Develop Reference

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?

My model.fit and model.evaluate are not working properly and I am getting an error

train_x = train['text']
valid_x = valid["text"]
train_y = train["label"]
valid_y = valid["label"]
train_y = train_y.values.reshape(-1,1)
vectorizer = TfidfVectorizer()
vectorizer.fit_transform(train_x)
x_train_count = vectorizer.fit_transform(train_x)
x_valid_count = vectorizer.fit_transform(valid_x)
x_test_count = vectorizer.fit_transform(test["text"])
model = tf.keras.Sequential()
model.add(Dense(50,input_dim=x_train_count.shape[1], kernel_initializer="uniform", activation="relu"))
model.add(Dense(1, kernel_initializer="uniform", activation="sigmoid"))
model.compile(loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"])
# # Fit the model
history = model.fit(x_train_count, train_y, validation_data=(x_valid_count,valid_y), epochs=3, batch_size=128)
loss, acc = model.evaluate(x_test_count, test["label"], verbose=0)
Error
--------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-1-be49478b4c50> in <module>
71 model.compile(loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"])
72 # # Fit the model
---> 73 history = model.fit(x_train_count, train_y, validation_data=(x_valid_count,valid_y), epochs=3, batch_size=128)
74
75 loss, acc = model.evaluate(x_test_count, test["label"], verbose=0)
~\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)
1048 training_utils.RespectCompiledTrainableState(self):
1049 # Creates a `tf.data.Dataset` and handles batch and epoch iteration.
-> 1050 data_handler = data_adapter.DataHandler(
1051 x=x,
1052 y=y,
~\anaconda3\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in __init__(self, x, y, sample_weight, batch_size, steps_per_epoch, initial_epoch, epochs, shuffle, class_weight, max_queue_size, workers, use_multiprocessing, model, steps_per_execution)
1098
1099 adapter_cls = select_data_adapter(x, y)
-> 1100 self._adapter = adapter_cls(
1101 x,
1102 y,
~\anaconda3\lib\site-packages\tensorflow\python\keras\engine\data_adapter.py in __init__(self, x, y, sample_weights, sample_weight_modes, batch_size, steps, shuffle, **kwargs)
564 inputs = pack_x_y_sample_weight(x, y, sample_weights)
565
--> 566 dataset = dataset_ops.DatasetV2.from_tensor_slices(inputs)
567 num_samples = int(nest.flatten(x)[0].shape[0])
568 if shuffle:
~\anaconda3\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py in from_tensor_slices(tensors)
689 Dataset: A `Dataset`.
690 """
--> 691 return TensorSliceDataset(tensors)
692
693 class _GeneratorState(object):
~\anaconda3\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py in __init__(self, element)
3155 element = structure.normalize_element(element)
3156 batched_spec = structure.type_spec_from_value(element)
-> 3157 self._tensors = structure.to_batched_tensor_list(batched_spec, element)
3158 self._structure = nest.map_structure(
3159 lambda component_spec: component_spec._unbatch(), batched_spec) # pylint: disable=protected-access
~\anaconda3\lib\site-packages\tensorflow\python\data\util\structure.py in to_batched_tensor_list(element_spec, element)
362 # pylint: disable=protected-access
363 # pylint: disable=g-long-lambda
--> 364 return _to_tensor_list_helper(
365 lambda state, spec, component: state + spec._to_batched_tensor_list(
366 component), element_spec, element)
~\anaconda3\lib\site-packages\tensorflow\python\data\util\structure.py in _to_tensor_list_helper(encode_fn, element_spec, element)
337 return encode_fn(state, spec, component)
338
--> 339 return functools.reduce(
340 reduce_fn, zip(nest.flatten(element_spec), nest.flatten(element)), [])
341
~\anaconda3\lib\site-packages\tensorflow\python\data\util\structure.py in reduce_fn(state, value)
335 def reduce_fn(state, value):
336 spec, component = value
--> 337 return encode_fn(state, spec, component)
338
339 return functools.reduce(
~\anaconda3\lib\site-packages\tensorflow\python\data\util\structure.py in <lambda>(state, spec, component)
363 # pylint: disable=g-long-lambda
364 return _to_tensor_list_helper(
--> 365 lambda state, spec, component: state + spec._to_batched_tensor_list(
366 component), element_spec, element)
367
~\anaconda3\lib\site-packages\tensorflow\python\framework\sparse_tensor.py in _to_batched_tensor_list(self, value)
367 raise ValueError(
368 "Unbatching a sparse tensor is only supported for rank >= 1")
--> 369 return [gen_sparse_ops.serialize_many_sparse(
370 value.indices, value.values, value.dense_shape,
371 out_type=dtypes.variant)]
~\anaconda3\lib\site-packages\tensorflow\python\ops\gen_sparse_ops.py in serialize_many_sparse(sparse_indices, sparse_values, sparse_shape, out_type, name)
493 return _result
494 except _core._NotOkStatusException as e:
--> 495 _ops.raise_from_not_ok_status(e, name)
496 except _core._FallbackException:
497 pass
~\anaconda3\lib\site-packages\tensorflow\python\framework\ops.py in raise_from_not_ok_status(e, name)
6860 message = e.message + (" name: " + name if name is not None else "")
6861 # pylint: disable=protected-access
-> 6862 six.raise_from(core._status_to_exception(e.code, message), None)
6863 # pylint: enable=protected-access
6864
~\anaconda3\lib\site-packages\six.py in raise_from(value, from_value)
InvalidArgumentError: indices[1] = [0,40295] is out of order. Many sparse ops require sorted indices.
Use tf.sparse.reorder to create a correctly ordered copy.

The object returned by the fit_transform() and fit() methods of TfIdfVectorizer are compressed sparse row format matrix. So in order to convert them into dense matrix use .toarray() function.
Furthermore, you should fit your TfIdfVectorizer on the train_set only and then use it to transform your validation and test set without re-fitting it every time to avoid to use data from test set since it might introduce some data leakage and yield in too optimistic performances. Also, since the test and validation sets are usually small fitting a TfIdf solely on them will result in poor vectorization. Finally, and the Idf factor will be different for the same words in training, validation and test sets, and this is usually not desired.
For the mentioned reasons I would suggest to fit the TfIdfVectorizer only on the training set and then use the fitted vectorizer to transform the validation and test sets.
Here an example:
vectorizer = TfidfVectorizer()
x_train_count = vectorizer.fit_transform(train_x).toarray()
x_valid_count = vectorizer.transform(valid_x).toarray()
x_test_count = vectorizer.transform(test["text"]).toarray()
If your data do not fit into memory, you could consider to iteratively convert to a dense matrix only one batch at the time. Here a function to create a batch generator from a sparse x_train matrix:
def sparse_matrix_batch_generator(X, y, batch_size=32):
num_samples = np.shape(y)[0]
shuffled_index = np.arange(num_samples)
np.random.shuffle(shuffled_index)
X = X[shuffled_index, :]
y = y[shuffled_index]
for n in range(num_samples//batch_size):
batch_index = shuffled_index[n*batch_size:(n+1)*batch_size]
X_batch = X[batch_index, :].todense()
y_batch = y[batch_index]
yield (X_batch, y_batch)

"Function call stack: keras_scratch_graph" - Glove embedded text sentiment analysis

A relatively simple block of code running in Jupyter notebook (because I cannot for the life of me get it working in Google Colab) but I'm getting the below error when running the model. The linked post shows some more of the detail around the inputs I'm working with.
I think it may be a GPU related error. I've followed several similarly titled posts and CUDA/Visual Studio installation tutorials, to no avail.
import gensim
import os
from gensim.models import KeyedVectors
from gensim.test.utils import datapath, get_tmpfile
from gensim.scripts.glove2word2vec import glove2word2vec
glove_file = datapath('glove.6B.50d.txt')
word2vec_glove_file = get_tmpfile("glove.6B.50d.word2vec.txt")
glove2word2vec(glove_file, word2vec_glove_file)
model = KeyedVectors.load_word2vec_format(word2vec_glove_file, binary=False)
# get the vector for each word in the glove file
emb_dict = {}
glove = open(glove_file, encoding="utf8")
for line in glove:
values = line.split()
word = values[0]
vector = numpy.asarray(values[1:], dtype='float32')
emb_dict[word] = vector
glove.close()
# get the top 10k words in the tweets, and find their vector from the glove files
num_words = 10000
glove_dims = 50
emb_matrix = numpy.zeros((num_words, glove_dims))
for w, i in token.word_index.items():
if i < num_words:
vect = emb_dict.get(w)
if vect is not None:
emb_matrix[i] = vect
else:
break
from keras import models, layers
from keras.layers import Embedding, Flatten, Dense
glove_model = models.Sequential()
glove_model.add(Embedding(num_words, glove_dims, input_length=max_tweet_len))
glove_model.add(layers.LSTM(100))
#glove_model.add(Flatten())
glove_model.add(Dense(3, activation='softmax'))
glove_model.layers[0].set_weights([emb_matrix])
glove_model.layers[0].trainable = False
glove_model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
history = glove_model.fit(train_seq_x, y_train, epochs=10, batch_size=64)
The error returned is:
Epoch 1/10
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-11-224ee1a00f0e> in <module>
13 glove_model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
14
---> 15 history = glove_model.fit(train_seq_x, y_train, epochs=10, batch_size=64)
~\anaconda3\lib\site-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, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
1237 steps_per_epoch=steps_per_epoch,
1238 validation_steps=validation_steps,
-> 1239 validation_freq=validation_freq)
1240
1241 def evaluate(self,
~\anaconda3\lib\site-packages\keras\engine\training_arrays.py in fit_loop(model, fit_function, fit_inputs, out_labels, batch_size, epochs, verbose, callbacks, val_function, val_inputs, shuffle, initial_epoch, steps_per_epoch, validation_steps, validation_freq)
194 ins_batch[i] = ins_batch[i].toarray()
195
--> 196 outs = fit_function(ins_batch)
197 outs = to_list(outs)
198 for l, o in zip(out_labels, outs):
~\anaconda3\lib\site-packages\tensorflow\python\keras\backend.py in __call__(self, inputs)
3790 value = math_ops.cast(value, tensor.dtype)
3791 converted_inputs.append(value)
-> 3792 outputs = self._graph_fn(*converted_inputs)
3793
3794 # EagerTensor.numpy() will often make a copy to ensure memory safety.
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
1603 TypeError: For invalid positional/keyword argument combinations.
1604 """
-> 1605 return self._call_impl(args, kwargs)
1606
1607 def _call_impl(self, args, kwargs, cancellation_manager=None):
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _call_impl(self, args, kwargs, cancellation_manager)
1643 raise TypeError("Keyword arguments {} unknown. Expected {}.".format(
1644 list(kwargs.keys()), list(self._arg_keywords)))
-> 1645 return self._call_flat(args, self.captured_inputs, cancellation_manager)
1646
1647 def _filtered_call(self, args, kwargs):
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1744 # No tape is watching; skip to running the function.
1745 return self._build_call_outputs(self._inference_function.call(
-> 1746 ctx, args, cancellation_manager=cancellation_manager))
1747 forward_backward = self._select_forward_and_backward_functions(
1748 args,
~\anaconda3\lib\site-packages\tensorflow\python\eager\function.py in call(self, ctx, args, cancellation_manager)
596 inputs=args,
597 attrs=attrs,
--> 598 ctx=ctx)
599 else:
600 outputs = execute.execute_with_cancellation(
~\anaconda3\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: indices[40,19] = 11263 is not in [0, 10000)
[[node embedding_1/embedding_lookup (defined at C:\Users\Jorda\anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py:3009) ]] [Op:__inference_keras_scratch_graph_1707]
Function call stack:
keras_scratch_graph
As requested in the comments, the method of tokenisation is as follows:
from keras.preprocessing import text, sequence
# create a tokenizer
token = text.Tokenizer()
token.fit_on_texts(tweets)
word_index = token.word_index
max_tweet_len = 30
# convert text to sequence of tokens and pad them to ensure equal length vectors
train_seq_x = sequence.pad_sequences(token.texts_to_sequences(x_train), maxlen=max_tweet_len)
test_seq_x = sequence.pad_sequences(token.texts_to_sequences(x_test), maxlen=max_tweet_len)
print(train_seq_x)
print(test_seq_x)

try to fit your tokenizer in this way
num_words = 10000
token = text.Tokenizer(num_words=num_words)
and when you define your model, change num_words with word_index+1 in Embedding layer

tensorflow and keras: None values not supported

I am running the code below in Jupyter notebook. The first chunk of code works okay but when the running the second chunk of code i get an error message "ValueError: None values not supported". I am using tensorflow and keras. Thanks a lot
features=skin_df.drop(columns=['cell_type_idx'],axis=1)
target=skin_df['cell_type_idx']
# Train Test Split
x_train_o, x_test_o, y_train_o, y_test_o = train_test_split(features, target, test_size=0.20,random_state=1234)
x_train = np.asarray(x_train_o['image'].tolist())
x_test = np.asarray(x_test_o['image'].tolist())
x_train_mean = np.mean(x_train)
x_train_std = np.std(x_train)
x_test_mean = np.mean(x_test)
x_test_std = np.std(x_test)
x_train = (x_train - x_train_mean)/x_train_std
x_test = (x_test - x_test_mean)/x_test_std
# Perform one-hot encoding on the labels
y_train = to_categorical(y_train_o, num_classes = 7)
y_test = to_categorical(y_test_o, num_classes = 7)
# Set a learning rate annealer
learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc',
patience=3,
verbose=1,
factor=0.5,
min_lr=0.00001)
#1. Function to plot model's validation loss and validation accuracy
def plot_model_history(model_history):
fig, axs = plt.subplots(1,2,figsize=(15,5))
# summarize history for accuracy
axs[0].plot(range(1,len(model_history.history['acc'])+1),model_history.history['acc'])
axs[0].plot(range(1,len(model_history.history['val_acc'])+1),model_history.history['val_acc'])
axs[0].set_title('Model Accuracy')
axs[0].set_ylabel('Accuracy')
axs[0].set_xlabel('Epoch')
axs[0].set_xticks(np.arange(1,len(model_history.history['acc'])+1),len(model_history.history['acc'])/10)
axs[0].legend(['train', 'val'], loc='best')
# summarize history for loss
axs[1].plot(range(1,len(model_history.history['loss'])+1),model_history.history['loss'])
axs[1].plot(range(1,len(model_history.history['val_loss'])+1),model_history.history['val_loss'])
axs[1].set_title('Model Loss')
axs[1].set_ylabel('Loss')
axs[1].set_xlabel('Epoch')
axs[1].set_xticks(np.arange(1,len(model_history.history['loss'])+1),len(model_history.history['loss'])/10)
axs[1].legend(['train', 'val'], loc='best')
plt.show()
epochs = 50
batch_size = 10
history = model.fit_generator(datagen.flow(x_train,y_train, batch_size=batch_size),
epochs = epochs, validation_data = (x_validate,y_validate),
verbose = 1, steps_per_epoch=x_train.shape[0] // batch_size
, callbacks=[learning_rate_reduction])
error message with trace back
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-74-b36dfc5ecc8e> in <module>
5 epochs = epochs, validation_data = (x_validate,y_validate),
6 verbose = 1, steps_per_epoch=x_train.shape[0] // batch_size
----> 7 , callbacks=[learning_rate_reduction])
~\.conda\envs\Project_2\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~\.conda\envs\Project_2\lib\site-packages\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)
1730 use_multiprocessing=use_multiprocessing,
1731 shuffle=shuffle,
-> 1732 initial_epoch=initial_epoch)
1733
1734 #interfaces.legacy_generator_methods_support
~\.conda\envs\Project_2\lib\site-packages\keras\engine\training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
40
41 do_validation = bool(validation_data)
---> 42 model._make_train_function()
43 if do_validation:
44 model._make_test_function()
~\.conda\envs\Project_2\lib\site-packages\keras\engine\training.py in _make_train_function(self)
314 training_updates = self.optimizer.get_updates(
315 params=self._collected_trainable_weights,
--> 316 loss=self.total_loss)
317 updates = self.updates + training_updates
318
~\.conda\envs\Project_2\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~\.conda\envs\Project_2\lib\site-packages\keras\backend\tensorflow_backend.py in symbolic_fn_wrapper(*args, **kwargs)
73 if _SYMBOLIC_SCOPE.value:
74 with get_graph().as_default():
---> 75 return func(*args, **kwargs)
76 else:
77 return func(*args, **kwargs)
~\.conda\envs\Project_2\lib\site-packages\keras\optimizers.py in get_updates(self, loss, params)
541 self.updates.append(K.update(vhat, vhat_t))
542 else:
--> 543 p_t = p - lr_t * m_t / (K.sqrt(v_t) + self.epsilon)
544
545 self.updates.append(K.update(m, m_t))
~\.conda\envs\Project_2\lib\site-packages\tensorflow_core\python\ops\math_ops.py in binary_op_wrapper(x, y)
904 try:
905 y = ops.convert_to_tensor_v2(
--> 906 y, dtype_hint=x.dtype.base_dtype, name="y")
907 except TypeError:
908 # If the RHS is not a tensor, it might be a tensor aware object
~\.conda\envs\Project_2\lib\site-packages\tensorflow_core\python\framework\ops.py in convert_to_tensor_v2(value, dtype, dtype_hint, name)
1254 name=name,
1255 preferred_dtype=dtype_hint,
-> 1256 as_ref=False)
1257
1258
~\.conda\envs\Project_2\lib\site-packages\tensorflow_core\python\framework\ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
1312
1313 if ret is None:
-> 1314 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1315
1316 if ret is NotImplemented:
~\.conda\envs\Project_2\lib\site-packages\tensorflow_core\python\framework\constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
315 as_ref=False):
316 _ = as_ref
--> 317 return constant(v, dtype=dtype, name=name)
318
319
~\.conda\envs\Project_2\lib\site-packages\tensorflow_core\python\framework\constant_op.py in constant(value, dtype, shape, name)
256 """
257 return _constant_impl(value, dtype, shape, name, verify_shape=False,
--> 258 allow_broadcast=True)
259
260
~\.conda\envs\Project_2\lib\site-packages\tensorflow_core\python\framework\constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
294 tensor_util.make_tensor_proto(
295 value, dtype=dtype, shape=shape, verify_shape=verify_shape,
--> 296 allow_broadcast=allow_broadcast))
297 dtype_value = attr_value_pb2.AttrValue(type=tensor_value.tensor.dtype)
298 const_tensor = g._create_op_internal( # pylint: disable=protected-access
~\.conda\envs\Project_2\lib\site-packages\tensorflow_core\python\framework\tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape, allow_broadcast)
437 else:
438 if values is None:
--> 439 raise ValueError("None values not supported.")
440 # if dtype is provided, forces numpy array to be the type
441 # provided if possible.
ValueError: None values not supported.
Please see the above error code. thanks

I have fixed the issue by creating a new environment and installing Keras and not tensorflow that seems to resolve my issue.

i think in model.compile you have assigned optimizer with predefined variable instead of that use this one """model.compile(optimizer = 'Adam' I wish the best

Writing your custom function for image preprocessing in Keras

I am a beginner training an image dataset on diabetic retinopathy, using the keras_flow_from_dataframe class. But my model has been underfitting. So I tried preprocessing, by writing a custom preprocessing function to be passed in my image data generator class, using OpenCV's adaptive thresholding implementation. The function works very well when I use it outside of Keras, but when I add it to my image data generator class and fit my model, it returns a type error saying bad argument type for built-in operation before my first epoch starts.
Here's the preprocessing code:
def preprocess(im):
im = cv2.imread(im, 1)
im= cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
im=cv2.resize(im, (300,300))
im.resize(300, 300, 1)
block_size = 73
constant = 2
# ADAPTIVE GAUSSIAN THRESHOLDING
thr2 = cv2.adaptiveThreshold(im, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, block_size, constant)
return thr2
It runs well outside of Keras when I test it with the images in my dataframe, but when I add it to my image data generator class, it throws an error.
train_datagen = ImageDataGenerator(
rotation_range=30,
width_shift_range=0.4,
height_shift_range=0.4,
shear_range=0.3,
zoom_range=0.3,
horizontal_flip = True,
fill_mode='nearest',
preprocessing_function = preprocess)
valid_datagen = ImageDataGenerator(preprocessing_function = preprocess)
Then I load in my dataset from dataframe:
from keras.preprocessing.image import ImageDataGenerator
traingen = train_datagen.flow_from_dataframe(x_train, x_col='path', y_col='level',class_mode='other',
target_size=(300,300), color_mode='grayscale', batch_size=16)
validgen = valid_datagen.flow_from_dataframe(valid, x_col='path', y_col='level',class_mode='other',
target_size=(300,300), color_mode='grayscale', batch_size=16)
Then I fit the model using model.fit_generator, which then throws me the type error: bad argument type for built-in operation.
TypeError Traceback (most recent call last)
<ipython-input-126-30ceb84a2574> in <module>()
2
3 history = model.fit_generator(traingen, validation_data = validgen, epochs=100, steps_per_epoch=10,
----> 4 validation_steps=10, verbose=1, callbacks=[lr_reduction])
5
6
~/var/python/lib/python3.6/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~/var/python/lib/python3.6/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1416 use_multiprocessing=use_multiprocessing,
1417 shuffle=shuffle,
-> 1418 initial_epoch=initial_epoch)
1419
1420 #interfaces.legacy_generator_methods_support
~/var/python/lib/python3.6/site-packages/keras/engine/training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
179 batch_index = 0
180 while steps_done < steps_per_epoch:
--> 181 generator_output = next(output_generator)
182
183 if not hasattr(generator_output, '__len__'):
~/var/python/lib/python3.6/site-packages/keras/utils/data_utils.py in get(self)
599 except Exception as e:
600 self.stop()
--> 601 six.reraise(*sys.exc_info())
602
603
~/var/python/lib/python3.6/site-packages/six.py in reraise(tp, value, tb)
691 if value.__traceback__ is not tb:
692 raise value.with_traceback(tb)
--> 693 raise value
694 finally:
695 value = None
~/var/python/lib/python3.6/site-packages/keras/utils/data_utils.py in get(self)
593 try:
594 while self.is_running():
--> 595 inputs = self.queue.get(block=True).get()
596 self.queue.task_done()
597 if inputs is not None:
~/var/python/lib/python3.6/multiprocessing/pool.py in get(self, timeout)
642 return self._value
643 else:
--> 644 raise self._value
645
646 def _set(self, i, obj):
~/var/python/lib/python3.6/multiprocessing/pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
117 job, i, func, args, kwds = task
118 try:
--> 119 result = (True, func(*args, **kwds))
120 except Exception as e:
121 if wrap_exception and func is not _helper_reraises_exception:
~/var/python/lib/python3.6/site-packages/keras/utils/data_utils.py in get_index(uid, i)
399 The value at index `i`.
400 """
--> 401 return _SHARED_SEQUENCES[uid][i]
402
403
~/var/python/lib/python3.6/site-packages/keras_preprocessing/image/iterator.py in __getitem__(self, idx)
63 index_array = self.index_array[self.batch_size * idx:
64 self.batch_size * (idx + 1)]
---> 65 return self._get_batches_of_transformed_samples(index_array)
66
67 def __len__(self):
~/var/python/lib/python3.6/site-packages/keras_preprocessing/image/iterator.py in _get_batches_of_transformed_samples(self, index_array)
233 params = self.image_data_generator.get_random_transform(x.shape)
234 x = self.image_data_generator.apply_transform(x, params)
--> 235 x = self.image_data_generator.standardize(x)
236 batch_x[i] = x
237 # optionally save augmented images to disk for debugging purposes
~/var/python/lib/python3.6/site-packages/keras_preprocessing/image/image_data_generator.py in standardize(self, x)
695 """
696 if self.preprocessing_function:
--> 697 x = self.preprocessing_function(x)
698 if self.rescale:
699 x *= self.rescale
<ipython-input-112-7bddefa5e731> in preprocess(im)
1 def preprocess(im):
----> 2 im = cv2.imread(im, 1)
3 im= cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
4 im=cv2.resize(im, (300,300))
5 im.resize(300, 300, 1)
TypeError: bad argument type for built-in operation
TypeError Traceback (most recent call last)
<ipython-input-126-30ceb84a2574> in <module>()
2
3 history = model.fit_generator(traingen, validation_data = validgen, epochs=100, steps_per_epoch=10,
----> 4 validation_steps=10, verbose=1, callbacks=[lr_reduction])
5
6
~/var/python/lib/python3.6/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~/var/python/lib/python3.6/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1416 use_multiprocessing=use_multiprocessing,
1417 shuffle=shuffle,
-> 1418 initial_epoch=initial_epoch)
1419
1420 #interfaces.legacy_generator_methods_support
~/var/python/lib/python3.6/site-packages/keras/engine/training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
179 batch_index = 0
180 while steps_done < steps_per_epoch:
--> 181 generator_output = next(output_generator)
182
183 if not hasattr(generator_output, '__len__'):
~/var/python/lib/python3.6/site-packages/keras/utils/data_utils.py in get(self)
599 except Exception as e:
600 self.stop()
--> 601 six.reraise(*sys.exc_info())
602
603
~/var/python/lib/python3.6/site-packages/six.py in reraise(tp, value, tb)
691 if value.__traceback__ is not tb:
692 raise value.with_traceback(tb)
--> 693 raise value
694 finally:
695 value = None
~/var/python/lib/python3.6/site-packages/keras/utils/data_utils.py in get(self)
593 try:
594 while self.is_running():
--> 595 inputs = self.queue.get(block=True).get()
596 self.queue.task_done()
597 if inputs is not None:
~/var/python/lib/python3.6/multiprocessing/pool.py in get(self, timeout)
642 return self._value
643 else:
--> 644 raise self._value
645
646 def _set(self, i, obj):
~/var/python/lib/python3.6/multiprocessing/pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
117 job, i, func, args, kwds = task
118 try:
--> 119 result = (True, func(*args, **kwds))
120 except Exception as e:
121 if wrap_exception and func is not _helper_reraises_exception:
~/var/python/lib/python3.6/site-packages/keras/utils/data_utils.py in get_index(uid, i)
399 The value at index `i`.
400 """
--> 401 return _SHARED_SEQUENCES[uid][i]
402
403
~/var/python/lib/python3.6/site-packages/keras_preprocessing/image/iterator.py in __getitem__(self, idx)
63 index_array = self.index_array[self.batch_size * idx:
64 self.batch_size * (idx + 1)]
---> 65 return self._get_batches_of_transformed_samples(index_array)
66
67 def __len__(self):
~/var/python/lib/python3.6/site-packages/keras_preprocessing/image/iterator.py in _get_batches_of_transformed_samples(self, index_array)
233 params = self.image_data_generator.get_random_transform(x.shape)
234 x = self.image_data_generator.apply_transform(x, params)
--> 235 x = self.image_data_generator.standardize(x)
236 batch_x[i] = x
237 # optionally save augmented images to disk for debugging purposes
~/var/python/lib/python3.6/site-packages/keras_preprocessing/image/image_data_generator.py in standardize(self, x)
695 """
696 if self.preprocessing_function:
--> 697 x = self.preprocessing_function(x)
698 if self.rescale:
699 x *= self.rescale
<ipython-input-112-7bddefa5e731> in preprocess(im)
1 def preprocess(im):
----> 2 im = cv2.imread(im, 1)
3 im= cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
4 im=cv2.resize(im, (300,300))
5 im.resize(300, 300, 1)
TypeError: bad argument type for built-in operation
TypeError Traceback (most recent call last)
<ipython-input-126-30ceb84a2574> in <module>()
2
3 history = model.fit_generator(traingen, validation_data = validgen, epochs=100, steps_per_epoch=10,
----> 4 validation_steps=10, verbose=1, callbacks=[lr_reduction])
5
6
~/var/python/lib/python3.6/site-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name + '` call to the ' +
90 'Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~/var/python/lib/python3.6/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
1416 use_multiprocessing=use_multiprocessing,
1417 shuffle=shuffle,
-> 1418 initial_epoch=initial_epoch)
1419
1420 #interfaces.legacy_generator_methods_support
~/var/python/lib/python3.6/site-packages/keras/engine/training_generator.py in fit_generator(model, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
179 batch_index = 0
180 while steps_done < steps_per_epoch:
--> 181 generator_output = next(output_generator)
182
183 if not hasattr(generator_output, '__len__'):
~/var/python/lib/python3.6/site-packages/keras/utils/data_utils.py in get(self)
599 except Exception as e:
600 self.stop()
--> 601 six.reraise(*sys.exc_info())
602
603
~/var/python/lib/python3.6/site-packages/six.py in reraise(tp, value, tb)
691 if value.__traceback__ is not tb:
692 raise value.with_traceback(tb)
--> 693 raise value
694 finally:
695 value = None
~/var/python/lib/python3.6/site-packages/keras/utils/data_utils.py in get(self)
593 try:
594 while self.is_running():
--> 595 inputs = self.queue.get(block=True).get()
596 self.queue.task_done()
597 if inputs is not None:
~/var/python/lib/python3.6/multiprocessing/pool.py in get(self, timeout)
642 return self._value
643 else:
--> 644 raise self._value
645
646 def _set(self, i, obj):
~/var/python/lib/python3.6/multiprocessing/pool.py in worker(inqueue, outqueue, initializer, initargs, maxtasks, wrap_exception)
117 job, i, func, args, kwds = task
118 try:
--> 119 result = (True, func(*args, **kwds))
120 except Exception as e:
121 if wrap_exception and func is not _helper_reraises_exception:
~/var/python/lib/python3.6/site-packages/keras/utils/data_utils.py in get_index(uid, i)
399 The value at index `i`.
400 """
--> 401 return _SHARED_SEQUENCES[uid][i]
402
403
~/var/python/lib/python3.6/site-packages/keras_preprocessing/image/iterator.py in __getitem__(self, idx)
63 index_array = self.index_array[self.batch_size * idx:
64 self.batch_size * (idx + 1)]
---> 65 return self._get_batches_of_transformed_samples(index_array)
66
67 def __len__(self):
~/var/python/lib/python3.6/site-packages/keras_preprocessing/image/iterator.py in _get_batches_of_transformed_samples(self, index_array)
233 params = self.image_data_generator.get_random_transform(x.shape)
234 x = self.image_data_generator.apply_transform(x, params)
--> 235 x = self.image_data_generator.standardize(x)
236 batch_x[i] = x
237 # optionally save augmented images to disk for debugging purposes
~/var/python/lib/python3.6/site-packages/keras_preprocessing/image/image_data_generator.py in standardize(self, x)
695 """
696 if self.preprocessing_function:
--> 697 x = self.preprocessing_function(x)
698 if self.rescale:
699 x *= self.rescale
<ipython-input-112-7bddefa5e731> in preprocess(im)
1 def preprocess(im):
----> 2 im = cv2.imread(im, 1)
3 im= cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
4 im=cv2.resize(im, (300,300))
5 im.resize(300, 300, 1)
TypeError: bad argument type for built-in operation
I have also thought about preprocessing the images and saving them to a folder then I'll load them from that folder to a dataframe, but it's computationally expensive and time consuming.

I ran into a problem like yours and my teacher helped me by pointing it to the docs of the tf preprocess_function, it said the preprocess_function argument is an image, you can read more on this.
That is why it gives you the error at cv2.imread(image). You should remove that line because im is an image that the generator gives you. There no need to load it because it's already loaded
My one work well, hope yours will be fine too.

I think the issue was with Keras parsing the openCV output, Because it ran well when i used another library to perform the processing called ImgAUg. Here's the link. https://pypi.org/project/imgaug/.
So i just scripted a preprocessing function with the library, and then i passed it into the keras imageDataGenerator class. It ran fine and didn't throw any error at me.