Develop Reference

Getting error when training the CNN model(tensorflow)

I am getting errors when training my CNN model which is for checking what a person is telling in sign language. I am working with keras, tensorflow.
This is my code:
import tensorflow as tf ;importing libraries
from tensorflow.keras import datasets,layers,models
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.keras.preprocessing.image import ImageDataGenerator
; Data preprocessing
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True)
training_set = train_datagen.flow_from_directory('split__data/Train',
target_size = (64, 64),
batch_size = 32,
class_mode = 'categorical')
test_datagen = ImageDataGenerator(rescale = 1./255)
test_set = test_datagen.flow_from_directory('split__data/Test',
target_size = (64, 64),
batch_size = 32,
class_mode = 'categorical')
; Building the model
cnn = tf.keras.models.Sequential()
cnn.add(tf.keras.layers.Conv2D(filters = 16,kernel_size = 3,activation = 'relu',input_shape = [64,64,3]))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2,strides=2))
cnn.add(tf.keras.layers.Conv2D(filters = 32,kernel_size = 3,activation = 'relu',input_shape = [64,64,3]))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2,strides=2))
cnn.add(tf.keras.layers.Conv2D(filters = 64,kernel_size = 3,activation = 'relu',input_shape = [64,64,3]))
cnn.add(tf.keras.layers.MaxPool2D(pool_size=2,strides=2))
cnn.add(tf.keras.layers.Flatten())
cnn.add(tf.keras.layers.Dense(units=500,activation='relu'))
cnn.add(tf.keras.layers.Dense(units=1,activation='softmax'))
; compiling and training
cnn.compile(optimizer = 'adam' , loss= 'categorical_crossentropy',metrics = ['accuracy'])
;the next line is giving me error
cnn.fit(x = training_set,validation_data = test_set,batch_size = 32,epochs = 10)
This is the error. I am not able to get from where these errors are being generated. I have tried changing batch size, image height and width but nothing happens. I am getting same error.
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-15-b67ba9813850> in <module>
----> 1 cnn.fit(x = training_set,validation_data = test_set,batch_size = 32,epochs = 10)
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\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_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
1181 _r=1):
1182 callbacks.on_train_batch_begin(step)
-> 1183 tmp_logs = self.train_function(iterator)
1184 if data_handler.should_sync:
1185 context.async_wait()
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
887
888 with OptionalXlaContext(self._jit_compile):
--> 889 result = self._call(*args, **kwds)
890
891 new_tracing_count = self.experimental_get_tracing_count()
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
948 # Lifting succeeded, so variables are initialized and we can run the
949 # stateless function.
--> 950 return self._stateless_fn(*args, **kwds)
951 else:
952 _, _, _, filtered_flat_args = \
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
3021 (graph_function,
3022 filtered_flat_args) = self._maybe_define_function(args, kwargs)
-> 3023 return graph_function._call_flat(
3024 filtered_flat_args, captured_inputs=graph_function.captured_inputs) # pylint: disable=protected-access
3025
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1958 and executing_eagerly):
1959 # No tape is watching; skip to running the function.
-> 1960 return self._build_call_outputs(self._inference_function.call(
1961 ctx, args, cancellation_manager=cancellation_manager))
1962 forward_backward = self._select_forward_and_backward_functions(
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py in call(self, ctx, args, cancellation_manager)
589 with _InterpolateFunctionError(self):
590 if cancellation_manager is None:
--> 591 outputs = execute.execute(
592 str(self.signature.name),
593 num_outputs=self._num_outputs,
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\eager\execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
57 try:
58 ctx.ensure_initialized()
---> 59 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
60 inputs, attrs, num_outputs)
61 except core._NotOkStatusException as e:
InvalidArgumentError: In[0] mismatch In[1] shape: 35 vs. 1: [32,35] [500,1] 0 0
[[node gradient_tape/sequential/dense_1/MatMul (defined at <ipython-input-15-b67ba9813850>:1) ]] [Op:__inference_train_function_847]
Function call stack:
train_function
can someone help?

How many classes are in the dataset? You have the code
cnn.add(tf.keras.layers.Dense(units=1,activation='softmax'))
This would indicate you are doing binary classification which I expect is not what you want. Try this after your generator code
classes=list(training_set.class_indices.keys())
class_count=len (classes) # this integer is the number of nodes you need in your models final layer
change the last layer in your model to
cnn.add(tf.keras.layers.Dense(units=class_count,activation='softmax'))

to predict a single image- first read in the image. If you trained your model on RGB images then
import matplotlib.pyplot as plt
import cv2
classes=list(train_gen.class_indices.keys())
img_path = r' full path to the image'
img=plt.imread(img_path)
img=cv2.resize(img, (64.64))
img=img/255
img=np.expand_dims(img, axis=0)
prediction=model.predict( img, verbose=1)
index=argmax(prediction)
predicted_class = classes(index)
I don't bother building my own CNN, instead I use transfer learning with the EfficientNetB3 model. Note EfficientNet expects pixels in the range 0 to 255 so do not scale the pixels. Code below works well for most applications
base_model=tf.keras.applications.EfficientNetB3(include_top=False, weights="imagenet",input_shape=img_shape, pooling='max')
x=base_model.output
x=keras.layers.BatchNormalization(axis=-1, momentum=0.99, epsilon=0.001 )(x)
x = Dense(256, kernel_regularizer = regularizers.l2(l = 0.016),activity_regularizer=regularizers.l1(0.006),
bias_regularizer=regularizers.l1(0.006) ,activation='relu')(x)
x=Dropout(rate=.45, seed=123)(x)
output=Dense(class_count, activation='softmax')(x)
model=Model(inputs=base_model.input, outputs=output)
model.compile(Adamax(learning_rate=.001), loss='categorical_crossentropy', metrics=['accuracy'])

InvalidArgumentError: Conv2DCustomBackpropFilterOp only supports NHWC - pruning neural network

Im having problems when I use the library tensorflow_model_optimization.
I am developing a code to prune an already trained neural network.
I imported the weights from an h5 file and so I use tensorflor_model_optimization to prune my neural network.
I have this error when I call the fit method:
InvalidArgumentError Traceback (most recent call last)
<ipython-input-26-ce9759e4dd53> in <module>
----> 1 model_for_pruning.fit_generator(base_treinamento, steps_per_epoch = 6000 /64, epochs = 5, validation_data = base_teste, validation_steps = 30, callbacks=callbacks)
~\anaconda3\envs\supernova\lib\site-packages\tensorflow\python\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1859 use_multiprocessing=use_multiprocessing,
1860 shuffle=shuffle,
-> 1861 initial_epoch=initial_epoch)
1862
1863 def evaluate_generator(self,
~\anaconda3\envs\supernova\lib\site-packages\tensorflow\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_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
1098 _r=1):
1099 callbacks.on_train_batch_begin(step)
-> 1100 tmp_logs = self.train_function(iterator)
1101 if data_handler.should_sync:
1102 context.async_wait()
~\anaconda3\envs\supernova\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
826 tracing_count = self.experimental_get_tracing_count()
827 with trace.Trace(self._name) as tm:
--> 828 result = self._call(*args, **kwds)
829 compiler = "xla" if self._experimental_compile else "nonXla"
830 new_tracing_count = self.experimental_get_tracing_count()
~\anaconda3\envs\supernova\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
853 # In this case we have created variables on the first call, so we run the
854 # defunned version which is guaranteed to never create variables.
--> 855 return self._stateless_fn(*args, **kwds) # pylint: disable=not-callable
856 elif self._stateful_fn is not None:
857 # Release the lock early so that multiple threads can perform the call
~\anaconda3\envs\supernova\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
2941 filtered_flat_args) = self._maybe_define_function(args, kwargs)
2942 return graph_function._call_flat(
-> 2943 filtered_flat_args, captured_inputs=graph_function.captured_inputs) # pylint: disable=protected-access
2944
2945 #property
~\anaconda3\envs\supernova\lib\site-packages\tensorflow\python\eager\function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1917 # No tape is watching; skip to running the function.
1918 return self._build_call_outputs(self._inference_function.call(
-> 1919 ctx, args, cancellation_manager=cancellation_manager))
1920 forward_backward = self._select_forward_and_backward_functions(
1921 args,
~\anaconda3\envs\supernova\lib\site-packages\tensorflow\python\eager\function.py in call(self, ctx, args, cancellation_manager)
558 inputs=args,
559 attrs=attrs,
--> 560 ctx=ctx)
561 else:
562 outputs = execute.execute_with_cancellation(
~\anaconda3\envs\supernova\lib\site-packages\tensorflow\python\eager\execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
58 ctx.ensure_initialized()
59 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60 inputs, attrs, num_outputs)
61 except core._NotOkStatusException as e:
62 if name is not None:
InvalidArgumentError: Conv2DCustomBackpropFilterOp only supports NHWC.
[[node gradient_tape/sequential_3/prune_low_magnitude_conv2d_18/Conv2D/Conv2DBackpropFilter (defined at <ipython-input-24-fc85f8818d30>:1) ]] [Op:__inference_train_function_10084]
Errors may have originated from an input operation.
Input Source operations connected to node gradient_tape/sequential_3/prune_low_magnitude_conv2d_18/Conv2D/Conv2DBackpropFilter:
sequential_3/prune_low_magnitude_activation_18/Relu (defined at C:\Users\Pichau\anaconda3\envs\supernova\lib\site-packages\tensorflow_model_optimization\python\core\sparsity\keras\pruning_wrapper.py:270)
Function call stack:
train_function
enter code here
My code:
from keras.models import model_from_json
from keras.preprocessing.image import ImageDataGenerator
import numpy as np
arquivo = open('model.json', 'r')
estrutura_rede = arquivo.read()
arquivo.close()
model = model_from_json(estrutura_rede)
model.load_weights('model.h5')
gerador_treinamento = ImageDataGenerator(rescale=None)
base_treinamento = gerador_treinamento.flow_from_directory('data/train', target_size = (51,51), batch_size = 64, class_mode = 'binary')
gerador_teste = ImageDataGenerator(rescale=None)
base_teste = gerador_teste.flow_from_directory('data/test', target_size = (51,51), batch_size = 64, class_mode = 'binary')
import tempfile
import tensorflow as tf
import tensorflow_model_optimization as tfmot
prune_low_magnitude = tfmot.sparsity.keras.prune_low_magnitude
batch_size = 128
epochs = 2
validation_split = 0.1
num_images = int(len(base_treinamento) * (1 - validation_split))
end_step = np.ceil(num_images / batch_size).astype(np.int32) * epochs
model_for_pruning.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
model_for_pruning.summary()
logdir = tempfile.mkdtemp()
callbacks = [
tfmot.sparsity.keras.UpdatePruningStep(),
tfmot.sparsity.keras.PruningSummaries(log_dir=logdir),
]
model_for_pruning.fit_generator(base_treinamento, steps_per_epoch = 6000 /64, epochs = 5, validation_data = base_teste, validation_steps = 30, callbacks=callbacks)
python: 3.6.12
tensorflow: 2.2.0
tensorflow-model-optimization: 0.5.0
Can someone help me?

Changing the runtime from CPU to GPU worked for me.
If you are running it on CPU consider changing it to GPU.

This does not seem like a pruning issue, but instead a problem with the data format of the model. It looks like one Conv2D layer should be using NHWC format (data_format="channels_last").
Could you share the code for the model?

model fit/ TypeError: 'NoneType' object is not callable

Hello I was trying to run model fit based on the following codes but somehow it keep saying
TypeError: 'NoneType' object is not callable. Not sure which part I have done wrong. THis is
part of my optimization training process. I am lost here... Is there minimum requirement to run such model.fit?
Please help me with this!
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras import datasets
(train_x, train_y), (test_x, test_y) = datasets.mnist.load_data()
inputs = layers.Input((28, 28, 1))
net = layers.Conv2D(32, (3, 3), padding ='SAME')(inputs)
net = layers.Activation('relu')(net)
net = layers.Conv2D(32, (3, 3), padding ='SAME')(net)
net = layers.Activation('relu')(net)
net = layers.MaxPooling2D(pool_size=(2, 2))(net)
net = layers.Dropout(0.25)(net)
net = layers.Conv2D(64, (3, 3), padding ='SAME')(net)
net = layers.Activation('relu')(net)
net = layers.Conv2D(64, (3, 3), padding ='SAME')(net)
net = layers.Activation('relu')(net)
net = layers.MaxPooling2D(pool_size=(2, 2))(net)
net = layers.Dropout(0.25)(net)
net = layers.Flatten()(net)
net = layers.Dense(512)(net)
net = layers.Activation('relu')(net)
net = layers.Dropout(0.5)(net)
net = layers.Dense(10)(net)
net = layers.Activation('softmax')(net)
model = tf.keras.Model(inputs=inputs, outputs=net, name='Basic_CNN')
loss_fun = tf.keras.losses.sparse_categorical_crossentropy
metrics = tf.keras.metrics.Accuracy()
optm = tf.keras.optimizers.Adam()
model.compile(optimizer=tf.keras.optimizers.Adam(),
loss='sparse_categorical_crossentropy',
metrics=[tf.keras.metrics.Accuracy()])
train_x.shape, train_y.shape
test_x.shape, test_y.shape
import numpy as np
np.expand_dims(train_x, -1).shape
tf.expand_dims(train_x, -1).shape
train_x = train_x[..., tf.newaxis]
test_x = test_x[..., tf.newaxis]
train_x.shape
np.min(train_x), np.max(train_x)
train_x = train_x / 255.
test_x = test_x / 255.
np.min(train_x), np.max(train_x)
num_epochs = 1
batch_size = 32
model.fit(train_x, train_y,
batch_size=batch_size,
shuffle=True,
epochs=num_epochs)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-20-870033ef5c40> in <module>
2 batch_size=batch_size,
3 shuffle=True,
----> 4 epochs=num_epochs)
~/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
106 def _method_wrapper(self, *args, **kwargs):
107 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
--> 108 return method(self, *args, **kwargs)
109
110 # Running inside `run_distribute_coordinator` already.
~/opt/anaconda3/lib/python3.6/site-packages/tensorflow/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_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
1096 batch_size=batch_size):
1097 callbacks.on_train_batch_begin(step)
-> 1098 tmp_logs = train_function(iterator)
1099 if data_handler.should_sync:
1100 context.async_wait()
~/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
778 else:
779 compiler = "nonXla"
--> 780 result = self._call(*args, **kwds)
781
782 new_tracing_count = self._get_tracing_count()
~/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
805 # In this case we have created variables on the first call, so we run the
806 # defunned version which is guaranteed to never create variables.
--> 807 return self._stateless_fn(*args, **kwds) # pylint: disable=not-callable
808 elif self._stateful_fn is not None:
809 # Release the lock early so that multiple threads can perform the call
TypeError: 'NoneType' object is not callable

You must do two things.
First you must change loss to: categorical_crossentropy.
Second you need your train_y and test_y have to be one-hot-encoded. That means they must have dimension (number_of_samples, 10), where 10 denotes number of classes. Add this after model.compile():
num_classes = 10 #number of classes, here is 10 (0,1,...,9)
train_y = keras.utils.to_categorical(train_y, num_classes)
test_y = keras.utils.to_categorical(test_y, num_classes)
Finally, let me say this you should change number of epochs and batch size to get better result. For example epochs count = 12 and batch size = 128

I was getting this error when I was referring to losses and metric functions by names. The error was gone after I replaced the names with objects. In your case I would recommend to add import statements and change the model compilation parameters, ie.:
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.losses import SparseCategoricalCrossentropy
from tensorflow.keras.metrics import Accuracy
...
model.compile(optimizer=Adam(),
loss=SparseCategoricalCrossentropy(from_logits=True),
metrics=[Accuracy()])

Keras - CNN - adjust dataset - remove biased class and data augmentation attempt

I have a a predicament with the model I am developing based on a popular dataset of skin-cancer images.
I have to points I'd like some guidance on -
A.
The original dataset is over +10K images with which almost 7000 images belong to one of the seven classes. I've created a subset of 4948 random images with which I ran a function to convert the images into a list of lists - first list contains the image and the latter the class as well as dismiss any images that are of class (5 - the class with the +6800K images). Thought process was to normalise the distribution across the classes.
Re-running the original model with an output (Dense layer of 6 neurons instead of 7) - retrieves an error.
Am I missing a step to 'indicate' to the model that there are only six possible classes? The model runs only when the output layer has seven neurons.
error:
Train on 1245 samples, validate on 312 samples
Epoch 1/30
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-138-8a3b40a69e37> in <module>
25 metrics=["accuracy"])
26
---> 27 model.fit(X_train, y_train, batch_size=32, epochs=30, validation_split=0.2)
/anaconda3/lib/python3.7/site-packages/tensorflow/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)
778 validation_steps=validation_steps,
779 validation_freq=validation_freq,
--> 780 steps_name='steps_per_epoch')
781
782 def evaluate(self,
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_arrays.py in model_iteration(model, inputs, targets, sample_weights, batch_size, epochs, verbose, callbacks, val_inputs, val_targets, val_sample_weights, shuffle, initial_epoch, steps_per_epoch, validation_steps, validation_freq, mode, validation_in_fit, prepared_feed_values_from_dataset, steps_name, **kwargs)
361
362 # Get outputs.
--> 363 batch_outs = f(ins_batch)
364 if not isinstance(batch_outs, list):
365 batch_outs = [batch_outs]
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/backend.py in __call__(self, inputs)
3290
3291 fetched = self._callable_fn(*array_vals,
-> 3292 run_metadata=self.run_metadata)
3293 self._call_fetch_callbacks(fetched[-len(self._fetches):])
3294 output_structure = nest.pack_sequence_as(
/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in __call__(self, *args, **kwargs)
1456 ret = tf_session.TF_SessionRunCallable(self._session._session,
1457 self._handle, args,
-> 1458 run_metadata_ptr)
1459 if run_metadata:
1460 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
InvalidArgumentError: Received a label value of 6 which is outside the valid range of [0, 6). Label values: 1 1 2 4 2 1 2 1 2 1 2 2 4 2 2 1 3 1 4 6 0 2 4 2 0 4 2 4 4 0 2 4
[[{{node loss_15/activation_63_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits}}]]
B.
I'm attempting to add Data Augmentation as the dataset is relatively small taking into account the number of classes and the sparsity of the images across the classes. Once I try to run the generator I receive the error message below which suggests that there is something wrong with one of the variables in the validation_data tuple. I cannot understand what the issue is.
Example values of the test set look like:
[[[[0.41568627]
[0.4 ]
[0.43137255]
...
[0.54509804]
[0.54901961]
[0.54509804]]
[[0.42352941]
[0.43137255]
[0.43921569]
...
[0.56078431]
[0.54117647]
[0.55294118]]
[[0.41960784]
[0.41960784]
[0.45490196]
...
[0.51764706]
[0.57254902]
[0.50588235]]
...
[[0.30980392]
[0.36470588]
[0.36470588]
...
[0.47058824]
[0.44705882]
[0.41960784]]
[[0.29803922]
[0.31764706]
[0.34509804]
...
[0.45098039]
[0.43921569]
[0.4 ]]
[[0.25882353]
[0.30196078]
[0.31764706]
...
[0.45490196]
[0.42745098]
[0.36078431]]]
[[[0.60784314]
[0.59215686]
[0.56862745]
...
[0.59607843]
[0.63921569]
[0.63529412]]
[[0.6627451 ]
[0.63137255]
[0.62352941]
...
[0.67843137]
[0.60784314]
[0.63529412]]
[[0.62745098]
[0.65098039]
[0.6 ]
...
[0.61568627]
[0.63921569]
[0.67058824]]
...
[[0.62352941]
[0.6 ]
[0.59607843]
...
[0.6627451 ]
[0.71372549]
[0.6745098 ]]
[[0.61568627]
[0.58431373]
[0.61568627]
...
[0.67058824]
[0.65882353]
[0.68235294]]
[[0.61176471]
[0.60392157]
[0.61960784]
...
[0.65490196]
[0.6627451 ]
[0.66666667]]]]
[2, 1, 4, 4, 2]
Error:
Epoch 1/10
1/155 [..............................] - ETA: 11s - loss: 1.7916 - acc: 0.3000
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-139-8f19a958861f> in <module>
12 history = model.fit_generator(trainAug.flow(X_train, y_train, batch_size=batch_size)
13 ,epochs = 10, validation_data = (X_test, y_test),
---> 14 steps_per_epoch= X_train.shape[0]// batch_size
15 )
16 #epochs = epochs, validation_data = (X_test, y_test),
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1431 shuffle=shuffle,
1432 initial_epoch=initial_epoch,
-> 1433 steps_name='steps_per_epoch')
1434
1435 def evaluate_generator(self,
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_generator.py in model_iteration(model, data, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch, mode, batch_size, steps_name, **kwargs)
262
263 is_deferred = not model._is_compiled
--> 264 batch_outs = batch_function(*batch_data)
265 if not isinstance(batch_outs, list):
266 batch_outs = [batch_outs]
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight, reset_metrics)
1173 self._update_sample_weight_modes(sample_weights=sample_weights)
1174 self._make_train_function()
-> 1175 outputs = self.train_function(ins) # pylint: disable=not-callable
1176
1177 if reset_metrics:
/anaconda3/lib/python3.7/site-packages/tensorflow/python/keras/backend.py in __call__(self, inputs)
3290
3291 fetched = self._callable_fn(*array_vals,
-> 3292 run_metadata=self.run_metadata)
3293 self._call_fetch_callbacks(fetched[-len(self._fetches):])
3294 output_structure = nest.pack_sequence_as(
/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in __call__(self, *args, **kwargs)
1456 ret = tf_session.TF_SessionRunCallable(self._session._session,
1457 self._handle, args,
-> 1458 run_metadata_ptr)
1459 if run_metadata:
1460 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
InvalidArgumentError: Received a label value of 6 which is outside the valid range of [0, 6). Label values: 0 1 6 4 2 4 2 0 1 2
[[{{node loss_15/activation_63_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits}}]]
Code:
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import sys
import os
import cv2
DATA_DIR = "/Users/namefolder/PycharmProjects/skin-cancer/HAM10000_images_part_1"
metadata = pd.read_csv(os.path.join(DATA_DIR, 'HAM10000_metadata.csv'))
lesion_type_dict = {'nv': 'Melanocytic nevi',
'mel': 'Melanoma',
'bkl': 'Benign keratosis-like lesions ',
'bcc': 'Basal cell carcinoma',
'akiec': 'Actinic keratoses',
'vasc': 'Vascular lesions',
'df': 'Dermatofibroma'}
metadata['cell_type'] = metadata['dx'].map(lesion_type_dict.get)
metadata['dx_code'] = pd.Categorical(metadata['dx']).codes
# save array of image-id and diagnosis-type (categorical)
metadata = metadata[['image_id', 'dx', 'dx_type', 'dx_code']]
training_data = []
IMG_SIZE=50
# preparing training data
def creating_training_data(path):
for img in os.listdir(path):
try:
img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)
new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
for index, row in metadata.iterrows():
if (img == row['image_id']+'.jpg') & (row['dx_code'] != 5):
try:
training_data.append([new_array, row['dx_code']])
except Exception as ee:
pass
except Exception as e:
pass
return training_data
training_data = creating_training_data(DATA_DIR)
import random
random.shuffle(training_data)
# Splitting data into X features and Y label
X_train = []
y_train = []
for features, label in training_data:
X_train.append(features)
y_train.append(label)
# Reshaping of the data - required by Tensorflow and Keras (*necessary step of deep-learning using these repos)
X_train = np.array(X_train).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
# Normalize data - to reduce processing requirements
X_train = X_train/255.0
# model configuration
model = Sequential()
model.add(Conv2D(64, (3,3), input_shape = X_train.shape[1:]))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3,3)))
model.add(Activation("relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Dense(6))
model.add(Activation("softmax"))
model.compile(loss="mean_squared_error",
optimizer="adam",
metrics=["accuracy"])
# Data Augmentation - Repo enabler
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ReduceLROnPlateau
# initialize the training training data augmentation object
trainAug = ImageDataGenerator(
rescale=1 / 255.0,
rotation_range=20,
zoom_range=0.05,
width_shift_range=0.05,
height_shift_range=0.05,
shear_range=0.05,
horizontal_flip=True,
fill_mode="nearest")
# initialize the validation (and testing) data augmentation object
valAug = ImageDataGenerator(rescale=1 / 255.0)
#set a leraning rate annealer
learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc',
patience=3,
verbose=1,
factor=0.5,
min_lr=0.00001)
#Augmented Images model development
)
trainAug.fit(X_train)
#Fit the model
epochs = 10
batch_size= 10
history = model.fit_generator(trainAug.flow(X_train, y_train, batch_size=batch_size),epochs = 10, validation_data = (X_test, y_test), steps_per_epoch= X_train.shape[0]// batch_size)

Initially you had 7 labels: your code was then expecting labels 0, 1, 2, 3, 4, 5, 6
You removed label 5 from the dataset, ok. Now you have 6 labels in total.
Your code is expecting: 0, 1, 2, 3, 4, 5
But what you have in your data is: 0, 1, 2, 3, 4, 6
After removing the label 5, you need to transform the labels 6 into 5.
Something in the lines of:
if (img == row['image_id']+'.jpg') & (row['dx_code'] > 5):
try:
training_data.append([new_array, row['dx_code'] - 1])
except Exception as ee:
pass
elif (img == row['image_id']+'.jpg') & (row['dx_code'] < 5):
try:
training_data.append([new_array, row['dx_code']])
except Exception as ee:
pass

InvalidArgumentError while training long short term memory network with Python/Keras (Audio classification)

I am new to Keras and I am trying to build a recurrent neural network to classify Audio files.
During the training, I am receiving an InvalidArgumentError: indices[28,0] = -711 is not in [0, 20000).
I have found various topics talking about this error but, to be honest, I did not understand what I have to change in the parameters I am passing to the network in order to help it managing the negative values I have in the training array.
Below the code:
from keras.models import Sequential
from keras.layers import Dense, Dropout, Embedding, LSTM, Bidirectional
max_features = 20000
maxlen = 40
batch_size = 32
model = Sequential()
model.add(Embedding(max_features, 128, input_length=maxlen))
model.add(Bidirectional(LSTM(64)))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
# try using different optimizers and different optimizer configs
model.compile('adam', 'binary_crossentropy', metrics=['accuracy'])
print('Train...')
model.fit(X_train, y_train,
batch_size=batch_size,
epochs=4,
validation_data=[X_test, y_test])
Error below:
Train...
Train on 964 samples, validate on 476 samples
Epoch 1/4
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-22-3452d23cb8b5> in <module>()
12 batch_size=batch_size,
13 epochs=4,
---> 14 validation_data=[X_test, y_test])
/usr/local/lib/python3.6/dist-packages/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, **kwargs)
1037 initial_epoch=initial_epoch,
1038 steps_per_epoch=steps_per_epoch,
-> 1039 validation_steps=validation_steps)
1040
1041 def evaluate(self, x=None, y=None,
/usr/local/lib/python3.6/dist-packages/keras/engine/training_arrays.py in fit_loop(model, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps)
197 ins_batch[i] = ins_batch[i].toarray()
198
--> 199 outs = f(ins_batch)
200 outs = to_list(outs)
201 for l, o in zip(out_labels, outs):
/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)
2713 return self._legacy_call(inputs)
2714
-> 2715 return self._call(inputs)
2716 else:
2717 if py_any(is_tensor(x) for x in inputs):
/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py in _call(self, inputs)
2673 fetched = self._callable_fn(*array_vals, run_metadata=self.run_metadata)
2674 else:
-> 2675 fetched = self._callable_fn(*array_vals)
2676 return fetched[:len(self.outputs)]
2677
/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in __call__(self, *args, **kwargs)
1437 ret = tf_session.TF_SessionRunCallable(
1438 self._session._session, self._handle, args, status,
-> 1439 run_metadata_ptr)
1440 if run_metadata:
1441 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
526 None, None,
527 compat.as_text(c_api.TF_Message(self.status.status)),
--> 528 c_api.TF_GetCode(self.status.status))
529 # Delete the underlying status object from memory otherwise it stays alive
530 # as there is a reference to status from this from the traceback due to
InvalidArgumentError: indices[28,0] = -711 is not in [0, 20000)
[[{{node embedding_3/embedding_lookup}} = GatherV2[Taxis=DT_INT32, Tindices=DT_INT32, Tparams=DT_FLOAT, _class=["loc:#training_1/Adam/Assign_2"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](embedding_3/embeddings/read, embedding_3/Cast, training_1/Adam/gradients/embedding_3/embedding_lookup_grad/concat/axis)]]
EDIT1: X_train is the float32 array below
array([[-5.79938449e+02, 6.63875936e+01, -6.75054944e+00, ...,
-2.89458464e+00, -2.30009868e+00, -2.34216322e+00],
[-3.38924973e+02, 1.60668197e+01, -5.39871140e+01, ...,
1.27180395e+00, 4.28090614e+00, 2.01538667e+00],
[-5.53199739e+02, 3.45314936e+01, -1.68711443e+01, ...,
-9.47345310e-02, -1.04780706e-02, 1.69060756e-01],
...,
[-5.91902354e+02, 6.14329122e+01, 1.43761675e+00, ...,
-4.38644438e+00, -3.67977820e+00, -1.89899207e+00],
[-7.04889969e+02, 6.24931510e+01, 1.90338300e+01, ...,
-1.47540089e+00, -1.75498741e+00, -4.55713837e-01],
[-8.24296641e+02, 7.43124586e+01, 1.43319513e+01, ...,
-7.60749297e-01, -1.05324700e+00, -8.54044186e-01]])