When trying to run
import numpy as np
import keras
X = np.ones((100,20))
Y1 = np.ones((100,5))
Y2 = np.ones((100,4))
Input_1= keras.layers.Input(shape=X.shape[1])
x = keras.layers.Dense(100)(Input_1)
x = keras.layers.Dense(100)(x)
out1 = keras.layers.Dense(5, kernel_regularizer='l1')(x)
out2 = keras.layers.Dense(4)(x)
model = keras.models.Model(inputs=Input_1, outputs=[out1,out2])
model.compile(loss = 'mse', loss_weights=np.arange(2))
model.fit(X, [Y1, Y2], epochs=2)
I get
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:805
train_function *
return step_function(self, iterator)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:795
step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.6/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/python3.6/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/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417
_call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:788
run_step **
outputs = model.train_step(data)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:756
train_step
y, y_pred, sample_weight, regularization_losses=self.losses)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:236
call
total_loss_metric_value = math_ops.add_n(loss_metric_values)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201
wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py:3572
add_n
return gen_math_ops.add_n(inputs, name=name)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_math_ops.py:419
add_n
"AddN", inputs=inputs, name=name)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py:750
_apply_op_helper
attrs=attr_protos, op_def=op_def)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py:592
_create_op_internal
compute_device)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py:3536
_create_op_internal
op_def=op_def)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py:2016
init
control_input_ops, op_def)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py:1856
_create_c_op
raise ValueError(str(e))
ValueError: Shapes must be equal rank, but are 1 and 0
From merging shape 1 with other shapes. for '{{node AddN}} = AddN[N=3, T=DT_FLOAT](mul_2, mul_5, dense_199/kernel/Regularizer/mul)' with input shapes: [2], [2], [].
The error disappears if I omit the regularizer.
I found that loss_weights has to be a list, not an array.
import numpy as np
import keras
X = np.ones((100,20))
Y1 = np.ones((100,5))
Y2 = np.ones((100,4))
Input_1= keras.layers.Input(shape=X.shape[1])
x = keras.layers.Dense(100)(Input_1)
x = keras.layers.Dense(100)(x)
out1 = keras.layers.Dense(5, kernel_regularizer='l1')(x)
out2 = keras.layers.Dense(4)(x)
model = keras.models.Model(inputs=Input_1, outputs=[out1,out2])
model.compile(loss = 'mse', loss_weights=list(np.arange(2)))
model.fit(X, [Y1, Y2], epochs=2)
I was facing the same issue.
changing the reduction of loss function from none to auto worked like a charm.
tf.keras.losses.MeanSquaredError(reduction=tf.keras.losses.Reduction.AUTO)
Related
This is the model that I am trying to train for identifying possible tag(out of three tags) for each word, also I have added a layer from another model whose output shape is [1, 100]tensors and then I have concatenate it with BiLSTM output-
input1_entity = Input(shape = (200,))
last_hidden_layer_output = last_hidden_layer(tensorflow.reshape(input1_entity, [1, 200]))
embedding_entity = Embedding((4817), 200, input_length = 200, weights = [embedding_matrix], trainable = False)(input1_entity)
bilstm1_entity = Bidirectional(LSTM(100, return_sequences = True, recurrent_dropout = 0.2), merge_mode = 'concat')(embedding_entity)
lstm1_entity = Bidirectional(LSTM(100, return_sequences = True, dropout = 0.5, recurrent_dropout = 0.2))(bilstm1_entity)
lstm2_entity = Bidirectional(LSTM(50))(lstm1_entity)
merge_layer = concatenate([lstm2_entity, last_hidden_layer_output])
dense1_entity = Dense(128, activation = 'relu')(merge_layer)
dense2_entity = Dense(128, activation = 'relu')(dense1_entity)
dropout1_entity = Dropout(0.5)(dense2_entity)
dense3_entity = Dense(64, activation = 'tanh')(dropout1_entity)
output1_entity = Dense(3, activation = 'softmax')(dense3_entity)
model_entity = Model(inputs = input1_entity, outputs = output1_entity)
model_entity.compile(
loss = 'categorical_crossentropy',
optimizer = 'adam',
metrics = [tensorflow.keras.metrics.CategoricalAccuracy()],
sample_weight_mode = 'temporal'
)
And this is how I am training the model -
history = model_entity.fit(pad_tokens_train,
np.array(pad_tags_train),
batch_size=250,
verbose=1,
epochs=50,
sample_weight = sample_weight,
validation_split=0.2)
But I keep on getting this error -
ValueError: in user code:
File "/Users/kawaii/miniforge3/envs/tensor_no_gpu/lib/python3.8/site-packages/keras/engine/training.py", line 878, in train_function *
return step_function(self, iterator)
File "/Users/kawaii/miniforge3/envs/tensor_no_gpu/lib/python3.8/site-packages/keras/engine/training.py", line 867, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/Users/kawaii/miniforge3/envs/tensor_no_gpu/lib/python3.8/site-packages/keras/engine/training.py", line 860, in run_step **
outputs = model.train_step(data)
File "/Users/kawaii/miniforge3/envs/tensor_no_gpu/lib/python3.8/site-packages/keras/engine/training.py", line 809, in train_step
loss = self.compiled_loss(
File "/Users/kawaii/miniforge3/envs/tensor_no_gpu/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 201, in __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
File "/Users/kawaii/miniforge3/envs/tensor_no_gpu/lib/python3.8/site-packages/keras/losses.py", line 141, in __call__
losses = call_fn(y_true, y_pred)
File "/Users/kawaii/miniforge3/envs/tensor_no_gpu/lib/python3.8/site-packages/keras/losses.py", line 245, in call **
return ag_fn(y_true, y_pred, **self._fn_kwargs)
File "/Users/kawaii/miniforge3/envs/tensor_no_gpu/lib/python3.8/site-packages/keras/losses.py", line 1664, in categorical_crossentropy
return backend.categorical_crossentropy(
File "/Users/kawaii/miniforge3/envs/tensor_no_gpu/lib/python3.8/site-packages/keras/backend.py", line 4994, in categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
ValueError: Shapes (None, 200, 3) and (1, 3) are incompatible
I'm trying to use tf.data.Dataset.list_files to load .tiff images and infer their labels from their names.
I use the following code but stumbled upon a strange issue, as described bellow:
import os
import datetime as dt
import numpy as np
import pathlib
from pathlib import Path
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import cv2
DATA_PATH = Path('PATH TO DATA')
BATCH_SIZE = 32
INPUT_IMAGE_SHAPE = (128, 128, 1)
CROP_SHAPE = INPUT_IMAGE_SHAPE
CENTRAL_CROP_PROP = .7
BRIGHTNESS_DELTA = 0.1
CONTRAST = (0.4, 0.6)
class ConvModel(keras.Model):
def __init__(self, input_shape):
super().__init__()
self.input_image_shape = input_shape
self.model = keras.Sequential([
layers.Input(shape=input_shape),
layers.Conv2D(32, 3),
layers.BatchNormalization(),
layers.ReLU(),
layers.MaxPool2D(),
layers.Conv2D(64, 5),
layers.BatchNormalization(),
layers.ReLU(),
layers.MaxPool2D(),
layers.Conv2D(128, 3, kernel_regularizer=keras.regularizers.l2(0.01)),
layers.BatchNormalization(),
layers.ReLU(),
layers.Flatten(),
layers.Dense(64, activation='relu', kernel_regularizer=keras.regularizers.l2(0.01)),
layers.Dropout(0.5),
layers.Dense(10)
])
def call(self, inputs):
return self.model(inputs)
def preprocessing_func(image):
img = tf.image.central_crop(image, CENTRAL_CROP_PROP)
if img.shape[2] == 3:
img = tf.image.rgb_to_grayscale(img)
return img
def augment(image):
img = tf.image.random_crop(image, size=CROP_SHAPE) # Slices a shape size portion out of value at a uniformly chosen offset. Requires value.shape >= size.
img = tf.image.random_brightness(img, max_delta=BRIGHTNESS_DELTA) # Equivalent to adjust_brightness() using a delta randomly picked in the interval [-max_delta, max_delta)
img = tf.image.random_contrast(img, lower=CONTRAST[0], upper=CONTRAST[1]) # Equivalent to adjust_contrast() but uses a contrast_factor randomly picked in the interval [lower, upper).
img = tf.image.random_flip_left_right(img)
img = tf.image.random_flip_up_down(img)
return img
def load_image(image_file):
# 1) Decode the path
image_file = image_file.decode('utf-8')
# 2) Read the image
img = cv2.imread(image_file)
if len(img.shape) < 3:
img = np.expand_dims(img, axis=-1)
img = preprocessing_func(image=img)
img = augment(img)
img = tf.cast(img, tf.float32)
img.set_shape(INPUT_IMAGE_SHAPE)
# 3) Get the label
label = tf.strings.split(image_file, "\\")[-1]
label = tf.strings.substr(label, pos=0, len=1)
label = tf.strings.to_number(label, out_type=tf.float32)
label = tf.cast(label, tf.float32)
label.set_shape([])
return img, label
def _fixup_shape(images, labels):
images.set_shape(INPUT_IMAGE_SHAPE)
labels.set_shape([])
return images, labels
if __name__=='__main__':
train_ds = tf.data.Dataset.list_files(str(DATA_PATH / '*.tiff'))
train_ds = train_ds.map(lambda x: tf.numpy_function(load_image, [x], (tf.float32, tf.float32)))
# train_ds = train_ds.map(_fixup_shape)
train_ds = train_ds.batch(BATCH_SIZE)
train_ds = train_ds.shuffle(buffer_size=1000)
train_ds = train_ds.prefetch(tf.data.AUTOTUNE)
train_ds = train_ds.repeat()
model = ConvModel(input_shape=INPUT_IMAGE_SHAPE)
model.compile(
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer=keras.optimizers.Adam(learning_rate=3e-4),
metrics=['accuracy']
)
train_log_dir = f'./logs/{dt.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")}/train_data'
callbacks = [
keras.callbacks.TensorBoard(
log_dir=train_log_dir,
write_images=True
)
]
model.fit(
train_ds,
batch_size=32,
steps_per_epoch=10,
epochs=10,
callbacks=callbacks
)
While I try to run it it throws up an error :
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-213-b1f3d317135b> in <module>
----> 1 model.fit(
2 train_ds,
3 batch_size=32,
4 steps_per_epoch=10,
5 epochs=10,
~\anaconda3\lib\site-packages\keras\utils\traceback_utils.py in error_handler(*args, **kwargs)
65 except Exception as e: # pylint: disable=broad-except
66 filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67 raise e.with_traceback(filtered_tb) from None
68 finally:
69 del filtered_tb
~\anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in autograph_handler(*args, **kwargs)
1127 except Exception as e: # pylint:disable=broad-except
1128 if hasattr(e, "ag_error_metadata"):
-> 1129 raise e.ag_error_metadata.to_exception(e)
1130 else:
1131 raise
ValueError: in user code:
File "C:\Users\mchls\anaconda3\lib\site-packages\keras\engine\training.py", line 878, in train_function *
return step_function(self, iterator)
File "C:\Users\mchls\anaconda3\lib\site-packages\keras\engine\training.py", line 867, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:\Users\mchls\anaconda3\lib\site-packages\keras\engine\training.py", line 860, in run_step **
outputs = model.train_step(data)
File "C:\Users\mchls\anaconda3\lib\site-packages\keras\engine\training.py", line 817, in train_step
self.compiled_metrics.update_state(y, y_pred, sample_weight)
File "C:\Users\mchls\anaconda3\lib\site-packages\keras\engine\compile_utils.py", line 439, in update_state
self.build(y_pred, y_true)
File "C:\Users\mchls\anaconda3\lib\site-packages\keras\engine\compile_utils.py", line 359, in build
self._metrics = tf.__internal__.nest.map_structure_up_to(y_pred, self._get_metric_objects,
File "C:\Users\mchls\anaconda3\lib\site-packages\keras\engine\compile_utils.py", line 485, in _get_metric_objects
return [self._get_metric_object(m, y_t, y_p) for m in metrics]
File "C:\Users\mchls\anaconda3\lib\site-packages\keras\engine\compile_utils.py", line 485, in <listcomp>
return [self._get_metric_object(m, y_t, y_p) for m in metrics]
File "C:\Users\mchls\anaconda3\lib\site-packages\keras\engine\compile_utils.py", line 506, in _get_metric_object
y_t_rank = len(y_t.shape.as_list())
ValueError: as_list() is not defined on an unknown TensorShape.
though manually running X.shape.as_list() and y.shape.as_list() works, as shown below:
X, y = next(iter(train_ds))
X.shape.as_list(), y.shape.as_list()
[OUT] ([16, 128, 128, 1], [16])
This issue is fixed, as described in this GitHub thread and in this answer, by manually mapping the following function on the dataset by train_ds = train_ds.map(_fixup_shape).batch(BATCH_SIZE):
def _fixup_shape(images, labels):
images.set_shape([128, 128, 1])
labels.set_shape([]) # I have 19 classes
# weights.set_shape([None])
return images, labels
if __name__=='__main__':
train_ds = tf.data.Dataset.list_files(str(DATA_PATH / '*.tiff'))
train_ds = train_ds.map(lambda x: tf.numpy_function(load_image, [x], (tf.float32, tf.float32)))
train_ds = train_ds.map(_fixup_shape)
train_ds = train_ds.batch(BATCH_SIZE)
train_ds = train_ds.shuffle(buffer_size=1000)
train_ds = train_ds.prefetch(tf.data.AUTOTUNE)
train_ds = train_ds.repeat()
but I can't figure out why is the _fixup_shape is needed in the first place, as I do state the shape inside the load_image function.
Is it a bug in TF 2.6.1 or is it an expected behavior?
Thanks
I am trying to implement a conditional autoencoder, which is really very straightforward, and getting errors while making the fit function work. Here is the full code snippet
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
class Sampling(layers.Layer):
"""Uses (z_mean, z_log_var) to sample z, the vector encoding a digit."""
def call(self, inputs):
z_mean, z_log_var = inputs
batch = tf.shape(z_mean)[0]
dim = tf.shape(z_mean)[1]
epsilon = tf.keras.backend.random_normal(shape=(batch, dim))
return z_mean + tf.exp(0.5 * z_log_var) * epsilon
class cVAE(keras.Model):
def __init__(self,
original_dim,
label_dim,
latent_dim,
beta=1,
batch_size=1,
**kwargs):
super(cVAE, self).__init__(**kwargs)
self.original_dim = original_dim
self.latent_dim = latent_dim
self.label_dim = label_dim
self.beta = beta
self.batch_size = batch_size
# Build the encoder
print("building encoder")
rnaseq_inputs = keras.Input(shape=(self.original_dim, ),batch_size=self.batch_size)
label_inputs = keras.Input(shape=(self.label_dim, ),batch_size=self.batch_size)
encoder_inputs = layers.concatenate([rnaseq_inputs, label_inputs], name='concat_1')
z_mean = layers.Dense(self.latent_dim,
kernel_initializer = 'glorot_uniform')(encoder_inputs)
z_mean = layers.BatchNormalization()(z_mean)
z_mean = layers.Activation('relu')(z_mean)
z_log_var = layers.Dense(self.latent_dim,
kernel_initializer = 'glorot_uniform')(encoder_inputs)
z_log_var = layers.BatchNormalization()(z_log_var)
z_log_var = layers.Activation('relu')(z_log_var)
z = Sampling()([z_mean, z_log_var])
zc = layers.concatenate([z, label_inputs],name='concat_2')
self.encoder = keras.Model([rnaseq_inputs, label_inputs], [z_mean, z_log_var, z, zc])
print("building decoder")
# Build the decoder
decoder_input_dim = self.latent_dim + self.label_dim
decoder_output_dim = self.original_dim + self.label_dim
decoder_inputs = keras.Input(shape=(decoder_input_dim, ))
decoder_outputs = keras.layers.Dense(decoder_output_dim,
activation='sigmoid')(decoder_inputs)
self.decoder = keras.Model(decoder_inputs, decoder_outputs)
self.total_loss_tracker = keras.metrics.Mean(name="total_loss")
self.reconstruction_loss_tracker = keras.metrics.Mean(
name="reconstruction_loss"
)
self.kl_loss_tracker = keras.metrics.Mean(name="kl_loss")
#property
def metrics(self):
return [
self.total_loss_tracker,
self.reconstruction_loss_tracker,
self.kl_loss_tracker,
]
def train_step(self, data):
with tf.GradientTape() as tape:
# exp_data, label_data = data
z_mean, z_log_var, z, zc = self.encoder(data)
reconstruction = self.decoder(zc)
reconstruction_loss = tf.reduce_mean(
tf.reduce_sum(
keras.losses.mean_squared_error(data, reconstruction)
)
)
kl_loss = -0.5 * (1 + z_log_var - tf.square(z_mean) - tf.exp(z_log_var))
kl_loss = tf.reduce_mean(tf.reduce_sum(kl_loss, axis=1))
total_loss = reconstruction_loss + kl_loss
grads = tape.gradient(total_loss, self.trainable_weights)
self.optimizer.apply_gradients(zip(grads, self.trainable_weights))
self.total_loss_tracker.update_state(total_loss)
self.reconstruction_loss_tracker.update_state(reconstruction_loss)
self.kl_loss_tracker.update_state(kl_loss)
return {
"loss": self.total_loss_tracker.result(),
"reconstruction_loss": self.reconstruction_loss_tracker.result(),
"kl_loss": self.kl_loss_tracker.result(),
}
toy_data = np.random.random((100,100)).astype('float32')
label = np.random.randint(0,high=2,size=100).reshape(100,1).astype('float32')
cvae_model = cVAE(original_dim=100,batch_size=2,label_dim=1,latent_dim=1)
cvae_model.compile(optimizer=keras.optimizers.Adam(learning_rate=0.003))
# fitting
cvae_model.fit([toy_data,label])
Up until fit function everything worked. To my surprise the fit function gives the following error,
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)
<ipython-input-232-1cc639e2055c>:182 train_step
keras.losses.mean_squared_error(data, reconstruction)
/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:1197 mean_squared_error
y_true = math_ops.cast(y_true, y_pred.dtype)
/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/ops/math_ops.py:964 cast
x = ops.convert_to_tensor(x, name="x")
/usr/local/lib/python3.7/dist-packages/tensorflow/python/profiler/trace.py:163 wrapped
return func(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py:1540 convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/array_ops.py:1525 _autopacking_conversion_function
return _autopacking_helper(v, dtype, name or "packed")
/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/array_ops.py:1444 _autopacking_helper
converted_elem = _autopacking_helper(elem, dtype, str(i))
/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/array_ops.py:1461 _autopacking_helper
return gen_array_ops.pack(elems_as_tensors, name=scope)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/gen_array_ops.py:6398 pack
"Pack", values=values, axis=axis, 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:592 _create_op_internal
compute_device)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py:3536 _create_op_internal
op_def=op_def)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py:2016 __init__
control_input_ops, op_def)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py:1856 _create_c_op
raise ValueError(str(e))
ValueError: Dimension 1 in both shapes must be equal, but are 100 and 1. Shapes are [2,100] and [2,1].
From merging shape 0 with other shapes. for '{{node Cast/x/0}} = Pack[N=2, T=DT_FLOAT, axis=0](IteratorGetNext, IteratorGetNext:1)' with input shapes: [2,100], [2,1].
I don't understand why it can't merge [2,100] and [2,1] on axis 1 it should produce [2,101], am I getting it wrong?
Here is what plot_model yields for encoder
PS: I tried to play with the axis of concatenation and none of the values worked.
The problem was in reconstruction, it got solved by the following concatenation in the train step
def train_step(self, data):
with tf.GradientTape() as tape:
# exp_data, label_data = data
z_mean, z_log_var, z, zc = self.encoder(data)
#form_data = np.concatenate(data)
reconstruction = self.decoder(zc)
data_cat = layers.concatenate([data[0][0],data[0][1]], axis=1)
reconstruction_loss = tf.reduce_mean(
tf.reduce_sum(
keras.losses.mean_squared_error(data_cat, reconstruction)
)
)
kl_loss = -0.5 * (1 + z_log_var - tf.square(z_mean) - tf.exp(z_log_var))
kl_loss = tf.reduce_mean(tf.reduce_sum(kl_loss, axis=1))
total_loss = reconstruction_loss + kl_loss
grads = tape.gradient(total_loss, self.trainable_weights)
self.optimizer.apply_gradients(zip(grads, self.trainable_weights))
self.total_loss_tracker.update_state(total_loss)
self.reconstruction_loss_tracker.update_state(reconstruction_loss)
self.kl_loss_tracker.update_state(kl_loss)
return {
"loss": self.total_loss_tracker.result(),
"reconstruction_loss": self.reconstruction_loss_tracker.result(),
"kl_loss": self.kl_loss_tracker.result(),
}
I have a multi-class classifier, that takes inputs from a generator:
def generate_train_data(path, x_shape):
genres = {"hip-hop":0, "r&b":1, "pop":2, "jazz":3}
genre_labels = to_categorical(list(genres.values()), num_classes=len(genres))
# some processing to create variables x and genre...
# (mock values)
x = np.zeros(x_shape)
x = x[None, :, :, :]
genre = "hip-hop"
yield (x, genre_labels[genres[genre]])
The classifier is defined below:
input_shape = (96, 84, 5)
i = Input(shape=input_shape, name='encoder_input')
cx = Conv2D(filters=8, kernel_size=3, strides=2, padding='same', activation='relu')(i)
cx = BatchNormalization()(cx)
cx = Conv2D(filters=16, kernel_size=3, strides=2, padding='same', activation='relu')(cx)
cx = BatchNormalization()(cx)
x = Flatten()(cx)
x = Dense(20, activation='relu')(x)
x = BatchNormalization()(x)
x = Dense(4, activation='softmax')(x)
classifier = Model(i, x, name='genre_classifier')
classifier.summary()
classifier.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
However, when I try to fit the classifier:
classifier.fit(generate_train_data(path, input_shape), epochs=30, validation_data=generate_test_data(path, input_shape), verbose=verbosity)
I get the following error:
ValueError: in user code:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:806 train_function *
return step_function(self, iterator)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:796 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1211 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:2585 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:2945 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:789 run_step **
outputs = model.train_step(data)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:749 train_step
y, y_pred, sample_weight, regularization_losses=self.losses)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:204 __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:149 __call__
losses = ag_call(y_true, y_pred)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:253 call **
return ag_fn(y_true, y_pred, **self._fn_kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1535 categorical_crossentropy
return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py:4687 categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
/usr/local/lib/python3.6/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, 4) are incompatible
The class label value returned by the generators is an array of length 4 so why is keras suggesting it is of size 1?
NOTE: This code is being run on Colab, tensorflow version 2.3. A mock version that reprocuces this error can be found on this Colab link: https://colab.research.google.com/drive/1SQZFspj3UOwP2ApIiaI2lvB2Z59bdVOk?usp=sharing
EDIT: added mock values in generate_train_data so that code can be reproducible
You need to add a dimension for batch_size for both x and y. In your generator, add a None-dimension by changing: genre_labels[genres[genre]] to genre_labels[genres[genre]][None, :].
The ouput of the one-hot encoding needed to be packed into a small 1 batch to fit [None,4] this is done by np.asarray([]).
Use
yield (x, np.asarray([genre_labels[genres[genre], :]]))
instead of:
yield (x, genre_labels[genres[genre]])
Traceback:
model = Model(input_tensor,x,name = 'vgg16_trunk')
File "/usr/local/lib/python3.6/dist-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 93, in __init__
self._init_graph_network(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 231, in _init_graph_network
self.inputs, self.outputs)
File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 1443, in _map_graph_network
str(layers_with_complete_input))
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_2:0", shape=(?, 32, 32, 3), dtype=float32) at layer "input_2". The following previous layers were accessed without issue: []
How to solve this problem in vgg16 ??
def create_model(input_shape):
channel_axis = 1 if K.image_data_format() == "channels_first" else -1
input_tensor = Input(shape=input_shape)
base_model = VGG16(classes=10,input_tensor=None,input_shape=input_shape,include_top=False)
x = base_model.output
x = BatchNormalization(axis=channel_axis, momentum=mom,
epsilon=eps, gamma_initializer=gamma)(x)
x = LeakyReLU(leakiness)(x)
model = Model(input_tensor,x,name = 'vgg16_trunk')
return model
Pass the input_tensor you created here:
input_tensor = Input(shape=input_shape)
where base_model is created:
base_model = VGG16(classes=10,input_tensor=input_tensor,include_top=False)
Please note also, that the tensor will already have the input_shape so it's not necessary to give it as parameter again when creating the base_model.