İ am working on an image dataset that is categorical 12 classes. İ am using transfer learning with VGG16. However, İ have faced an error: Shapes (None, None) and (None, 28, 28, 12) are incompatible.
My code:
IMAGE_SHAPE = (224, 224)
BATCH_SIZE = 32
train = ImageDataGenerator()
train_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale= 1./255, fill_mode= 'nearest')
train_data = train_generator.flow_from_directory(directory="path",target_size=IMAGE_SHAPE , color_mode="rgb" , class_mode='categorical', batch_size=BATCH_SIZE , shuffle = True )
valid = ImageDataGenerator()
validation_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)
valid_data = validation_generator.flow_from_directory(directory="path, target_size=IMAGE_SHAPE , color_mode="rgb" , class_mode='categorical' , batch_size=BATCH_SIZE , shuffle = True )
test = ImageDataGenerator()
test_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)
test_data = test_generator.flow_from_directory(directory='path',target_size=IMAGE_SHAPE , color_mode="rgb" , class_mode='categorical' , batch_size=1 , shuffle = False )
test_data.reset()
from keras.applications.vgg19 import VGG19
vggmodel = VGG19(weights='imagenet', include_top=True)
for layers in (vggmodel.layers)[:32]:
print(layers)
layers.trainable = False
import tensorflow as tf
tf.keras.Model
tf.keras.layers.Dense
from keras import optimizers
tf.keras.preprocessing.image.ImageDataGenerator
tf.keras.preprocessing.image.load_img
X= vggmodel.layers[-12].output
flatten = tf.keras.layers.Flatten()(X)
out = vggmodel.layers(flatten)
predictions = tf.keras.layers.Dense(num_classes, activation='softmax')
model_final = Model(vggmodel.input, predictions)
model_final.compile(optimizer = optimizers.Adam(lr=0.0003), loss='categorical_crossentropy', metrics=["accuracy"])
for image_batch, labels_batch in train_data:
print(image_batch.shape)
print(labels_batch.shape)
break
from keras.callbacks import ModelCheckpoint, EarlyStopping
checkpoint = ModelCheckpoint("vgg16_1.h5", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
early = EarlyStopping(monitor='val_acc',patience=40, verbose=1, mode='auto')
model_final.fit_generator(generator= train_data, steps_per_epoch= 2, epochs= 100, validation_data= valid_data, validation_steps=1, callbacks=[checkpoint,early])
model_final.save_weights("vgg16_1.h5")
Error: ValueError: Shapes (None, None) and (None, 28, 28, 12) are incompatible[![enter image description here]
Error details:
ValueError Traceback (most recent call last)
<ipython-input-39-938295cc34c4> in <module>()
2 checkpoint = ModelCheckpoint("vgg16_1.h5", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
3 early = EarlyStopping(monitor='val_acc', min_delta=0, patience=40, verbose=1, mode='auto')
----> 4 model_final.fit_generator(generator= train_images , steps_per_epoch= 2, epochs= 100, validation_data= val_images , validation_steps=1, callbacks=[checkpoint,early])
5 model_final.save_weights("vgg16_1.h5")
10 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
984 except Exception as e: # pylint:disable=broad-except
985 if hasattr(e, "ag_error_metadata"):
--> 986 raise e.ag_error_metadata.to_exception(e)
987 else:
988 raise
ValueError: in user code:
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:830 train_function *
return step_function(self, iterator)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:813 run_step *
outputs = model.train_step(data)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:771 train_step *
loss = self.compiled_loss(
/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py:201 __call__ *
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/usr/local/lib/python3.7/dist-packages/keras/losses.py:142 __call__ *
losses = call_fn(y_true, y_pred)
/usr/local/lib/python3.7/dist-packages/keras/losses.py:246 call *
return ag_fn(y_true, y_pred, **self._fn_kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:206 wrapper **
return target(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/keras/losses.py:1631 categorical_crossentropy
y_true, y_pred, from_logits=from_logits)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:206 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/keras/backend.py:4827 categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/tensor_shape.py:1161 assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (None, None) and (None, 28, 28, 12) are incompatible
1]1
Updated Code:
image_dir = Path('../content/dataset')
# Get filepaths and labels
filepaths = list(image_dir.glob(r'**/*.png'))
labels = list(map(lambda x: os.path.split(os.path.split(x)[0])[1], filepaths))
def create_gen():
# Load the Images with a generator and Data Augmentation
train_generator = tf.keras.preprocessing.image.ImageDataGenerator(
preprocessing_function=tf.keras.applications.vgg16.preprocess_input,
validation_split=0.1
)
test_generator = tf.keras.preprocessing.image.ImageDataGenerator(
preprocessing_function=tf.keras.applications.vgg16.preprocess_input
)
train_images = train_generator.flow_from_dataframe(
dataframe=train_df,
x_col='Filepath',
y_col='Label',
target_size=(224, 224),
color_mode='rgb',
class_mode='categorical',
batch_size=32,
shuffle=True,
seed=0,
subset='training',
rotation_range=30, # Uncomment to use data augmentation
zoom_range=0.15,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.15,
horizontal_flip=True,
fill_mode="nearest"
)
val_images = train_generator.flow_from_dataframe(
dataframe=train_df,
x_col='Filepath',
y_col='Label',
target_size=(224, 224),
color_mode='rgb',
class_mode='categorical',
batch_size=32,
shuffle=True,
seed=0,
subset='validation',
rotation_range=30, # Uncomment to use data augmentation
zoom_range=0.15,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.15,
horizontal_flip=True,
fill_mode="nearest"
)
test_images = test_generator.flow_from_dataframe(
dataframe=test_df,
x_col='Filepath',
y_col='Label',
target_size=(224, 224),
color_mode='rgb',
class_mode='categorical',
batch_size=32,
shuffle=False
)
return train_generator,test_generator,train_images,val_images,test_images
from keras.applications.vgg16 import VGG16
vggmodel = VGG16(weights='imagenet', include_top=True)
for layers in (vggmodel.layers)[:256]:
print(layers)
layers.trainable = False
X= vggmodel.layers[-12].output
predictions = Dense(12, activation="softmax")(X)
model_final = Model(vggmodel.input, predictions)
model_final.compile(optimizer = optimizers.Adam(lr=0.0003), loss='categorical_crossentropy', metrics=["accuracy"])
# Separate in train and test data
train_df, test_df = train_test_split(image_df, train_size=0.9, shuffle=True, random_state=1)
# Create the generators
train_generator,test_generator,train_images,val_images,test_images = create_gen()
from keras.callbacks import ModelCheckpoint, EarlyStopping
checkpoint = ModelCheckpoint("vgg16_1.h5", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
early = EarlyStopping(monitor='val_acc', min_delta=0, patience=40, verbose=1, mode='auto')
model_final.fit_generator(generator= train_images, steps_per_epoch= 2, epochs= 100, validation_data= val_images, validation_steps=1, callbacks=[checkpoint,early])
model_final.save_weights("vgg16_1.h5")
Details error:
valueError Traceback (most recent call last)
<ipython-input-56-5210d7f2da32> in <module>()
2 checkpoint = ModelCheckpoint("vgg16_1.h5", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
3 early = EarlyStopping(monitor='val_acc', min_delta=0, patience=40, verbose=1, mode='auto')
----> 4 model_final.fit_generator(generator= train_images, steps_per_epoch= 2, epochs= 100, validation_data= val_images, validation_steps=1, callbacks=[checkpoint,early])
5 model_final.save_weights("vgg16_1.h5")
10 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
984 except Exception as e: # pylint:disable=broad-except
985 if hasattr(e, "ag_error_metadata"):
--> 986 raise e.ag_error_metadata.to_exception(e)
987 else:
988 raise
ValueError: in user code:
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:830 train_function *
return step_function(self, iterator)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:813 run_step *
outputs = model.train_step(data)
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py:771 train_step *
loss = self.compiled_loss(
/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py:201 __call__ *
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/usr/local/lib/python3.7/dist-packages/keras/losses.py:142 __call__ *
losses = call_fn(y_true, y_pred)
/usr/local/lib/python3.7/dist-packages/keras/losses.py:246 call *
return ag_fn(y_true, y_pred, **self._fn_kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:206 wrapper **
return target(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/keras/losses.py:1631 categorical_crossentropy
y_true, y_pred, from_logits=from_logits)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/dispatch.py:206 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/keras/backend.py:4827 categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/tensor_shape.py:1161 assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (None, None) and (None, 28, 28, 12) are incompatible
There are many small errros in your code:
You are using string path instead of variable path while using generators.
Also train path, validation path and test path should be different.
You have not specified input_tensor for VGG19 model.
Your piece of code should be like this:
#train_dir_path is path to your training images
train_data = train_generator.flow_from_directory(directory=train_dir_path,target_size=IMAGE_SHAPE , color_mode="rgb" , class_mode='categorical', batch_size=BATCH_SIZE , shuffle = True )
#valid_dir_path is path to your validation images
valid_data = validation_generator.flow_from_directory(directory=valid_dir_path, target_size=IMAGE_SHAPE , color_mode="rgb" , class_mode='categorical' , batch_size=BATCH_SIZE , shuffle = True )
The output of VGG model should be flatten before passing to Dense layer
Full code:
IMAGE_SHAPE = (224, 224)
BATCH_SIZE = 32
train = ImageDataGenerator()
train_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale= 1./255, fill_mode= 'nearest')
#train_dir_path is path to your training images
train_data = train_generator.flow_from_directory(directory=train_dir_path,target_size=IMAGE_SHAPE , color_mode="rgb" , class_mode='categorical', batch_size=BATCH_SIZE , shuffle = True )
valid = ImageDataGenerator()
validation_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)
#valid_dir_path is path to your validation images
valid_data = validation_generator.flow_from_directory(directory=valid_dir_path, target_size=IMAGE_SHAPE , color_mode="rgb" , class_mode='categorical' , batch_size=BATCH_SIZE , shuffle = True )
test = ImageDataGenerator()
test_generator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)
#test_dir_path is path to your test images
test_data = test_generator.flow_from_directory(directory=test_dir_path,target_size=IMAGE_SHAPE , color_mode="rgb" , class_mode='categorical' , batch_size=1 , shuffle = False )
test_data.reset()
from keras.applications.vgg19 import VGG19
vggmodel = VGG19(weights='imagenet', include_top=True, input_tensor=tensorflow.keras.layers.Input(shape=(224,224,3)))
for layers in (vggmodel.layers)[:32]:
print(layers)
layers.trainable = False
X= vggmodel.layers[-12].output
X = tensorflow.keras.layers.Flatten()(X)
predictions = Dense(12, activation="softmax")(X)
model_final = Model(vggmodel.input, predictions)
model_final.compile(optimizer = optimizers.Adam(lr=0.0003), loss='categorical_crossentropy', metrics=["accuracy"])
for image_batch, labels_batch in train_data:
print(image_batch.shape)
print(labels_batch.shape)
break
from keras.callbacks import ModelCheckpoint, EarlyStopping
checkpoint = ModelCheckpoint("vgg16_1.h5", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
early = EarlyStopping(monitor='val_acc',patience=40, verbose=1, mode='auto')
model_final.fit_generator(generator= train_data, steps_per_epoch= 2, epochs= 100, validation_data= valid_data, validation_steps=1, callbacks=[checkpoint,early])
model_final.save_weights("vgg16_1.h5")
Related
Below is the code I am trying to custom the global average pooling code. My goal is to change the line "return np.mean(inputs, axis=(1, 2)" and write my own custom pooling method. However, although the code is working, I'm having problems with gradients and I can't get the same result with the global average pooling method. I am getting the below warning. Can you help me please?
WARNING:tensorflow:Gradients do not exist for variables ['conv2d_2/kernel:0', 'conv2d_2/bias:0', 'conv2d_3/kernel:0', 'conv2d_3/bias:0'] when minimizing the loss. If you're using model.compile(), did you forget to provide a lossargument?
WARNING:tensorflow:Gradients do not exist for variables ['conv2d_2/kernel:0', 'conv2d_2/bias:0', 'conv2d_3/kernel:0', 'conv2d_3/bias:0'] when minimizing the loss. If you're using model.compile(), did you forget to provide a lossargument?
import numpy as np
import tensorflow as tf
import math
import os
import random
import itertools
from tensorflow.python.ops import gen_nn_ops
from tensorflow.python.ops import array_ops
import numba as nb
import matplotlib.pyplot as plt
import skimage
from keras import backend as K
random.seed(91)
class LGPooling2D(tf.keras.layers.Layer):
def __init__(self, pool_size=(3, 3), strides=(2, 2), padding='SAME', data_format='channels_last', **kwargs):
super(LGPooling2D, self).__init__(**kwargs)
self.pool_size = pool_size
self.strides = strides
self.padding = padding
self.data_format = 'NHWC' if data_format == 'channels_last' else 'NCHW'
self.output_dim = 64
def build(self, input_shape):
super(LGPooling2D, self).build(input_shape)
def _pooling_function(self, x, name=None):
#b = K.shape(x)[0]
input_shape = tf.keras.backend.int_shape(x)
b, r,c,channel = input_shape[0],input_shape[1],input_shape[2],input_shape[3]
def _mid_pool(inputs, is_train):
return np.mean(inputs, axis=(1, 2)) # we change this part.
def custom_grad(op, grad):
if self.data_format == 'NHWC':
ksizes = [1, self.pool_size[0], self.pool_size[1], 1]
strides = [1, self.strides[0], self.strides[1], 1]
else:
ksizes = [1, 1, self.pool_size[0], self.pool_size[1]]
strides = [1, 1, self.strides[0], self.strides[1]]
return gen_nn_ops.max_pool_grad_v2(
op.inputs[0],
op.outputs[0],
grad,
ksizes,
strides,
self.padding,
data_format=self.data_format
), tf.constant(0.0)
def py_func(func, inp, Tout, stateful=True, name=None, grad=None, rnd_name=None):
# Need to generate a unique name to avoid duplicates:
tf.compat.v1.RegisterGradient(rnd_name)(grad)
g = tf.compat.v1.get_default_graph()
with g.gradient_override_map({"PyFunc": rnd_name}):
return tf.compat.v1.py_func(func, inp, Tout, stateful=stateful, name=name)
def _mid_range_pool(x, name=None):
rnd_name = 'LGPooling2D' + str(np.random.randint(0, 1E+8))
with tf.compat.v1.name_scope(name, "mod", [x]) as name:
z = py_func(_mid_pool,
[x, tf.keras.backend.learning_phase()],
[tf.float32],
name=name,
grad=custom_grad, rnd_name=rnd_name)[0]
z.set_shape((b, channel))
return z
return _mid_range_pool(x, name)
def compute_output_shape(self, input_shape):
r, c = input_shape[1], input_shape[2]
sr, sc = self.strides
num_r = math.ceil(r/sr) if self.padding == 'SAME' else r//sr
num_c = math.ceil(c/sc) if self.padding == 'SAME' else c//sc
return (input_shape[0], input_shape[3])
def call(self, inputs):
# K.in_train_phase(self._tf_pooling_function(inputs), self._pooling_function_test(inputs))
input_shape = tf.shape(inputs)
output = self._pooling_function(inputs)
# output = tf.reshape(output, self.compute_output_shape(input_shape))
return output
def get_config(self):
config = {
'pool_size': self.pool_size,
'strides': self.strides
}
base_config = super(LGPooling2D, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def get_model():
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(32, kernel_size=(3, 3),activation="relu",input_shape=input_shape))
# model.add(tf.keras.layers.SpatialDropout2D(0.15))
model.add(tf.keras.layers.MaxPooling2D())
model.add(tf.keras.layers.Conv2D(64, kernel_size=(3, 3),activation='relu'))
# model.add(tf.keras.layers.SpatialDropout2D(0.1))
# model.add(tf.keras.layers.MaxPooling2D())
model.add(LGPooling2D(pool_size=(3, 3), strides=(2, 2)))
# model.add(tf.keras.layers.GlobalAveragePooling2D())
# model.add(tf.keras.layers.Flatten())
# model.add(tf.keras.layers.Dense(100, activation='relu'))
# model.add(tf.keras.layers.Dropout(0.1))
model.add(tf.keras.layers.Dense(num_classes, activation='softmax'))
optim = tf.keras.optimizers.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=1e-6)
model.compile( loss="categorical_crossentropy",optimizer=optim, metrics=['accuracy'])
return model
batch_size = 32
num_classes = 100
epochs = 50
# input image dimensions
img_rows, img_cols = 32, 32
# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar100.load_data()
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 3)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 3)
input_shape = (img_rows, img_cols, 3)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255.0
x_test /= 255.0
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = tf.keras.utils.to_categorical(y_train, num_classes)
y_test = tf.keras.utils.to_categorical(y_test, num_classes)
reduceLROnPlat = tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.4, patience=6, verbose=1, mode='min', min_delta=0.0001, cooldown=5, min_lr=0.00001)
callbacks_list = [reduceLROnPlat]
print('custom pooling')
model = get_model()
# model = get_model(IMG_SHAPE = (32, 32, 3))
tf.keras.utils.plot_model(model, to_file='LbpModel.png', show_shapes=True)
modelcustom = model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_split=0.10,
callbacks=callbacks_list)
First of all I am very new to deep learning. Here I want to create a confusion matrix. For this reason, I need y_pred and y_true. I calculated y_true and y_pred the following way:
y_true = test_gen.classes
y_pred = (model.predict(test_gen)>0.5).astype("int32")
My confusion matrix code is:
from sklearn.metrics import classification_report, confusion_matrix
print('Confusion Matrix')
print(confusion_matrix(y_true, y_pred ))
mat = confusion_matrix(y_true, y_pred)
I set metrics=['accuracy','TruePositives', 'TrueNegatives', 'FalsePositives', 'FalseNegatives'] in my model.compile
best_model = model
best_model.load_weights('./classify_model.h5')
best_model.evaluate(test_gen)
The value that I get for TruePositives,TrueNegatives, FalsePositives,FalseNegatives from best_model.evaluate(test_gen) don't match with my confusion matrix value.
My Train dataset:
My test dataset:
target_size=(224,224)
batch_size=64
train_datagen = ImageDataGenerator(
preprocessing_function=tf.keras.applications.resnet_v2.preprocess_input,
horizontal_flip=True, zoom_range=0.1
)
test_datagen = ImageDataGenerator(
preprocessing_function=tf.keras.applications.resnet_v2.preprocess_input
)
train_gen = train_datagen.flow_from_dataframe(
train_df,
directory=train_path,
x_col='file_paths',
y_col='labels',
target_size=target_size,
batch_size=batch_size,
color_mode='rgb',
class_mode='binary'
)
valid_gen = test_datagen.flow_from_dataframe(
valid_df,
directory=train_path,
x_col='file_paths',
y_col='labels',
target_size=target_size,
batch_size=batch_size,
color_mode='rgb',
class_mode='binary'
)
test_gen = test_datagen.flow_from_dataframe(
test_df,
directory=test_path,
x_col='file_paths',
y_col='labels',
target_size=target_size,
batch_size=batch_size,
color_mode='rgb',
class_mode='binary'
)
base_model = tf.keras.applications.ResNet50V2(include_top=False, input_shape=(224,224,3))
model = tf.keras.Sequential([
base_model,
tf.keras.layers.GlobalAveragePooling2D(),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.BatchNormalization(),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(1, activation='sigmoid')
])
lr=0.001
model.compile(loss='binary_crossentropy', optimizer=Adam(learning_rate=lr), metrics=['accuracy', 'TruePositives', 'TrueNegatives', 'FalsePositives', 'FalseNegatives'])
I am having trouble calculating y_true and y_pred correctly. Please help me to construct confusion matrix for this code.
Please help me run the code. This doesn't work. I have been trying hard to solve this for days. The model_final.fit() also doesn't work. Why is this showing the same error for the method. This is almost the entire code.
EDIT: The train_generator and validation_generator added.
img_width, img_height = 400, 400
train_data_dir = "data/train"
validation_data_dir = "data/validation"
nb_train_samples = 4125
nb_validation_samples = 466
batch_size = 16,
epochs = 5
output_num_classes = 2
K.set_image_data_format('channels_last')
model = applications.VGG19(weights="imagenet", include_top=False, input_shape=(img_width, img_height, 3))
model.summary()
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
x = Dropout(0.5)(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(output_num_classes, activation="softmax")(x)
model_final = Model(inputs=model.input, outputs=predictions)
model_final.compile(loss="categorical_crossentropy",
optimizer=optimizers.SGD(learning_rate=0.0001, momentum=0.9),
metrics=['accuracy'])
train_datagen = ImageDataGenerator(rescale=1./255,
zoom_range=0.3,
width_shift_range=0.3,
height_shift_range=0.3,
rotation_range=30,
horizontal_flip=True,
fill_mode='nearest')
train_generator = train_datagen.flow_from_directory(train_data_dir,
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='categorical')
validation_datagen = ImageDataGenerator(rescale=1./255,
zoom_range=0.3,
width_shift_range=0.3,
height_shift_range=0.3,
rotation_range=30,
horizontal_flip=True,
fill_mode='nearest')
validation_generator = validation_datagen.flow_from_directory(validation_data_dir,
target_size=(img_height, img_width),
batch_size = batch_size,
class_mode='categorical')
The code above is before fitting.
model_final.fit_generator(train_generator,
steps_per_epoch=nb_train_samples,
epochs = epochs,
validation_data = validation_generator,
validation_steps = nb_validation_samples)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:1844: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.
warnings.warn('`Model.fit_generator` is deprecated and '
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-87-b195f52ce8fb> in <module>()
3 epochs = epochs,
4 validation_data = validation_generator,
----> 5 validation_steps = nb_validation_samples)
/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/iterator.py in __len__(self)
66
67 def __len__(self):
---> 68 return (self.n + self.batch_size - 1) // self.batch_size # round up
69
70 def on_epoch_end(self):
TypeError: unsupported operand type(s) for +: 'int' and 'tuple' ```
I was able to replicate your issue with sample code as shown below
import tensorflow as tf
from tensorflow.keras.applications import ResNet50
import os
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.models import Sequential
from google.colab import drive
drive.mount('/content/drive')
train_dir = '/content/drive/My Drive/Dogs_Vs_Cats/train'
test_dir = '/content/drive/My Drive/Dogs_Vs_Cats/test'
img_width, img_height = 224, 224
input_shape = (img_width, img_height, 3)
epochs = 8
batch_size = 32,
train_datagen = ImageDataGenerator(
rescale = 1. /255,
horizontal_flip = True)
test_datagen = ImageDataGenerator(
rescale = 1. /255)
train_data = train_datagen.flow_from_directory(
train_dir,
target_size = (img_width, img_height),
batch_size = batch_size,
class_mode = 'binary')
test_data = test_datagen.flow_from_directory(
test_dir,
target_size = (img_width, img_height),
class_mode = 'binary')
Conv_Base = ResNet50(include_top = False, weights = 'imagenet', input_shape = input_shape)
model = Sequential()
model.add(Conv_Base)
model.add(Flatten())
model.add(Dense(units = 256, activation = 'relu'))
model.add(Dropout(0.5))
model.add(Dense(units = 1, activation = 'sigmoid'))
model.summary()
model.compile(loss = 'binary_crossentropy',
optimizer = 'Adam',
metrics = [tf.keras.metrics.Precision(), tf.keras.metrics.Recall()])
model.fit(
train_data,
steps_per_epoch = 10,
epochs = 2,
validation_data = test_data,
verbose = 1,
validation_steps = 32)
Output:
Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).
Found 2000 images belonging to 2 classes.
Found 1018 images belonging to 2 classes.
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
resnet50 (Functional) (None, 7, 7, 2048) 23587712
_________________________________________________________________
flatten (Flatten) (None, 100352) 0
_________________________________________________________________
dense (Dense) (None, 256) 25690368
_________________________________________________________________
dropout (Dropout) (None, 256) 0
_________________________________________________________________
dense_1 (Dense) (None, 1) 257
=================================================================
Total params: 49,278,337
Trainable params: 49,225,217
Non-trainable params: 53,120
_________________________________________________________________
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-1-5a5644117355> in <module>()
60 validation_data = test_data,
61 verbose = 1,
---> 62 validation_steps = 32)
3 frames
/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/iterator.py in __len__(self)
66
67 def __len__(self):
---> 68 return (self.n + self.batch_size - 1) // self.batch_size # round up
69
70 def on_epoch_end(self):
TypeError: unsupported operand type(s) for +: 'int' and 'tuple'
Solution to fix:
As rightly suggested by #Dr. Snoopy, this issue was due to comma right after batch_size definition. It converts the integer into a tuple and which is not supported.
Changing batch_size = 32, to batch_size = 32 has resolved the issue.
Working code as shown below
import tensorflow as tf
from tensorflow.keras.applications import ResNet50
import os
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.models import Sequential
from google.colab import drive
drive.mount('/content/drive')
train_dir = '/content/drive/My Drive/Dogs_Vs_Cats/train'
test_dir = '/content/drive/My Drive/Dogs_Vs_Cats/test'
img_width, img_height = 224, 224
input_shape = (img_width, img_height, 3)
epochs = 8
batch_size = 32 # removed comma
train_datagen = ImageDataGenerator(
rescale = 1. /255,
horizontal_flip = True)
test_datagen = ImageDataGenerator(
rescale = 1. /255)
train_data = train_datagen.flow_from_directory(
train_dir,
target_size = (img_width, img_height),
batch_size = batch_size,
class_mode = 'binary')
test_data = test_datagen.flow_from_directory(
test_dir,
target_size = (img_width, img_height),
class_mode = 'binary')
Conv_Base = ResNet50(include_top = False, weights = 'imagenet', input_shape = input_shape)
model = Sequential()
model.add(Conv_Base)
model.add(Flatten())
model.add(Dense(units = 256, activation = 'relu'))
model.add(Dropout(0.5))
model.add(Dense(units = 1, activation = 'sigmoid'))
model.summary()
model.compile(loss = 'binary_crossentropy',
optimizer = 'Adam',
metrics = [tf.keras.metrics.Precision(), tf.keras.metrics.Recall()])
model.fit(
train_data,
steps_per_epoch = 10,
epochs = 2,
validation_data = test_data,
verbose = 1,
validation_steps = 32)
Output:
Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).
Found 2000 images belonging to 2 classes.
Found 1018 images belonging to 2 classes.
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
resnet50 (Functional) (None, 7, 7, 2048) 23587712
_________________________________________________________________
flatten_1 (Flatten) (None, 100352) 0
_________________________________________________________________
dense_2 (Dense) (None, 256) 25690368
_________________________________________________________________
dropout_1 (Dropout) (None, 256) 0
_________________________________________________________________
dense_3 (Dense) (None, 1) 257
=================================================================
Total params: 49,278,337
Trainable params: 49,225,217
Non-trainable params: 53,120
_________________________________________________________________
Epoch 1/2
10/10 [==============================] - 107s 10s/step - loss: 9.5302 - precision_1: 0.6096 - recall_1: 0.6485 - val_loss: 14405.0479 - val_precision_1: 0.0000e+00 - val_recall_1: 0.0000e+00
Epoch 2/2
10/10 [==============================] - 68s 7s/step - loss: 2.2295 - precision_1: 0.8191 - recall_1: 0.8799 - val_loss: 3977.1418 - val_precision_1: 0.4912 - val_recall_1: 1.0000
<tensorflow.python.keras.callbacks.History at 0x7fbba005cc50>
I am trying to train a model on Google Colab, in order to play around with training on TPU. However, I am running into the following error:
AttributeError Traceback (most recent call last)
<ipython-input-82-e74efc36d872> in <module>()
----> 1 tpu_model.fit_generator(training_set, steps_per_epoch = 8000, epochs = 25)
2 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/callbacks.py in configure_callbacks(callbacks, model, do_validation, batch_size, epochs, steps_per_epoch, samples, verbose, count_mode, mode)
118 callback_list.model.stop_training = False
119 # pylint: disable=protected-access
--> 120 if callback_list.model._ckpt_saved_epoch is not None:
121 # The attribute `_ckpt_saved_epoch` is supposed to be None at the start of
122 # training (it should be made None at the end of successful multi-worker
AttributeError: 'KerasTPUModel' object has no attribute '_ckpt_saved_epoch'
While trying to run the following code.
import tensorflow as tf
from tensorflow.keras import layers
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import os
import zipfile
print(tf.VERSION)
local_zip = '/home/cats_and_dogs_filtered.zip'
zip_ref = zipfile.ZipFile(local_zip, 'r')
zip_ref.extractall('/home')
zip_ref.close()
def create_model():
classifier = tf.keras.models.Sequential()
classifier.add(layers.Conv2D(32, (3, 3), input_shape=(64, 64, 3), activation='relu'))
classifier.add(layers.MaxPooling2D(pool_size=(2, 2)))
classifier.add(layers.Conv2D(32, (3, 3), activation= 'relu'))
classifier.add(layers.MaxPooling2D(pool_size=(2, 2)))
classifier.add(layers.Flatten())
classifier.add(layers.Dense(units=128, activation= 'relu'))
classifier.add(layers.Dense(units=1, activation= 'sigmoid'))
return classifier
train_datagen = ImageDataGenerator(rescale = 1./255, shear_range = 0.2, zoom_range = 0.2, horizontal_flip = True)
training_set = train_datagen.flow_from_directory('/home/cats_and_dogs_filtered/train', target_size = (64, 64), batch_size = 32, class_mode = 'binary')
model = create_model()
TPU_WORKER = 'grpc://' + os.environ['COLAB_TPU_ADDR']
tpu_model = tf.contrib.tpu.keras_to_tpu_model( model, strategy=tf.contrib.tpu.TPUDistributionStrategy(tf.contrib.cluster_resolver.TPUClusterResolver(TPU_WORKER)))
tpu_model.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
tpu_model.save_weights('./tpu_model.h5', overwrite=True)
tpu_model.fit_generator(training_set, steps_per_epoch = 8000, epochs = 25)
I am not sure what is going on. I used similar code to train it on CPU (takes a long time to train).
I'm making an Autoencoder in Keras and Tensorflow and I keep running into the below error. I think it's a problem to do with my model architecture and how the dimensions of the input are transformed when passed in the encoder and decoder.
Error Traceback:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-83-4f4e153bd0cf> in <module>()
48
49 autoencoder.compile(optimizer=keras.optimizers.SGD(learning_rate=1e-3), loss = 'binary_crossentropy')
---> 50 autoencoder.fit(x_train, x_train, epochs=50, batch_size = 256, shuffle= True, validation_data=(x_test, x_test))
51 encoded_imgs = encoder.predict(x_test)
52 decoder_imgs = decoder.predict(encoded_imgs)
2 frames
/usr/local/lib/python3.6/dist-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)
707 steps=steps_per_epoch,
708 validation_split=validation_split,
--> 709 shuffle=shuffle)
710
711 # Prepare validation data.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name, steps, validation_split, shuffle, extract_tensors_from_dataset)
2690 # Additional checks to avoid users mistakenly using improper loss fns.
2691 training_utils.check_loss_and_target_compatibility(
-> 2692 y, self._feed_loss_fns, feed_output_shapes)
2693
2694 # If sample weight mode has not been set and weights are None for all the
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training_utils.py in check_loss_and_target_compatibility(targets, loss_fns, output_shapes)
547 raise ValueError('A target array with shape ' + str(y.shape) +
548 ' was passed for an output of shape ' + str(shape) +
--> 549 ' while using as loss `' + loss_name + '`. '
550 'This loss expects targets to have the same shape '
551 'as the output.')
ValueError: A target array with shape (60000, 28, 28, 1) was passed for an output of shape (None, 28, 28, 128) while using as loss `binary_crossentropy`. This loss expects targets to have the same shape as the output.
Here is my code: Any feedback would be appreciated.
import tensorflow as tf
from tensorflow import keras
from keras.datasets import mnist
import numpy as np
from keras import backend as K
(x_train, x_train), (x_test, x_test) = mnist.load_data()
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
# x_train = x_train.reshape(6000, 28, 28, 1)
# x_test = x_test.reshape(6000,28, 28, 1)
x_train, x_test = np.expand_dims(x_train, -1), np.expand_dims(x_test, -1)
encoder_img = tf.keras.layers.Input(shape=(28, 28, 1), name="input")
x = tf.keras.layers.Conv2D(128, 3,activation = 'relu', kernel_initializer = keras.initializers.RandomUniform)(encoder_img)
x = tf.keras.layers.MaxPooling2D(1)(x)
x = tf.keras.layers.Conv2D(64, 3, activation = 'relu')(x)
x = tf.keras.layers.MaxPooling2D(1)(x)
x = tf.keras.layers.Conv2D(32, 3,activation = 'relu')(x)
x = tf.keras.layers.MaxPooling2D(1)(x)
x = tf.keras.layers.Conv2D(16, 3, activation = 'relu')(x)
encoder_output = tf.keras.layers.GlobalMaxPooling2D()(x)
#Spatial sparsity -
encoder = tf.keras.Model(inputs=encoder_img, outputs=encoder_output, name = 'encoder')
encoder.summary()
decoder_input = tf.keras.layers.Reshape((20, 20, 16))(encoder_output)
x = tf.keras.layers.Conv2DTranspose(16, 3, activation = 'relu')(decoder_input)
x = tf.keras.layers.UpSampling2D(1)(x)
x = tf.keras.layers.Conv2DTranspose(32, 3, activation = 'relu')(x)
x = tf.keras.layers.UpSampling2D(1)(x)
x = tf.keras.layers.Conv2DTranspose(64, 3, activation = 'relu')(x)
x = tf.keras.layers.UpSampling2D(1)(x)
decoder_output = tf.keras.layers.Conv2DTranspose(128, 3, activation = 'relu')(x)
autoencoder = tf.keras.Model(inputs = encoder_img, outputs = decoder_output, name='autoencoder')
autoencoder.summary()
autoencoder.compile(optimizer=keras.optimizers.SGD(learning_rate=1e-3), loss = 'binary_crossentropy')
autoencoder.fit(x_train, x_train, epochs=50, batch_size = 256, shuffle= True, validation_data=(x_test, x_test))
encoded_imgs = encoder.predict(x_test)
decoder_imgs = decoder.predict(encoded_imgs)
New Error with below as replacement
decoder_output = tf.keras.layers.Conv2DTranspose(1, 3, activation = 'relu')(x)
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
<ipython-input-84-cbc6c54cd473> in <module>()
48
49 autoencoder.compile(optimizer=keras.optimizers.SGD(learning_rate=1e-3), loss = 'binary_crossentropy')
---> 50 autoencoder.fit(x_train, x_train, epochs=50, batch_size = 256, shuffle= True, validation_data=(x_test, x_test))
51 encoded_imgs = encoder.predict(x_test)
52 decoder_imgs = decoder.predict(encoded_imgs)
3 frames
/usr/local/lib/python3.6/dist-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: Input to reshape is a tensor with 4096 values, but the requested shape has 1638400
[[{{node reshape_56/Reshape}}]]