Develop Reference

Multiple input neural network training crashes

I'm currently working on a neural network which is supposed to adjust a camera pose based on a given pose and an image.
I can't get the network to train and my question is - what am I doing wrong ?
Data gets loaded by a custom dataloader function. The network and training setup script:
import dataloader
from tensorflow.keras import optimizers, Model, Input
from tensorflow.keras.callbacks import TensorBoard, ModelCheckpoint
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.layers import Dense, concatenate
tensorboard_callback = TensorBoard(
log_dir="./tensorboard_logs",
histogram_freq=1,
write_graph=True,
write_images=False,
update_freq="epoch",
)
cp_callback = ModelCheckpoint(filepath="./model",
monitor="loss",
save_best_only=True,
save_weights_only=False,
verbose=1)
first_input = Input(shape=(25088,))
first_dense = Dense(6000, activation="relu")
x = first_dense(first_input)
x = Dense(1500, activation="relu")(x)
x = Dense(375, activation="relu")(x)
second_input = Input(shape=(6,))
merged = concatenate([x, second_input])
output = Dense(6, activation="sigmoid")(merged)
model = Model(inputs=[first_input, second_input], outputs=output, name="network_name")
# define optimizer
opt = optimizers.Adam(
learning_rate=0.001,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-07,
amsgrad=False,
name="Adam"
)
# Compile the model with optimizers and loss functions
model.compile(optimizer=opt, loss="MeanSquaredError", metrics=["MeanSquaredError"])
model.summary()
train_gen = dataloader.Dataloader().dataloader(batch_size=5, training=True)
val_gen = dataloader.Dataloader().dataloader(batch_size=5, training=True)
# Train model
model.fit(
x=train_gen,
validation_data=next(val_gen),
# validation_data=tuple(train_gen),
validation_steps=1,
steps_per_epoch=7,
initial_epoch=1,
epochs=1000,
shuffle=False,
callbacks=[tensorboard_callback, cp_callback]
)
model.save("./model/new_model.h5")
This results in following architecture:
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 25088)] 0
__________________________________________________________________________________________________
dense (Dense) (None, 6000) 150534000 input_1[0][0]
__________________________________________________________________________________________________
dense_1 (Dense) (None, 1500) 9001500 dense[0][0]
__________________________________________________________________________________________________
dense_2 (Dense) (None, 375) 562875 dense_1[0][0]
__________________________________________________________________________________________________
input_2 (InputLayer) [(None, 6)] 0
__________________________________________________________________________________________________
concatenate (Concatenate) (None, 381) 0 dense_2[0][0]
input_2[0][0]
__________________________________________________________________________________________________
dense_3 (Dense) (None, 6) 2292 concatenate[0][0]
==================================================================================================
Total params: 160,100,667
Trainable params: 160,100,667
Non-trainable params: 0
__________________________________________________________________________________________________
The first input is the mentioned image. the second input is the to be adjusted pose.
My issue is that there seems to be an error in how I hand over the data from my dataloader to the fit() function. I receive following error:
2022-02-03 13:17:42.111511: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)
Epoch 2/1000
Traceback (most recent call last):
File "C:\path\network.py", line 73, in <module>
model.fit(
File "C:\Python39\lib\site-packages\keras\engine\training.py", line 1184, in fit
tmp_logs = self.train_function(iterator)
File "C:\Python39\lib\site-packages\tensorflow\python\eager\def_function.py", line 885, in __call__
result = self._call(*args, **kwds)
File "C:\Python39\lib\site-packages\tensorflow\python\eager\def_function.py", line 933, in _call
self._initialize(args, kwds, add_initializers_to=initializers)
File "C:\Python39\lib\site-packages\tensorflow\python\eager\def_function.py", line 759, in _initialize
self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
File "C:\Python39\lib\site-packages\tensorflow\python\eager\function.py", line 3066, in _get_concrete_function_internal_garbage_collected
graph_function, _ = self._maybe_define_function(args, kwargs)
File "C:\Python39\lib\site-packages\tensorflow\python\eager\function.py", line 3463, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File "C:\Python39\lib\site-packages\tensorflow\python\eager\function.py", line 3298, in _create_graph_function
func_graph_module.func_graph_from_py_func(
File "C:\Python39\lib\site-packages\tensorflow\python\framework\func_graph.py", line 1007, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "C:\Python39\lib\site-packages\tensorflow\python\eager\def_function.py", line 668, in wrapped_fn
out = weak_wrapped_fn().__wrapped__(*args, **kwds)
File "C:\Python39\lib\site-packages\tensorflow\python\framework\func_graph.py", line 994, in wrapper
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
C:\Python39\lib\site-packages\keras\engine\training.py:853 train_function *
return step_function(self, iterator)
C:\Python39\lib\site-packages\keras\engine\training.py:842 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Python39\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1286 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Python39\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2849 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Python39\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3632 _call_for_each_replica
return fn(*args, **kwargs)
C:\Python39\lib\site-packages\keras\engine\training.py:835 run_step **
outputs = model.train_step(data)
C:\Python39\lib\site-packages\keras\engine\training.py:787 train_step
y_pred = self(x, training=True)
C:\Python39\lib\site-packages\keras\engine\base_layer.py:1020 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
C:\Python39\lib\site-packages\keras\engine\input_spec.py:199 assert_input_compatibility
raise ValueError('Layer ' + layer_name + ' expects ' +
ValueError: Layer network_name expects 2 input(s), but it received 10 input tensors. Inputs received: [<tf.Tensor 'ExpandDims:0' shape=(None,
1) dtype=float32>, <tf.Tensor 'ExpandDims_1:0' shape=(None, 1) dtype=float32>, <tf.Tensor 'ExpandDims_2:0' shape=(None, 1) dtype=float32>, <tf.Tensor 'ExpandDims_3:0' shape=(None, 1) dtype=float32>, <tf.Tensor 'ExpandDims_4:0' shape=(None, 1) dtype=float32>, <tf.Tensor 'ExpandDims_5:0' shape=(None, 1) dtype=float32>, <tf.Tensor 'ExpandDims_6:0' shape=(None, 1) dtype=float32>, <tf.Tensor 'ExpandDims_7:0' shape=(None, 1) dtype=float32>, <tf.Tensor 'ExpandDims_8:0' shape=(None, 1) dtype=float32>, <tf.Tensor 'ExpandDims_9:0' shape=(None, 1) dtype=float32>]
I found an article (sadly can't find it anymore and didn't save the link) which said that the problem could be solved by applying the tuple() function to val_generator in the fit() function, but that resulted in my script just doing nothing after compiling the network
Please also let me know if there are general problems with the network architecture or how to improve. Since this is my first real neural network project I'm not really certain about anything I'm doing to be honest.
If there is any additional info, one might need- please let me know.
Thanks in advance

Keras ValueError: Dimensions must be equal, but are 2 and 32 for '{{node Equal}} with input shapes: [?,2], [?,32,32]

I was trying to train a simple Keras network for classification when I faced the following error. I know there is something wrong with my inputs but I couldn't figure out how to fix it. Here is my code
my data set shape :
x_train : float32 0.0 1.0 (2444, 64, 64, 1)
y_train : float32 0.0 1.0 (2444, 2)
x_test : float32 0.0 1.0 (9123, 64, 64, 1)
y_test : float32 0.0 1.0 (9123, 2)
the model :
inputs = keras.Input(shape=(64,64,1), dtype='float32')
x = keras.layers.Conv2D(12,(9,9), padding="same",input_shape=(64,64,1), dtype='float32',activation='relu')(inputs)
x = keras.layers.Conv2D(18,(7,7), padding="same", activation='relu')(x)
x = keras.layers.MaxPool2D(pool_size=(2,2))(x)
x = keras.layers.Dropout(0.25)(x)
x = keras.layers.Dense(50, activation='relu')(x)
x = keras.layers.Dropout(0.4)(x)
outputs = keras.layers.Dense(2, activation='softmax')(x)
model = keras.Model(inputs, outputs)
model summary :
Model: "model_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_2 (InputLayer) [(None, 64, 64, 1)] 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 64, 64, 12) 984
_________________________________________________________________
conv2d_3 (Conv2D) (None, 64, 64, 18) 10602
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 32, 32, 18) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 32, 32, 18) 0
_________________________________________________________________
dense_2 (Dense) (None, 32, 32, 50) 950
_________________________________________________________________
dropout_3 (Dropout) (None, 32, 32, 50) 0
_________________________________________________________________
dense_3 (Dense) (None, 32, 32, 2) 102
=================================================================
Total params: 12,638
Trainable params: 12,638
Non-trainable params: 0
________________________
compiler and fitter which error occurs when I wanna fit the model
model.compile(
loss=keras.losses.SparseCategoricalCrossentropy(),
optimizer=keras.optimizers.Adam(0.01),
metrics=["acc"],
)
model.fit(x_train, y_train, batch_size=32, epochs = 20, validation_split= 0.3,
callbacks=[tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=3)])
and finally the error:
ValueError Traceback (most recent call last)
<ipython-input-31-e4cade46a08c> in <module>()
1 model.fit(x_train, y_train, batch_size=32, epochs = 20, validation_split= 0.3,
----> 2 callbacks=[tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=3)])
9 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
992 except Exception as e: # pylint:disable=broad-except
993 if hasattr(e, "ag_error_metadata"):
--> 994 raise e.ag_error_metadata.to_exception(e)
995 else:
996 raise
ValueError: in user code:
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:853 train_function *
return step_function(self, iterator)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:842 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1286 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2849 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3632 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:835 run_step **
outputs = model.train_step(data)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:792 train_step
self.compiled_metrics.update_state(y, y_pred, sample_weight)
/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py:457 update_state
metric_obj.update_state(y_t, y_p, sample_weight=mask)
/usr/local/lib/python3.7/dist-packages/keras/utils/metrics_utils.py:73 decorated
update_op = update_state_fn(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/keras/metrics.py:177 update_state_fn
return ag_update_state(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/keras/metrics.py:681 update_state **
matches = ag_fn(y_true, y_pred, **self._fn_kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:206 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/keras/metrics.py:3537 sparse_categorical_accuracy
return tf.cast(tf.equal(y_true, y_pred), backend.floatx())
/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:206 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/math_ops.py:1864 equal
return gen_math_ops.equal(x, y, name=name)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/gen_math_ops.py:3219 equal
name=name)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/op_def_library.py:750 _apply_op_helper
attrs=attr_protos, op_def=op_def)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py:601 _create_op_internal
compute_device)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py:3569 _create_op_internal
op_def=op_def)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py:2042 __init__
control_input_ops, op_def)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py:1883 _create_c_op
raise ValueError(str(e))
ValueError: Dimensions must be equal, but are 2 and 32 for '{{node Equal}} = Equal[T=DT_FLOAT, incompatible_shape_error=true](IteratorGetNext:1, Cast_1)' with input shapes: [?,2], [?,32,32].

As you can see in the model summary, the output shape of the model is (None,32,32,2), while based on target values it should be (None,2), Try to add Flatten layer before Dense layers:
x = keras.layers.Dropout(0.25)(x)
x = keras.layers.Flatten()(x) # Add this
x = keras.layers.Dense(50, activation='relu')(x)

TensorFlow - ValueError: Shapes (None, 1) and (None, 10) are incompatible

I am trying to implement an image classifier using "The Street View House Numbers (SVHN) Dataset" from this link. I am using format 2 which contains 32x32 RGB centered digit images from 0 to 9. When I try to compile and fit the model I get the following error:
Epoch 1/10
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-37-31870b6986af> in <module>()
3
4 model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
----> 5 model.fit(trainX, trainY, validation_data=(validX, validY), batch_size=128, epochs=10)
9 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
975 except Exception as e: # pylint:disable=broad-except
976 if hasattr(e, "ag_error_metadata"):
--> 977 raise e.ag_error_metadata.to_exception(e)
978 else:
979 raise
ValueError: in user code:
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function *
return step_function(self, iterator)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:795 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:788 run_step **
outputs = model.train_step(data)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:756 train_step
y, y_pred, sample_weight, regularization_losses=self.losses)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/compile_utils.py:203 __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:152 __call__
losses = call_fn(y_true, y_pred)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:256 call **
return ag_fn(y_true, y_pred, **self._fn_kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/losses.py:1537 categorical_crossentropy
return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/backend.py:4833 categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/tensor_shape.py:1134 assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (None, 1) and (None, 10) are incompatible
The code is:
model = Sequential([
Conv2D(filters=64, kernel_size=3, strides=2, activation='relu', input_shape=(32,32,3)),
MaxPooling2D(pool_size=(2, 2), strides=1, padding='same'),
Conv2D(filters=32, kernel_size=3, strides=1, activation='relu'),
MaxPooling2D(pool_size=(2, 2), strides=1, padding='same'),
Flatten(),
Dense(10, activation='softmax')
])
model.summary()
Model: "sequential_10"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_23 (Conv2D) (None, 15, 15, 64) 1792
_________________________________________________________________
max_pooling2d_23 (MaxPooling (None, 15, 15, 64) 0
_________________________________________________________________
conv2d_24 (Conv2D) (None, 13, 13, 32) 18464
_________________________________________________________________
max_pooling2d_24 (MaxPooling (None, 13, 13, 32) 0
_________________________________________________________________
flatten_10 (Flatten) (None, 5408) 0
_________________________________________________________________
dense_13 (Dense) (None, 10) 54090
=================================================================
Total params: 74,346
Trainable params: 74,346
Non-trainable params: 0
_________________________________________________________________
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(trainX, trainY, validation_data=(validX, validY), batch_size=128, epochs=10)
I was unable to solve the error, does anyone have any ideas on how to fix it?

As i could not see your coding for trainY; seems like - your trainY has only one column and your model output have 10 neurons, so Shapes (None, 1) and (None, 10) are incompatible. you can try this on your trainY(i.e one-hot encoding)
from sklearn.preprocessing import LabelBinarizer
label_as_binary = LabelBinarizer()
train__y_labels = label_as_binary.fit_transform(trainY)
and compile will look like as (look for train__y_labels)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(train_X_input, train__y_labels, batch_size=128, epochs=1)
note: if your valid also throws the error, same would be needed on all y(s).

Change the compile statement so that
loss = 'sparse_categorical_cross_entropy'
The "sparse" indicates that the y values are numeric rather than one-hot

error when using Mirrored strategy in Tensorflow

I read the data and processed it using the following code :
data = pd.read_csv('Step1_output.csv')
data = data.sample(frac=1).reset_index(drop=True)
data1 = pd.DataFrame(data, columns=['Res_pair'])
# creating instance of labelencoder
labelencoder = LabelEncoder()
# Assigning numerical values and storing in another column
data1['Res_pair_ID'] = labelencoder.fit_transform(data1['Res_pair'])
data['Res_pair'] = data1['Res_pair_ID']
data = data.to_numpy()
train_X = data[0:data.shape[0],0:566]
train_y = data[0:data.shape[0],566:data.shape[1]]
train_X = train_X.reshape((train_X.shape[0], train_X.shape[1], 1))
I build the model using following code where I have tried to distribute the dataset using mirrored strategy of Tensorflow :
print("Hyper-parameter values:\n")
print('Momentum Rate =',momentum_rate,'\n')
print('learning rate =',learning_rate,'\n')
print('Number of neurons =',neurons,'\n')
strategy = tensorflow.distribute.MirroredStrategy()
with strategy.scope():
model = tf.keras.Sequential([
tf.keras.layers.Conv1D(64,kernel_size = 3,activation='relu',input_shape=train_X.shape[1:]),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(neurons,activation='relu'),
tf.keras.layers.Dense(neurons,activation='relu'),
tf.keras.layers.Dense(neurons,activation='relu'),
tf.keras.layers.Dense(neurons,activation='relu'),
tf.keras.layers.Dense(10, activation='softmax'),])
sgd = optimizers.SGD(lr=learning_rate, decay=1e-6, momentum=momentum_rate, nesterov=True)
model.compile(loss='categorical_crossentropy',optimizer=sgd,metrics=['accuracy',tensorflow.keras.metrics.Precision()])
results = model.fit(train_X,train_y,validation_split = 0.2,epochs=10,batch_size = 100)
print(results)
path = 'saved_model/'
model.save(path, save_format='tf')
for k in range(100):
momentum_rate = random.random()
learning_rate = random.uniform(0,0.2)
neurons = random.randint(10,50)
I tried to run the code on GPU but it runs for some time and then throws this error :
Hyper-parameter values:
Momentum Rate = 0.6477407029392913
learning rate = 0.03988890117492503
Number of neurons = 35
Epoch 1/10
1/270110 [..............................] - ETA: 28s - loss: nan - accuracy: 0.0100 - precision: 0.0100Traceback (most recent call last):
File "parallelised_script_realdata2.py", line 56, in <module>
results = model.fit(train_X,train_y,validation_split = 0.2,epochs=10,batch_size = 100)
File "/usr/local/lib64/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 108, in _method_wrapper
return method(self, *args, **kwargs)
File "/usr/local/lib64/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1098, in fit
tmp_logs = train_function(iterator)
File "/usr/local/lib64/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 780, in __call__
result = self._call(*args, **kwds)
File "/usr/local/lib64/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 807, in _call
return self._stateless_fn(*args, **kwds) # pylint: disable=not-callable
File "/usr/local/lib64/python3.6/site-packages/tensorflow/python/eager/function.py", line 2829, in __call__
return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
File "/usr/local/lib64/python3.6/site-packages/tensorflow/python/eager/function.py", line 1848, in _filtered_call
cancellation_manager=cancellation_manager)
File "/usr/local/lib64/python3.6/site-packages/tensorflow/python/eager/function.py", line 1924, in _call_flat
ctx, args, cancellation_manager=cancellation_manager))
File "/usr/local/lib64/python3.6/site-packages/tensorflow/python/eager/function.py", line 550, in call
ctx=ctx)
File "/usr/local/lib64/python3.6/site-packages/tensorflow/python/eager/execute.py", line 60, in quick_execute
inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InvalidArgumentError: assertion failed: [predictions must be >= 0] [Condition x >= y did not hold element-wise:] [x (sequential/dense_4/Softmax:0) = ] [[nan nan nan...]...] [y (Cast_6/x:0) = ] [0]
[[{{node assert_greater_equal/Assert/AssertGuard/else/_21/assert_greater_equal/Assert/AssertGuard/Assert}}]] [Op:__inference_train_function_1270]
Function call stack:
train_function
Update: The code works well if I don't use strategy = tensorflow.distribute.MirroredStrategy(). Like the code below (but will fail for larger datasets for memory shortage):
def convolutional_neural_network(x, y):
print("Hyper-parameter values:\n")
print('Momentum Rate =',momentum_rate,'\n')
print('learning rate =',learning_rate,'\n')
print('Number of neurons =',neurons,'\n')
model = Sequential()
model.add(Conv1D(filters=64,input_shape=train_X.shape[1:],activation='relu',kernel_size = 3))
model.add(Flatten())
model.add(Dense(neurons,activation='relu')) # first hidden layer
model.add(Dense(neurons, activation='relu')) # second hidden layer
model.add(Dense(neurons, activation='relu'))
model.add(Dense(neurons, activation='relu'))
model.add(Dense(10, activation='softmax'))
sgd = optimizers.SGD(lr=learning_rate, decay=1e-6, momentum=momentum_rate, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy',tensorflow.keras.metrics.Precision()])
history = model.fit(train_X, train_y, validation_split=0.2, epochs=10, batch_size=100)
momentum_rate = 0.09
learning_rate = 0.01
neurons = 40
print(convolutional_neural_network(train_X, train_y))
Update 2: Still facing a similar issue with smaller dataset
_________________________________________________________________
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1d (Conv1D) (None, 564, 64) 256
_________________________________________________________________
flatten (Flatten) (None, 36096) 0
_________________________________________________________________
dense (Dense) (None, 50) 1804850
_________________________________________________________________
dense_1 (Dense) (None, 50) 2550
_________________________________________________________________
dense_2 (Dense) (None, 50) 2550
_________________________________________________________________
dense_3 (Dense) (None, 50) 2550
_________________________________________________________________
dense_4 (Dense) (None, 10) 510
=================================================================
Total params: 1,813,266
Trainable params: 1,813,266
Non-trainable params: 0

The model definition seems fine, so does the strategy.
Can you just verify train_Y for sanity check? Mostly I'm sure the error lies there.
If that's not the case, try running model.fit and latter ones outside the scope.

Why is the sequential layer expecting 3 dimensions in Keras?

Upon trying to train my LSTM network, I am given the error: ValueError: Input 0 of layer sequential_2 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, None].
My code is as follows:
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
numFeatures = 26; #amino acids
numClasses = 64; #codons
x_test = tf.ragged.constant(XTest)
y_train = tf.ragged.constant(YTrain)
y_test = tf.ragged.constant(YTest)
x_train = tf.ragged.constant(XTrain)
model = keras.Sequential(
[
keras.Input(shape=(26, 10), ragged=True),
layers.LSTM(128,use_bias=False),
layers.Dense(10, activation="softmax")
]
)
model.compile(
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer="adam",
metrics=["accuracy"]
)
model.fit(
x_train, y_train, validation_data=(x_test, y_test), batch_size=5, epochs=1
)
model.summary() shows me this:
Model: "sequential_2"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_2 (LSTM) (None, 128) 70656
_________________________________________________________________
dense_2 (Dense) (None, 10) 1290
=================================================================
Total params: 71,946
Trainable params: 71,946
Non-trainable params: 0
_________________________________________________________________
I get the following error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-11-ae3b9eb7daa0> in <module>()
15 )
16 model.fit(
---> 17 x_train, y_train, validation_data=(x_test, y_test), batch_size=5, epochs=1
18 )
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
966 except Exception as e: # pylint:disable=broad-except
967 if hasattr(e, "ag_error_metadata"):
--> 968 raise e.ag_error_metadata.to_exception(e)
969 else:
970 raise
ValueError: in user code:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:571 train_function *
outputs = self.distribute_strategy.run(
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:951 run **
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:531 train_step **
y_pred = self(x, training=True)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py:886 __call__
self.name)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/input_spec.py:180 assert_input_compatibility
str(x.shape.as_list()))
ValueError: Input 0 of layer sequential_2 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, None]