add(x, bias, data_format)
5973 if len(bias_shape) == 1:
5974 if data_format == 'channels_first':
-> 5975 return tf.nn.bias_add(x, bias, data_format='NCHW')
5976 return tf.nn.bias_add(x, bias, data_format='NHWC')
5977 if ndim(x) in (3, 4, 5):
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
204 """Call target, and fall back on dispatchers if there is a TypeError."""
205 try:
--> 206 return target(*args, **kwargs)
207 except (TypeError, ValueError):
208 # Note: convert_to_eager_tensor currently raises a ValueError, not a
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py in bias_add(value, bias, data_format, name)
3495 else:
3496 return gen_nn_ops.bias_add(
-> 3497 value, bias, data_format=data_format, name=name)
3498
3499
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/ops/gen_nn_ops.py in bias_add(value, bias, data_format, name)
689 data_format = _execute.make_str(data_format, "data_format")
690 _, _, _op, _outputs = _op_def_library._apply_op_helper(
--> 691 "BiasAdd", value=value, bias=bias, data_format=data_format, name=name)
692 _result = _outputs[:]
693 if _execute.must_record_gradient():
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(op_type_name, name, **keywords)
748 op = g._create_op_internal(op_type_name, inputs, dtypes=None,
749 name=scope, input_types=input_types,
--> 750 attrs=attr_protos, op_def=op_def)
751
752 # `outputs` is returned as a separate return value so that the output
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py in _create_op_internal(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_device)
599 return super(FuncGraph, self)._create_op_internal( # pylint: disable=protected-access
600 op_type, captured_inputs, dtypes, input_types, name, attrs, op_def,
--> 601 compute_device)
602
603 def capture(self, tensor, name=None, shape=None):
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in _create_op_internal(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_device)
3567 input_types=input_types,
3568 original_op=self._default_original_op,
-> 3569 op_def=op_def)
3570 self._create_op_helper(ret, compute_device=compute_device)
3571 return ret
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in __init__(self, node_def, g, inputs, output_types, control_inputs, input_types, original_op, op_def)
2040 op_def = self._graph._get_op_def(node_def.op)
2041 self._c_op = _create_c_op(self._graph, node_def, inputs,
-> 2042 control_input_ops, op_def)
2043 name = compat.as_str(node_def.name)
2044
~/anaconda3/envs/JupyterSystemEnv/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs, op_def)
1881 except errors.InvalidArgumentError as e:
1882 # Convert to ValueError for backwards compatibility.
-> 1883 raise ValueError(str(e))
1884
1885 return c_op
ValueError: Shape must be at least rank 3 but is rank 2 for '{{node bidirectional_6/forward_lstm_7/lstm_cell_20/BiasAdd}} = BiasAdd[T=DT_HALF, data_format="NCHW"](bidirectional_6/forward_lstm_7/lstm_cell_20/MatMul, bidirectional_6/forward_lstm_7/lstm_cell_20/split_1)' with input shapes: [?,200], [200].

Keras Error: Dimensions must be equal, but are 10 and 2 for 'loss/output_1_loss/SquaredDifference' with input shapes: [8,10], [8,2]

I'm working on a simple mlp model. The input shape for model fitting is here.
fea_train_np.shape = (6000, 1, 15, 21, 512)
fea_val_np.shape = (1500, 1, 15, 21, 512)
y_train_np.shape = (6000, 2)
y_val_np.shape = (1500, 2)
And here is the mlp I'm working on. The last layer using linear activation as I want to do regression instead of classification.
mlp1 = keras.Sequential(
[
layers.Flatten(),
layers.Dense(256, activation='relu'), # Add a fully-connecte layer with 16 units and relu activation function as the hidden layer
layers.Dense(10, activation='linear')
],
)
mlp1.compile(optimizer = optimizers.Adam(learning_rate = 0.001),
loss = keras.losses.MeanSquaredError(),
metrics = [keras.metrics.MeanSquaredError()])
mlp = mlp1.fit(fea_train_np, y_train_np, epochs=20, batch_size=8, validation_data=(fea_val_np, y_val_np))
result = mlp.predict(fea_val_np, y_val_np)
And I got this error when I was trying to fit my model:
Train on 6000 samples, validate on 1500 samples
Epoch 1/20
8/6000 [..............................] - ETA: 12s
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\ops.py in _create_c_op(graph, node_def, inputs, control_inputs)
1618 try:
-> 1619 c_op = c_api.TF_FinishOperation(op_desc)
1620 except errors.InvalidArgumentError as e:
InvalidArgumentError: Dimensions must be equal, but are 10 and 2 for 'loss/output_1_loss/SquaredDifference' (op: 'SquaredDifference') with input shapes: [8,10], [8,2].
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-32-37335a6a8cd3> in <module>
11 metrics = [keras.metrics.MeanSquaredError()])
12
---> 13 mlp = mlp1.fit(fea_train_np, y_train_np, epochs=20, batch_size=8, validation_data=(fea_val_np, y_val_np))
14 result = mlp.predict(fea_val_np, y_val_np)
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
817 max_queue_size=max_queue_size,
818 workers=workers,
--> 819 use_multiprocessing=use_multiprocessing)
820
821 def evaluate(self,
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
340 mode=ModeKeys.TRAIN,
341 training_context=training_context,
--> 342 total_epochs=epochs)
343 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
344
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in run_one_epoch(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)
126 step=step, mode=mode, size=current_batch_size) as batch_logs:
127 try:
--> 128 batch_outs = execution_function(iterator)
129 except (StopIteration, errors.OutOfRangeError):
130 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in execution_function(input_fn)
96 # `numpy` translates Tensors to values in Eager mode.
97 return nest.map_structure(_non_none_constant_value,
---> 98 distributed_function(input_fn))
99
100 return execution_function
C:\ForHDD\Anaconda\envs\CV\lib\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():
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\def_function.py in _call(self, *args, **kwds)
613 # This is the first call of __call__, so we have to initialize.
614 initializers = []
--> 615 self._initialize(args, kwds, add_initializers_to=initializers)
616 finally:
617 # At this point we know that the initialization is complete (or less
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
495 self._concrete_stateful_fn = (
496 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
--> 497 *args, **kwds))
498
499 def invalid_creator_scope(*unused_args, **unused_kwds):
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
2387 args, kwargs = None, None
2388 with self._lock:
-> 2389 graph_function, _, _ = self._maybe_define_function(args, kwargs)
2390 return graph_function
2391
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\function.py in _maybe_define_function(self, args, kwargs)
2701
2702 self._function_cache.missed.add(call_context_key)
-> 2703 graph_function = self._create_graph_function(args, kwargs)
2704 self._function_cache.primary[cache_key] = graph_function
2705 return graph_function, args, kwargs
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
2591 arg_names=arg_names,
2592 override_flat_arg_shapes=override_flat_arg_shapes,
-> 2593 capture_by_value=self._capture_by_value),
2594 self._function_attributes,
2595 # Tell the ConcreteFunction to clean up its graph once it goes out of
C:\ForHDD\Anaconda\envs\CV\lib\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,
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\eager\def_function.py in wrapped_fn(*args, **kwds)
437 # __wrapped__ allows AutoGraph to swap in a converted function. We give
438 # the function a weak reference to itself to avoid a reference cycle.
--> 439 return weak_wrapped_fn().__wrapped__(*args, **kwds)
440 weak_wrapped_fn = weakref.ref(wrapped_fn)
441
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in distributed_function(input_iterator)
83 args = _prepare_feed_values(model, input_iterator, mode, strategy)
84 outputs = strategy.experimental_run_v2(
---> 85 per_replica_function, args=args)
86 # Out of PerReplica outputs reduce or pick values to return.
87 all_outputs = dist_utils.unwrap_output_dict(
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in experimental_run_v2(self, fn, args, kwargs)
761 fn = autograph.tf_convert(fn, ag_ctx.control_status_ctx(),
762 convert_by_default=False)
--> 763 return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
764
765 def reduce(self, reduce_op, value, axis):
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in call_for_each_replica(self, fn, args, kwargs)
1817 kwargs = {}
1818 with self._container_strategy().scope():
-> 1819 return self._call_for_each_replica(fn, args, kwargs)
1820
1821 def _call_for_each_replica(self, fn, args, kwargs):
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in _call_for_each_replica(self, fn, args, kwargs)
2162 self._container_strategy(),
2163 replica_id_in_sync_group=constant_op.constant(0, dtypes.int32)):
-> 2164 return fn(*args, **kwargs)
2165
2166 def _reduce_to(self, reduce_op, value, destinations):
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\autograph\impl\api.py in wrapper(*args, **kwargs)
290 def wrapper(*args, **kwargs):
291 with ag_ctx.ControlStatusCtx(status=ag_ctx.Status.DISABLED):
--> 292 return func(*args, **kwargs)
293
294 if inspect.isfunction(func) or inspect.ismethod(func):
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in train_on_batch(model, x, y, sample_weight, class_weight, reset_metrics, standalone)
431 y,
432 sample_weights=sample_weights,
--> 433 output_loss_metrics=model._output_loss_metrics)
434
435 if reset_metrics:
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in train_on_batch(model, inputs, targets, sample_weights, output_loss_metrics)
310 sample_weights=sample_weights,
311 training=True,
--> 312 output_loss_metrics=output_loss_metrics))
313 if not isinstance(outs, list):
314 outs = [outs]
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in _process_single_batch(model, inputs, targets, output_loss_metrics, sample_weights, training)
251 output_loss_metrics=output_loss_metrics,
252 sample_weights=sample_weights,
--> 253 training=training))
254 if total_loss is None:
255 raise ValueError('The model cannot be run '
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in _model_loss(model, inputs, targets, output_loss_metrics, sample_weights, training)
165
166 if hasattr(loss_fn, 'reduction'):
--> 167 per_sample_losses = loss_fn.call(targets[i], outs[i])
168 weighted_losses = losses_utils.compute_weighted_loss(
169 per_sample_losses,
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\losses.py in call(self, y_true, y_pred)
219 y_pred, y_true = tf_losses_util.squeeze_or_expand_dimensions(
220 y_pred, y_true)
--> 221 return self.fn(y_true, y_pred, **self._fn_kwargs)
222
223 def get_config(self):
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\keras\losses.py in mean_squared_error(y_true, y_pred)
769 y_pred = ops.convert_to_tensor(y_pred)
770 y_true = math_ops.cast(y_true, y_pred.dtype)
--> 771 return K.mean(math_ops.squared_difference(y_pred, y_true), axis=-1)
772
773
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\ops\gen_math_ops.py in squared_difference(x, y, name)
10037 try:
10038 _, _, _op, _outputs = _op_def_library._apply_op_helper(
> 10039 "SquaredDifference", x=x, y=y, name=name)
10040 except (TypeError, ValueError):
10041 result = _dispatch.dispatch(
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\op_def_library.py in _apply_op_helper(op_type_name, name, **keywords)
740 op = g._create_op_internal(op_type_name, inputs, dtypes=None,
741 name=scope, input_types=input_types,
--> 742 attrs=attr_protos, op_def=op_def)
743
744 # `outputs` is returned as a separate return value so that the output
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\func_graph.py in _create_op_internal(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_device)
593 return super(FuncGraph, self)._create_op_internal( # pylint: disable=protected-access
594 op_type, inputs, dtypes, input_types, name, attrs, op_def,
--> 595 compute_device)
596
597 def capture(self, tensor, name=None, shape=None):
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\ops.py in _create_op_internal(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_device)
3320 input_types=input_types,
3321 original_op=self._default_original_op,
-> 3322 op_def=op_def)
3323 self._create_op_helper(ret, compute_device=compute_device)
3324 return ret
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\ops.py in __init__(self, node_def, g, inputs, output_types, control_inputs, input_types, original_op, op_def)
1784 op_def, inputs, node_def.attr)
1785 self._c_op = _create_c_op(self._graph, node_def, grouped_inputs,
-> 1786 control_input_ops)
1787 name = compat.as_str(node_def.name)
1788 # pylint: enable=protected-access
C:\ForHDD\Anaconda\envs\CV\lib\site-packages\tensorflow_core\python\framework\ops.py in _create_c_op(graph, node_def, inputs, control_inputs)
1620 except errors.InvalidArgumentError as e:
1621 # Convert to ValueError for backwards compatibility.
-> 1622 raise ValueError(str(e))
1623
1624 return c_op
ValueError: Dimensions must be equal, but are 10 and 2 for 'loss/output_1_loss/SquaredDifference' (op: 'SquaredDifference') with input shapes: [8,10], [8,2].
I tried to change loss = keras.losses.MeanSquaredError() to loss = [keras.losses.MeanSquaredError()] and the error keeps the same.
Can someone tell me what I did wrong here? Any suggestion will be appreciated.

I think the problem doesnt have to do with the loss function you use but with the dimensions of the data you use.
I see that y_val_np.shape has 2 dimensions (shape[1]), but in the model mlp1 the last layer returns output of 10 dimensions.
If this is helpful, and that is what u need to do, i believe changing the dims on the last layer of mlp1 to 2 instead of 10 will solve the problem

Tensorflow 2.0 training, use_multiprocessing=use_multiprocessing error

While I was training below convolution neural network with (96,96,3) images converted to numpy arrays and saved to .npy files, Below error has occurred.
I dont know where have I gone wrong. Help needed in resolving the error, might be in loss function not sure.
Architecture for Auto Encoder
model = models.Sequential()
model.add(layers.Conv2D(input_shape= (96,96,3), filters= 64, kernel_size= (3,3), strides= 2, padding= 'same', activation= tf.keras.layers.LeakyReLU(alpha= 0.3), name= 'conv_layer_1', dtype= tf.float32))
model.add(layers.Conv2D(filters= 128, kernel_size= (3,3), strides= 2, padding = 'same', activation= tf.keras.layers.LeakyReLU(alpha= 0.3), name= 'conv_layer_2', dtype= tf.float32))
model.add(layers.Conv2D(filters= 64, kernel_size= (3,3), strides= 2, padding = 'same', activation= tf.keras.layers.LeakyReLU(alpha= 0.3), name= 'deconv_layer_1', dtype= tf.float32))
model.add(layers.Conv2D(filters= 1, kernel_size= (3,3), strides= 2, padding = 'same', activation= tf.keras.layers.LeakyReLU(alpha= 0.3), name= 'deconv_layer_2', dtype= tf.float32))
model.compile(optimizer = tf.keras.optimizers.Adam(learning_rate = 0.01), loss = tf.keras.losses.mean_squared_error)
model.summary()
model.fit(np.array(x_train).reshape(10, 3, 96, 96), epochs=1, use_multiprocessing = True)
[multiprocessing= False same error]
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-53-77429e1864b4> in <module>
----> 1 model.fit(x_train, epochs=1, use_multiprocessing = False)
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
817 max_queue_size=max_queue_size,
818 workers=workers,
--> 819 use_multiprocessing=use_multiprocessing)
820
821 def evaluate(self,
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
340 mode=ModeKeys.TRAIN,
341 training_context=training_context,
--> 342 total_epochs=epochs)
343 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
344
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2.py in run_one_epoch(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)
126 step=step, mode=mode, size=current_batch_size) as batch_logs:
127 try:
--> 128 batch_outs = execution_function(iterator)
129 except (StopIteration, errors.OutOfRangeError):
130 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in execution_function(input_fn)
96 # `numpy` translates Tensors to values in Eager mode.
97 return nest.map_structure(_non_none_constant_value,
---> 98 distributed_function(input_fn))
99
100 return execution_function
/opt/conda/lib/python3.6/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():
/opt/conda/lib/python3.6/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"
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py in __call__(self, *args, **kwargs)
2360 """Calls a graph function specialized to the inputs."""
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
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py in _maybe_define_function(self, args, kwargs)
2701
2702 self._function_cache.missed.add(call_context_key)
-> 2703 graph_function = self._create_graph_function(args, kwargs)
2704 self._function_cache.primary[cache_key] = graph_function
2705 return graph_function, args, kwargs
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
2591 arg_names=arg_names,
2592 override_flat_arg_shapes=override_flat_arg_shapes,
-> 2593 capture_by_value=self._capture_by_value),
2594 self._function_attributes,
2595 # Tell the ConcreteFunction to clean up its graph once it goes out of
/opt/conda/lib/python3.6/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,
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/eager/def_function.py in wrapped_fn(*args, **kwds)
437 # __wrapped__ allows AutoGraph to swap in a converted function. We give
438 # the function a weak reference to itself to avoid a reference cycle.
--> 439 return weak_wrapped_fn().__wrapped__(*args, **kwds)
440 weak_wrapped_fn = weakref.ref(wrapped_fn)
441
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in distributed_function(input_iterator)
83 args = _prepare_feed_values(model, input_iterator, mode, strategy)
84 outputs = strategy.experimental_run_v2(
---> 85 per_replica_function, args=args)
86 # Out of PerReplica outputs reduce or pick values to return.
87 all_outputs = dist_utils.unwrap_output_dict(
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/distribute/distribute_lib.py in experimental_run_v2(self, fn, args, kwargs)
761 fn = autograph.tf_convert(fn, ag_ctx.control_status_ctx(),
762 convert_by_default=False)
--> 763 return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
764
765 def reduce(self, reduce_op, value, axis):
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/distribute/distribute_lib.py in call_for_each_replica(self, fn, args, kwargs)
1817 kwargs = {}
1818 with self._container_strategy().scope():
-> 1819 return self._call_for_each_replica(fn, args, kwargs)
1820
1821 def _call_for_each_replica(self, fn, args, kwargs):
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/distribute/distribute_lib.py in _call_for_each_replica(self, fn, args, kwargs)
2162 self._container_strategy(),
2163 replica_id_in_sync_group=constant_op.constant(0, dtypes.int32)):
-> 2164 return fn(*args, **kwargs)
2165
2166 def _reduce_to(self, reduce_op, value, destinations):
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/autograph/impl/api.py in wrapper(*args, **kwargs)
290 def wrapper(*args, **kwargs):
291 with ag_ctx.ControlStatusCtx(status=ag_ctx.Status.DISABLED):
--> 292 return func(*args, **kwargs)
293
294 if inspect.isfunction(func) or inspect.ismethod(func):
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in train_on_batch(model, x, y, sample_weight, class_weight, reset_metrics, standalone)
431 y,
432 sample_weights=sample_weights,
--> 433 output_loss_metrics=model._output_loss_metrics)
434
435 if reset_metrics:
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_eager.py in train_on_batch(model, inputs, targets, sample_weights, output_loss_metrics)
310 sample_weights=sample_weights,
311 training=True,
--> 312 output_loss_metrics=output_loss_metrics))
313 if not isinstance(outs, list):
314 outs = [outs]
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_eager.py in _process_single_batch(model, inputs, targets, output_loss_metrics, sample_weights, training)
251 output_loss_metrics=output_loss_metrics,
252 sample_weights=sample_weights,
--> 253 training=training))
254 if total_loss is None:
255 raise ValueError('The model cannot be run '
/opt/conda/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_eager.py in _model_loss(model, inputs, targets, output_loss_metrics, sample_weights, training)
165
166 if hasattr(loss_fn, 'reduction'):
--> 167 per_sample_losses = loss_fn.call(targets[i], outs[i])
168 weighted_losses = losses_utils.compute_weighted_loss(
169 per_sample_losses,
IndexError: list index out of range

When using the fit function in keras, you must pass the corresponding "labels" to the training images. In this case, being an auto-encoder, you would have to pass the images themselves as labels again.
model.fit(np.array(x_train).reshape(10, 3, 96, 96), np.array(x_train).reshape(10, 3, 96, 96), epochs=1, use_multiprocessing = True)
You can find more info about autoencoders in Keras here.

How to fix error: TypeError: unsupported operand type(s) for *: 'int' and 'NoneType in Keras

I'm trying to use shared Embedding layer for different input length, But I got errors as follows.
Code:
input1 = [Input(name = "input1", shape = (10,))]
input2 = [Input(name = "input2", shape = (10,))]
input3 = [Input(name = 'input3', shape = (1,))]
input4 = [Input(name = 'input4', shape = (1,))]
input5 = [Input(name = 'input5', shape = (1,))]
inputs= input1 + input2 + input3 + input4 + input5
embed = Embedding(name = 'embed', input_dim = 1000, output_dim = 20)
out1 = Flatten(name = 'output1')(embed(inputs[0]))
out2 = Flatten(name = 'output2')(embed(inputs[1]))
out3 = Flatten(name = 'output3')(embed(inputs[2]))
out4 = Flatten(name = 'output4')(embed(inputs[3]))
out5 = Flatten(name = 'output5')(embed(inputs[4]))
concat = Concatenate(name = 'concat')([out1, out2, out3, out4, out5])
result = Dense(name = 'result' + 'dense', units=1, activation='sigmoid')(concat)
model = Model(inputs = inputs, outputs = result)
#model.summary()
optimizer = Adam(learning_rate=0.01)
model.compile(loss='binary_crossentropy', optimizer=optimizer)
input1 = np.random.randint(0, 100, (100,10))
input2 = np.random.randint(0, 100, (100,10))
input3 = np.random.randint(0, 100, (100,1))
input4 = np.random.randint(0, 100, (100,1))
input5 = np.random.randint(0, 100, (100,1))
dummy_y = (input4 > 0).reshape(-1, 1)
model_input = [input1, input2, input3, input4, input5]
model.fit(x = model_input, y = dummy_y)
Error:
TypeError Traceback (most recent call last)
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\backprop.py in _num_elements(grad)
615 if isinstance(grad, ops.IndexedSlices):
--> 616 return functools.reduce(operator.mul, grad.values._shape_tuple(), 1) # pylint: disable=protected-access
617 raise ValueError("`grad` not a Tensor or IndexedSlices.")
TypeError: unsupported operand type(s) for *: 'int' and 'NoneType'
The above exception was the direct cause of the following exception:
SystemError Traceback (most recent call last)
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\backprop.py in _aggregate_grads(gradients)
597
--> 598 if len(gradients) == 1:
599 return gradients[0]
SystemError: returned a result with an error set
The above exception was the direct cause of the following exception:
SystemError Traceback (most recent call last)
in
27 dummy_y = (input4 > 0).reshape(-1, 1)
28 model_input = [input1, input2, input3, input4, input5]
---> 29 model.fit(x = model_input, y = dummy_y)
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
726 max_queue_size=max_queue_size,
727 workers=workers,
--> 728 use_multiprocessing=use_multiprocessing)
729
730 def evaluate(self,
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, **kwargs)
322 mode=ModeKeys.TRAIN,
323 training_context=training_context,
--> 324 total_epochs=epochs)
325 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
326
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in run_one_epoch(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)
121 step=step, mode=mode, size=current_batch_size) as batch_logs:
122 try:
--> 123 batch_outs = execution_function(iterator)
124 except (StopIteration, errors.OutOfRangeError):
125 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in execution_function(input_fn)
84 # `numpy` translates Tensors to values in Eager mode.
85 return nest.map_structure(_non_none_constant_value,
---> 86 distributed_function(input_fn))
87
88 return execution_function
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\def_function.py in __call__(self, *args, **kwds)
455
456 tracing_count = self._get_tracing_count()
--> 457 result = self._call(*args, **kwds)
458 if tracing_count == self._get_tracing_count():
459 self._call_counter.called_without_tracing()
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\def_function.py in _call(self, *args, **kwds)
501 # This is the first call of __call__, so we have to initialize.
502 initializer_map = object_identity.ObjectIdentityDictionary()
--> 503 self._initialize(args, kwds, add_initializers_to=initializer_map)
504 finally:
505 # At this point we know that the initialization is complete (or less
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
406 self._concrete_stateful_fn = (
407 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
--> 408 *args, **kwds))
409
410 def invalid_creator_scope(*unused_args, **unused_kwds):
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
1846 if self.input_signature:
1847 args, kwargs = None, None
-> 1848 graph_function, _, _ = self._maybe_define_function(args, kwargs)
1849 return graph_function
1850
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\function.py in _maybe_define_function(self, args, kwargs)
2148 graph_function = self._function_cache.primary.get(cache_key, None)
2149 if graph_function is None:
-> 2150 graph_function = self._create_graph_function(args, kwargs)
2151 self._function_cache.primary[cache_key] = graph_function
2152 return graph_function, args, kwargs
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
2039 arg_names=arg_names,
2040 override_flat_arg_shapes=override_flat_arg_shapes,
-> 2041 capture_by_value=self._capture_by_value),
2042 self._function_attributes,
2043 # Tell the ConcreteFunction to clean up its graph once it goes out of
~\AppData\Local\Programs\Python\Python37\lib\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)
913 converted_func)
914
--> 915 func_outputs = python_func(*func_args, **func_kwargs)
916
917 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\def_function.py in wrapped_fn(*args, **kwds)
356 # __wrapped__ allows AutoGraph to swap in a converted function. We give
357 # the function a weak reference to itself to avoid a reference cycle.
--> 358 return weak_wrapped_fn().__wrapped__(*args, **kwds)
359 weak_wrapped_fn = weakref.ref(wrapped_fn)
360
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in distributed_function(input_iterator)
71 strategy = distribution_strategy_context.get_strategy()
72 outputs = strategy.experimental_run_v2(
---> 73 per_replica_function, args=(model, x, y, sample_weights))
74 # Out of PerReplica outputs reduce or pick values to return.
75 all_outputs = dist_utils.unwrap_output_dict(
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in experimental_run_v2(self, fn, args, kwargs)
758 fn = autograph.tf_convert(fn, ag_ctx.control_status_ctx(),
759 convert_by_default=False)
--> 760 return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
761
762 def reduce(self, reduce_op, value, axis):
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in call_for_each_replica(self, fn, args, kwargs)
1785 kwargs = {}
1786 with self._container_strategy().scope():
-> 1787 return self._call_for_each_replica(fn, args, kwargs)
1788
1789 def _call_for_each_replica(self, fn, args, kwargs):
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in _call_for_each_replica(self, fn, args, kwargs)
2130 self._container_strategy(),
2131 replica_id_in_sync_group=constant_op.constant(0, dtypes.int32)):
-> 2132 return fn(*args, **kwargs)
2133
2134 def _reduce_to(self, reduce_op, value, destinations):
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\autograph\impl\api.py in wrapper(*args, **kwargs)
290 def wrapper(*args, **kwargs):
291 with ag_ctx.ControlStatusCtx(status=ag_ctx.Status.DISABLED):
--> 292 return func(*args, **kwargs)
293
294 if inspect.isfunction(func) or inspect.ismethod(func):
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in train_on_batch(model, x, y, sample_weight, class_weight, reset_metrics)
262 y,
263 sample_weights=sample_weights,
--> 264 output_loss_metrics=model._output_loss_metrics)
265
266 if reset_metrics:
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in train_on_batch(model, inputs, targets, sample_weights, output_loss_metrics)
309 sample_weights=sample_weights,
310 training=True,
--> 311 output_loss_metrics=output_loss_metrics))
312 if not isinstance(outs, list):
313 outs = [outs]
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in _process_single_batch(model, inputs, targets, output_loss_metrics, sample_weights, training)
266 model._backwards(tape, scaled_total_loss)
267 else:
--> 268 grads = tape.gradient(scaled_total_loss, trainable_weights)
269 if isinstance(model.optimizer,
270 loss_scale_optimizer.LossScaleOptimizer):
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\backprop.py in gradient(self, target, sources, output_gradients, unconnected_gradients)
1012 output_gradients=output_gradients,
1013 sources_raw=flat_sources_raw,
-> 1014 unconnected_gradients=unconnected_gradients)
1015
1016 if not self._persistent:
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\eager\imperative_grad.py in imperative_grad(tape, target, sources, output_gradients, sources_raw, unconnected_gradients)
74 output_gradients,
75 sources_raw,
---> 76 compat.as_str(unconnected_gradients.value))
SystemError: PyEval_EvalFrameEx returned a result with an error set
The error occured when I tried to fit the model, however I try with first four inputs, I can run without the error, any suggestion that would be appreciated.
I jsut adding some traceback errors, Thank you in advance.

Trying to use previously trained tf.keras model as pretraining, but getting "ValueError: Input 0 of layer dense_3 is incompatible with the laye

I created and trained a model to classify beer names from invoice strings encoded as integer sequences from characters.
batch_size = 512 # Batch size for training.
epochs = 5 # Number of epochs to train for.
model = Sequential()
model.add(Dense(512, activation='relu'))
model.add(Dropout(rate=0.2, noise_shape=None, seed=None))
model.add(Dense(512, activation='relu'))
model.add(Dropout(rate=0.2, noise_shape=None, seed=None))
model.add(Dense(train_beer['product_name'].nunique(), activation='softmax'))
optimizer = RMSprop(learning_rate=0.001)
model.compile(loss=tf.keras.losses.CategoricalCrossentropy(), optimizer=optimizer, metrics=['accuracy'])
model.fit(train_encoded, train_labels, epochs=epochs, batch_size=batch_size, validation_data=(test_encoded,test_labels))
Now I want to use the first two layers as pre-training for another model, so I remove the activation layer and add a new one and re-compile the model. (Note for testing purposes I re-added the same laye
model.pop()
model.add(Dense(train_beer['product_name'].nunique(), activation='softmax'))
optimizer = RMSprop(learning_rate=0.001)
model.compile(loss=tf.keras.losses.CategoricalCrossentropy(), optimizer=optimizer, metrics=['accuracy'])
batch_size = 512 # Batch size for training.
epochs = 5 # Number of epochs to train for.
model.fit(train_encoded, train_labels, epochs=epochs, batch_size=batch_size, validation_data=(test_encoded,test_labels))
but I get the error:
Train on 313213 samples, validate on 16323 samples Epoch 1/5 512/313213 [..............................] - ETA: 29s
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-13-e341e0cd9a82> in <module>
2 epochs = 5 # Number of epochs to train for.
3
----> 4 model.fit(train_encoded, train_labels, epochs=epochs, batch_size=batch_size, validation_data=(test_encoded,test_labels))
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing,
**kwargs)
726 max_queue_size=max_queue_size,
727 workers=workers,
--> 728 use_multiprocessing=use_multiprocessing)
729
730 def evaluate(self,
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, **kwargs)
322 mode=ModeKeys.TRAIN,
323 training_context=training_context,
--> 324 total_epochs=epochs)
325 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
326
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in run_one_epoch(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)
121 step=step, mode=mode, size=current_batch_size) as batch_logs:
122 try:
--> 123 batch_outs = execution_function(iterator)
124 except (StopIteration, errors.OutOfRangeError):
125 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in execution_function(input_fn)
84 # `numpy` translates Tensors to values in Eager mode.
85 return nest.map_structure(_non_none_constant_value,
---> 86 distributed_function(input_fn))
87
88 return execution_function
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\eager\def_function.py in __call__(self, *args, **kwds)
455
456 tracing_count = self._get_tracing_count()
--> 457 result = self._call(*args, **kwds)
458 if tracing_count == self._get_tracing_count():
459 self._call_counter.called_without_tracing()
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\eager\def_function.py in _call(self, *args, **kwds)
501 # This is the first call of __call__, so we have to initialize.
502 initializer_map = object_identity.ObjectIdentityDictionary()
--> 503 self._initialize(args, kwds, add_initializers_to=initializer_map)
504 finally:
505 # At this point we know that the initialization is complete (or less
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
406 self._concrete_stateful_fn = (
407 self._stateful_fn._get_concrete_function_internal_garbage_collected(
# pylint: disable=protected-access
--> 408 *args, **kwds))
409
410 def invalid_creator_scope(*unused_args, **unused_kwds):
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args,
**kwargs) 1846 if self.input_signature: 1847 args, kwargs = None, None
-> 1848 graph_function, _, _ = self._maybe_define_function(args, kwargs) 1849 return graph_function 1850
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\eager\function.py in _maybe_define_function(self, args, kwargs) 2148 graph_function = self._function_cache.primary.get(cache_key, None) 2149 if graph_function is None:
-> 2150 graph_function = self._create_graph_function(args, kwargs) 2151 self._function_cache.primary[cache_key] = graph_function 2152 return graph_function, args, kwargs
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes) 2039 arg_names=arg_names, 2040 override_flat_arg_shapes=override_flat_arg_shapes,
-> 2041 capture_by_value=self._capture_by_value), 2042 self._function_attributes, 2043 # Tell the ConcreteFunction to clean up its graph once it goes out of
~\.conda\envs\fintech_ml\lib\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)
913 converted_func)
914
--> 915 func_outputs = python_func(*func_args, **func_kwargs)
916
917 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\eager\def_function.py in wrapped_fn(*args, **kwds)
356 # __wrapped__ allows AutoGraph to swap in a converted function. We give
357 # the function a weak reference to itself to avoid a reference cycle.
--> 358 return weak_wrapped_fn().__wrapped__(*args, **kwds)
359 weak_wrapped_fn = weakref.ref(wrapped_fn)
360
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in distributed_function(input_iterator)
71 strategy = distribution_strategy_context.get_strategy()
72 outputs = strategy.experimental_run_v2(
---> 73 per_replica_function, args=(model, x, y, sample_weights))
74 # Out of PerReplica outputs reduce or pick values to return.
75 all_outputs = dist_utils.unwrap_output_dict(
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in experimental_run_v2(self, fn, args, kwargs)
758 fn = autograph.tf_convert(fn, ag_ctx.control_status_ctx(),
759 convert_by_default=False)
--> 760 return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
761
762 def reduce(self, reduce_op, value, axis):
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in call_for_each_replica(self, fn, args, kwargs) 1785 kwargs
= {} 1786 with self._container_strategy().scope():
-> 1787 return self._call_for_each_replica(fn, args, kwargs) 1788 1789 def _call_for_each_replica(self, fn, args, kwargs):
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in _call_for_each_replica(self, fn, args, kwargs) 2130 self._container_strategy(), 2131 replica_id_in_sync_group=constant_op.constant(0, dtypes.int32)):
-> 2132 return fn(*args, **kwargs) 2133 2134 def _reduce_to(self, reduce_op, value, destinations):
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\autograph\impl\api.py in wrapper(*args, **kwargs)
290 def wrapper(*args, **kwargs):
291 with ag_ctx.ControlStatusCtx(status=ag_ctx.Status.DISABLED):
--> 292 return func(*args, **kwargs)
293
294 if inspect.isfunction(func) or inspect.ismethod(func):
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in train_on_batch(model, x, y, sample_weight, class_weight, reset_metrics)
262 y,
263 sample_weights=sample_weights,
--> 264 output_loss_metrics=model._output_loss_metrics)
265
266 if reset_metrics:
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in train_on_batch(model, inputs, targets, sample_weights, output_loss_metrics)
309 sample_weights=sample_weights,
310 training=True,
--> 311 output_loss_metrics=output_loss_metrics))
312 if not isinstance(outs, list):
313 outs = [outs]
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in _process_single_batch(model, inputs, targets, output_loss_metrics, sample_weights, training)
250 output_loss_metrics=output_loss_metrics,
251 sample_weights=sample_weights,
--> 252 training=training))
253 if total_loss is None:
254 raise ValueError('The model cannot be run '
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\training_eager.py in _model_loss(model, inputs, targets, output_loss_metrics, sample_weights, training)
125 inputs = nest.map_structure(ops.convert_to_tensor, inputs)
126
--> 127 outs = model(inputs, **kwargs)
128 outs = nest.flatten(outs)
129
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\base_layer.py in __call__(self, inputs, *args, **kwargs)
845 outputs = base_layer_utils.mark_as_return(outputs, acd)
846 else:
--> 847 outputs = call_fn(cast_inputs, *args, **kwargs)
848
849 except errors.OperatorNotAllowedInGraphError as e:
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\sequential.py in call(self, inputs, training, mask)
268 kwargs['training'] = training
269
--> 270 outputs = layer(inputs, **kwargs)
271
272 # `outputs` will be the inputs to the next layer.
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\base_layer.py in __call__(self, inputs, *args, **kwargs)
810 # are casted, not before.
811 input_spec.assert_input_compatibility(self.input_spec, inputs,
--> 812 self.name)
813 graph = backend.get_graph()
814 with graph.as_default(), backend.name_scope(self._name_scope()):
~\.conda\envs\fintech_ml\lib\site-packages\tensorflow_core\python\keras\engine\input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
211 ' incompatible with the layer: expected axis ' + str(axis) +
212 ' of input shape to have value ' + str(value) +
--> 213 ' but received input with shape ' + str(shape))
214 # Check shape.
215 if spec.shape is not None:
ValueError: Input 0 of layer dense_3 is incompatible with the layer: expected axis -1 of input shape to have value 6022 but received input with shape [None, 512]

I can't really tell you why that is happening (I'll probably have to look into the source code). I'm suspecting that the layers get re-wired incorrectly somewhere down the line. But you can do the following to get this working.
new_model = Sequential()
for l in model.layers[:-1]:
new_model.add(l)
new_model.add(Dense(100, activation='softmax'))