I'm trying to implement a simple Unet network using Keras on Tensorflow 2.0 backend.
I use custom image generator without augumentated data. My templates anf masks are 1536x1536 RGB images (masks are black and white).
import numpy as np
import os
import cv2
import random
from tensorflow.python.keras.models import Model
from tensorflow.python.keras.layers import Input, BatchNormalization, Activation, Dense, Dropout
from tensorflow.python.keras.layers.core import Lambda, RepeatVector, Reshape
from tensorflow.python.keras.layers.convolutional import Conv2D, Conv2DTranspose
from tensorflow.python.keras.layers.pooling import MaxPooling2D, GlobalMaxPool2D
from tensorflow.python.keras.layers.merge import concatenate, add
from tensorflow.python.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau
from tensorflow.keras.optimizers import Adam
from tensorflow.python.keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
import tensorflow as tf
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
session = tf.compat.v1.Session(config=config)
def data_gen(templates_folder, masks_folder, image_width, batch_size): # Custom image generator
counter = 0
images_list = os.listdir(templates_folder)
random.shuffle(images_list)
while True:
templates_pack = np.zeros((batch_size, image_width, image_width, 3)).astype('float')
masks_pack = np.zeros((batch_size, image_width, image_width, 1)).astype('float')
for i in range(counter, counter + batch_size):
template = cv2.imread(templates_folder + '/' + images_list[i]) / 255.
templates_pack[i - counter] = template
mask = cv2.imread(masks_folder + '/' + images_list[i], cv2.IMREAD_GRAYSCALE) / 255.
mask = mask.reshape(image_width, image_width, 1) # Add extra dimension for parity with template size [1536 * 1536 * 3]
masks_pack[i - counter] = mask
counter += batch_size
if counter + batch_size >= len(images_list):
counter = 0
random.shuffle(images_list)
yield templates_pack, masks_pack
def conv2d_block(input_tensor, n_filters, kernel_size=3, batchnorm=True):
x = Conv2D(filters=n_filters, kernel_size=(kernel_size, kernel_size), kernel_initializer="he_normal", padding="same")(input_tensor)
if batchnorm:
x = BatchNormalization()(x)
x = Activation("relu")(x)
x = Conv2D(filters=n_filters, kernel_size=(kernel_size, kernel_size), kernel_initializer="he_normal", padding="same")(x)
if batchnorm:
x = BatchNormalization()(x)
x = Activation("relu")(x)
return x
def get_unet(input_img, n_filters=16, dropout=0.5, batchnorm=True):
c1 = conv2d_block(input_img, n_filters=n_filters * 1, kernel_size=3, batchnorm=batchnorm)
p1 = MaxPooling2D((2, 2))(c1)
p1 = Dropout(dropout * 0.5)(p1)
c2 = conv2d_block(p1, n_filters=n_filters * 2, kernel_size=3, batchnorm=batchnorm)
p2 = MaxPooling2D((2, 2))(c2)
p2 = Dropout(dropout)(p2)
c3 = conv2d_block(p2, n_filters=n_filters * 4, kernel_size=3, batchnorm=batchnorm)
p3 = MaxPooling2D((2, 2))(c3)
p3 = Dropout(dropout)(p3)
c4 = conv2d_block(p3, n_filters=n_filters * 8, kernel_size=3, batchnorm=batchnorm)
p4 = MaxPooling2D(pool_size=(2, 2))(c4)
p4 = Dropout(dropout)(p4)
c5 = conv2d_block(p4, n_filters=n_filters * 16, kernel_size=3, batchnorm=batchnorm)
u6 = Conv2DTranspose(n_filters * 8, (3, 3), strides=(2, 2), padding='same')(c5)
u6 = concatenate([u6, c4])
u6 = Dropout(dropout)(u6)
c6 = conv2d_block(u6, n_filters=n_filters * 8, kernel_size=3, batchnorm=batchnorm)
u7 = Conv2DTranspose(n_filters * 4, (3, 3), strides=(2, 2), padding='same')(c6)
u7 = concatenate([u7, c3])
u7 = Dropout(dropout)(u7)
c7 = conv2d_block(u7, n_filters=n_filters * 4, kernel_size=3, batchnorm=batchnorm)
u8 = Conv2DTranspose(n_filters * 2, (3, 3), strides=(2, 2), padding='same')(c7)
u8 = concatenate([u8, c2])
u8 = Dropout(dropout)(u8)
c8 = conv2d_block(u8, n_filters=n_filters * 2, kernel_size=3, batchnorm=batchnorm)
u9 = Conv2DTranspose(n_filters * 1, (3, 3), strides=(2, 2), padding='same')(c8)
u9 = concatenate([u9, c1], axis=3)
u9 = Dropout(dropout)(u9)
c9 = conv2d_block(u9, n_filters=n_filters * 1, kernel_size=3, batchnorm=batchnorm)
outputs = Conv2D(1, (1, 1), activation='sigmoid')(c9)
model = Model(inputs=[input_img], outputs=[outputs])
return model
callbacks = [
EarlyStopping(patience=10, verbose=1),
ReduceLROnPlateau(factor=0.1, patience=3, min_lr=0.00001, verbose=1),
ModelCheckpoint("model-prototype.h5", verbose=1, save_best_only=True,
save_weights_only=True)
]
train_templates_path = "E:/train/templates"
train_masks_path = "E:/train/masks"
valid_templates_path = "E:/valid/templates"
valid_masks_path = "E:/valid/masks"
TRAIN_SET_SIZE = len(os.listdir(train_templates_path))
VALID_SET_SIZE = len(os.listdir(valid_templates_path))
BATCH_SIZE = 1
EPOCHS = 100
STEPS_PER_EPOCH = TRAIN_SET_SIZE / BATCH_SIZE
VALIDATION_STEPS = VALID_SET_SIZE / BATCH_SIZE
IMAGE_WIDTH = 1536
train_generator = data_gen(train_templates_path, train_masks_path, IMAGE_WIDTH, batch_size = BATCH_SIZE)
val_generator = data_gen(valid_templates_path, valid_masks_path, IMAGE_WIDTH, batch_size = BATCH_SIZE)
model = get_unet(input_img, n_filters=16, dropout=0.05, batchnorm=True)
model.compile(optimizer=Adam(lr=0.001), loss="binary_crossentropy", metrics=["accuracy"])
results = model.fit_generator(train_generator, epochs=EPOCHS, steps_per_epoch=STEPS_PER_EPOCH, validation_data=val_generator, validation_steps=VALIDATION_STEPS, callbacks=callbacks)
For some reason I get a following error:
Epoch 1/100
Traceback (most recent call last):
File "E:/Explorium/python/unet_trainer.py", line 83, in <module>
results = model.fit_generator(train_generator, epochs=EPOCHS, steps_per_epoch=STEPS_PER_EPOCH, validation_data=val_generator, validation_steps=VALIDATION_STEPS, callbacks=callbacks)
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 1297, in fit_generator
steps_name='steps_per_epoch')
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training_generator.py", line 265, in model_iteration
batch_outs = batch_function(*batch_data)
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 973, in train_on_batch
class_weight=class_weight, reset_metrics=reset_metrics)
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py", line 253, in train_on_batch
extract_tensors_from_dataset=True)
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2472, in _standardize_user_data
exception_prefix='input')
File "C:\Users\E-soft\Anaconda3\envs\Explorium\lib\site-packages\tensorflow_core\python\keras\engine\training_utils.py", line 574, in standardize_input_data
str(data_shape))
ValueError: Error when checking input: expected img to have shape (1536, 1536, 1) but got array with shape (1536, 1536, 3)
It seems that Keras can't normalize data using standardize_input_data(), but I have no idea why it's happening.
I have this vgg model. Which I am using to extract an image features. But I am getting an attribute error: I can't seem to understand the error. I am using keras 2.2.4 and tensorflow 1.13.1 with python 3.7.3. I am using anaconda with spyder as IDE.
import numpy as np
import warnings
#tf.compat.v1.reset_default_graph()
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Input
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.layers import GlobalMaxPooling2D
from tensorflow.keras.layers import GlobalAveragePooling2D
from tensorflow.keras.preprocessing import image
from tensorflow.python.keras.utils import layer_utils , get_source_inputs
from tensorflow.python.keras.utils.data_utils import get_file
from tensorflow.python.keras import backend as K
from tensorflow.python.keras.applications.imagenet_utils import decode_predictions
from tensorflow.python.keras.applications.imagenet_utils import preprocess_input
from keras_applications.imagenet_utils import _obtain_input_shape
#from keras.engine.topology import get_source_inputs
#from tensorflow.python.keras.utils.layer_utils import get_source_inputs
WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5'
WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5'
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
def VGG16(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None,
pooling=None,
classes=1000):
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
require_flatten=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vgg16')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
)
else:
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='block5_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1')
layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
model.layers.pop() # Get rid of the classification layer
model.outputs = [model.layers[-1].output]
model.layers[-1].outbound_nodes = [ ]
return model```
I am getting the following error on the second last line of the code:
File "/home/natsu/Final_code/vgg16.py", line 200, in VGG16
model.layers[-1].outbound_nodes = []
File "/home/natsu/anaconda3/envs/py-env/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 1639, in __setattr__
super(Layer, self).__setattr__(name, value)
AttributeError: can't set attribute```
I was able to execute your code successfully in tensorflow version 1.15 without any modifications.
I was able to execute your code successfully in tensorflow version 2.2.0 with minor modifications shown below -
Modify,
from tensorflow.python.keras.utils import layer_utils , get_source_inputs
to
from tensorflow.python.keras.utils import layer_utils
from tensorflow.python.keras.utils.layer_utils import get_source_inputs
Can you please upgrade the tensorflow version and check if the error is fixed.
Hope this answers your question. Happy Learning.
I am trying to write a convolutional neural network in keras that uses an Inception style module, like the example from keras functional API page. To "simplify" things I decided it would be good to put this module in a python function to be reusable with different filter and input sizes. This however generates the error message:
TypeError: float() argument must be a string or a number, not
'Dimension'
How should I write this function, and what's wrong with this one
"""This is the "inception" module."""
def incepm_v1(out_filters, input_shape)->Model:
from keras.layers import Conv2D, MaxPooling2D, Input
input_img = Input(shape=input_shape)
tower_1 = Conv2D(out_filters, (1, 1), padding='same',
activation='relu')(input_img)
tower_1 = Conv2D(out_filters, (3, 3), padding='same',
activation='relu')(tower_1)
tower_2 = Conv2D(out_filters, (1, 1), padding='same',
activation='relu')(input_img)
tower_2 = Conv2D(out_filters, (5, 5), padding='same',
activation='relu')(tower_2)
tower_3 = MaxPooling2D((3, 3), strides=(1, 1), padding='same')
(input_img)
tower_3 = Conv2D(out_filters, (1, 1), padding='same',
activation='relu')(tower_3)
output = keras.layers.concatenate([tower_1, tower_2, tower_3],
axis=1)
model = Model(inputs=input_img, outputs=output)
return model
"This is then used in the following model"
def Unetish_model1(image_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)):
image = Input(shape=image_shape)
#First layer 96X96
conv1 = Conv2D(32, (3,3),padding='same', activation =
'relu'(image)
conv1out = Conv2D(16, (1,1),padding = 'same', activation =
'relu')(conv1)
conv1out = MaxPooling2D((2,2), strides = (2,2))(conv1out)
aux1out = Conv2D(16, (1,1), padding = 'same', activation =
'relu')(conv1)
#Second layer 48x48
#print(conv1out.shape)
conv2 = incepm_v1(64, conv1out.shape[1:])(conv1out)
conv2out = Conv2D(32, (1,1), padding = 'same', activation =
'relu')(conv2)
conv2out = MaxPooling2D((2,2), strides = (2,2))(conv2out)
aux2out = Conv2D(32, (1,1), padding = 'same', activation =
'relu')(conv2)
".... removed for sparsity"
model = Model(inputs =image, outputs = output)
model.summary()
return model
IMAGE_SIZE = 96
Unet = Unetish_model1(image_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))
--------------------------------------------------------------------
-------
TypeError Traceback (most recent
call last)
<ipython-input-79-9f51199eb354> in <module>()
1 IMAGE_SIZE = 96
----> 2 Unet = Unetish_model1(image_shape=(IMAGE_SIZE, IMAGE_SIZE,
3))
<ipython-input-78-663bab493362> in Unetish_model1(image_shape)
10 #Second layer 48x48
11 #print(conv1out.shape)
---> 12 conv2 = incepm_v1(64, conv1out.shape[1:])(conv1out)
13 conv2out = Conv2D(32, (1,1), padding = 'same',
activation = 'relu')(conv2)
14 conv2out = MaxPooling2D((2,2), strides = (2,2))
(conv2out)
<ipython-input-72-b8563ad454e6> in incepm_v1(out_filters,
input_shape)
4 input_img = Input(shape=input_shape)
5
----> 6 tower_1 = Conv2D(out_filters, (1, 1), padding='same',
activation='relu')(input_img)
7 tower_1 = Conv2D(out_filters, (3, 3), padding='same',
activation='relu')(tower_1)
8
~/anaconda3/envs/dlib/lib/python3.5/site-
packages/keras/engine/topology.py in __call__(self, inputs,
**kwargs)
588
'`layer.build(batch_input_shape)`')
589 if len(input_shapes) == 1:
--> 590 self.build(input_shapes[0])
591 else:
592 self.build(input_shapes)
~/anaconda3/envs/dlib/lib/python3.5/site-
packages/keras/layers/convolutional.py in build(self,
input_shape)
136 name='kernel',
137
regularizer=self.kernel_regularizer,
--> 138
constraint=self.kernel_constraint)
139 if self.use_bias:
140 self.bias = self.add_weight(shape=
(self.filters,),
~/anaconda3/envs/dlib/lib/python3.5/site-
packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' +
object_name +
90 '` call to the Keras 2 API: '
+ signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
~/anaconda3/envs/dlib/lib/python3.5/site-
packages/keras/engine/topology.py in add_weight(self, name,
shape, dtype, initializer, regularizer, trainable, constraint)
409 if dtype is None:
410 dtype = K.floatx()
--> 411 weight = K.variable(initializer(shape),
412 dtype=dtype,
413 name=name,
~/anaconda3/envs/dlib/lib/python3.5/site-
packages/keras/initializers.py in __call__(self, shape, dtype)
207 scale /= max(1., fan_out)
208 else:
--> 209 scale /= max(1., float(fan_in + fan_out) / 2)
210 if self.distribution == 'normal':
211 stddev = np.sqrt(scale)
TypeError: float() argument must be a string or a number, not
'Dimension'
I am using keras version 2.1.3 in an anaconda enviroment with tensorflow backended with gpu
layer_name.shape will give you a tensorflow.python.framework.tensor_shape.TensorShape containing tensorflow.python.framework.tensor_shape.Dimension.
In this case, you should use K.int_shape(layer_name), which gives you tuple of integers.
from keras.layers import Conv2D, MaxPooling2D, Input, Concatenate
from keras.models import Model
import keras.backend as K
"""This is the "inception" module."""
def incepm_v1(out_filters, input_shape)->Model:
input_img = Input(shape=input_shape)
tower_1 = Conv2D(out_filters, (1, 1), padding='same',
activation='relu')(input_img)
tower_1 = Conv2D(out_filters, (3, 3), padding='same',
activation='relu')(tower_1)
tower_2 = Conv2D(out_filters, (1, 1), padding='same',
activation='relu')(input_img)
tower_2 = Conv2D(out_filters, (5, 5), padding='same',
activation='relu')(tower_2)
tower_3 = MaxPooling2D((3, 3), strides=(1, 1), padding='same')(input_img)
tower_3 = Conv2D(out_filters, (1, 1), padding='same',
activation='relu')(tower_3)
output = Concatenate(axis=1)([tower_1, tower_2, tower_3])
model = Model(inputs=input_img, outputs=output)
return model
"""This is then used in the following model"""
def Unetish_model1(image_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)):
image = Input(shape=image_shape)
#First layer 96X96
conv1 = Conv2D(32, (3,3),padding='same', activation = 'relu')(image)
conv1out = Conv2D(16, (1,1),padding = 'same', activation =
'relu')(conv1)
conv1out = MaxPooling2D((2,2), strides = (2,2))(conv1out)
aux1out = Conv2D(16, (1,1), padding = 'same', activation = 'relu')(conv1)
#Second layer 48x48
#conv2 = incepm_v1(64, conv1out.shape[1:])(conv1out)
conv2 = incepm_v1(64, K.int_shape(conv1out)[1:])(conv1out)
conv2out = Conv2D(32, (1,1), padding = 'same', activation =
'relu')(conv2)
conv2out = MaxPooling2D((2,2), strides = (2,2))(conv2out)
aux2out = Conv2D(32, (1,1), padding = 'same', activation =
'relu')(conv2)
#".... removed for sparsity"
model = Model(inputs =image, outputs = output)
model.summary()
return model
IMAGE_SIZE = 96
Unet = Unetish_model1(image_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))
The code above also fixes the usage of Concatenate layer.
And note that this piece of code still can be run successfully since some parts of Unetish_model1 is omitted.
I want to extract a part of the SSD512 architecture into a separate model. The function that returns the required model is below:
def ssd_512_end(image_size,
n_classes,
mode='training',
l2_regularization=0.0005,
min_scale=None,
max_scale=None,
scales=None,
aspect_ratios_global=None,
aspect_ratios_per_layer=[[1.0, 2.0, 0.5],
[1.0, 2.0, 0.5, 3.0, 1.0/3.0],
[1.0, 2.0, 0.5, 3.0, 1.0/3.0],
[1.0, 2.0, 0.5, 3.0, 1.0/3.0],
[1.0, 2.0, 0.5, 3.0, 1.0/3.0],
[1.0, 2.0, 0.5],
[1.0, 2.0, 0.5]],
two_boxes_for_ar1=True,
steps=[8, 16, 32, 64, 128, 256, 512],
offsets=None,
clip_boxes=False,
variances=[0.1, 0.1, 0.2, 0.2],
coords='centroids',
normalize_coords=True,
subtract_mean=[123, 117, 104],
divide_by_stddev=None,
swap_channels=[2, 1, 0],
confidence_thresh=0.01,
iou_threshold=0.45,
top_k=200,
nms_max_output_size=400,
return_predictor_sizes=False):
n_predictor_layers = 7 # The number of predictor conv layers in the network is 7 for the original SSD512
n_classes += 1 # Account for the background class.
l2_reg = l2_regularization # Make the internal name shorter.
img_height, img_width, img_channels = image_size[0], image_size[1], image_size[2]
############################################################################
# Get a few exceptions out of the way.
############################################################################
if aspect_ratios_global is None and aspect_ratios_per_layer is None:
raise ValueError("`aspect_ratios_global` and `aspect_ratios_per_layer` cannot both be None. At least one needs to be specified.")
if aspect_ratios_per_layer:
if len(aspect_ratios_per_layer) != n_predictor_layers:
raise ValueError("It must be either aspect_ratios_per_layer is None or len(aspect_ratios_per_layer) == {}, but len(aspect_ratios_per_layer) == {}.".format(n_predictor_layers, len(aspect_ratios_per_layer)))
if (min_scale is None or max_scale is None) and scales is None:
raise ValueError("Either `min_scale` and `max_scale` or `scales` need to be specified.")
if scales:
if len(scales) != n_predictor_layers+1:
raise ValueError("It must be either scales is None or len(scales) == {}, but len(scales) == {}.".format(n_predictor_layers+1, len(scales)))
else: # If no explicit list of scaling factors was passed, compute the list of scaling factors from `min_scale` and `max_scale`
scales = np.linspace(min_scale, max_scale, n_predictor_layers+1)
if len(variances) != 4:
raise ValueError("4 variance values must be pased, but {} values were received.".format(len(variances)))
variances = np.array(variances)
if np.any(variances <= 0):
raise ValueError("All variances must be >0, but the variances given are {}".format(variances))
if (not (steps is None)) and (len(steps) != n_predictor_layers):
raise ValueError("You must provide at least one step value per predictor layer.")
if (not (offsets is None)) and (len(offsets) != n_predictor_layers):
raise ValueError("You must provide at least one offset value per predictor layer.")
############################################################################
# Compute the anchor box parameters.
############################################################################
# Set the aspect ratios for each predictor layer. These are only needed for the anchor box layers.
if aspect_ratios_per_layer:
aspect_ratios = aspect_ratios_per_layer
else:
aspect_ratios = [aspect_ratios_global] * n_predictor_layers
# Compute the number of boxes to be predicted per cell for each predictor layer.
# We need this so that we know how many channels the predictor layers need to have.
if aspect_ratios_per_layer:
n_boxes = []
for ar in aspect_ratios_per_layer:
if (1 in ar) & two_boxes_for_ar1:
n_boxes.append(len(ar) + 1) # +1 for the second box for aspect ratio 1
else:
n_boxes.append(len(ar))
else: # If only a global aspect ratio list was passed, then the number of boxes is the same for each predictor layer
if (1 in aspect_ratios_global) & two_boxes_for_ar1:
n_boxes = len(aspect_ratios_global) + 1
else:
n_boxes = len(aspect_ratios_global)
n_boxes = [n_boxes] * n_predictor_layers
if steps is None:
steps = [None] * n_predictor_layers
if offsets is None:
offsets = [None] * n_predictor_layers
############################################################################
# Define functions for the Lambda layers below.
############################################################################
def identity_layer(tensor):
return tensor
def input_mean_normalization(tensor):
return tensor - np.array(subtract_mean)
def input_stddev_normalization(tensor):
return tensor / np.array(divide_by_stddev)
def input_channel_swap(tensor):
if len(swap_channels) == 3:
return K.stack([tensor[...,swap_channels[0]], tensor[...,swap_channels[1]], tensor[...,swap_channels[2]]], axis=-1)
elif len(swap_channels) == 4:
return K.stack([tensor[...,swap_channels[0]], tensor[...,swap_channels[1]], tensor[...,swap_channels[2]], tensor[...,swap_channels[3]]], axis=-1)
############################################################################
# Build the network.
############################################################################
x = Input(shape=(img_height, img_width, img_channels))
# The following identity layer is only needed so that the subsequent lambda layers can be optional.
x1 = Lambda(identity_layer, output_shape=(img_height, img_width, img_channels), name='identity_layer')(x)
if not (subtract_mean is None):
x1 = Lambda(input_mean_normalization, output_shape=(img_height, img_width, img_channels), name='input_mean_normalization')(x1)
if not (divide_by_stddev is None):
x1 = Lambda(input_stddev_normalization, output_shape=(img_height, img_width, img_channels), name='input_stddev_normalization')(x1)
if swap_channels:
x1 = Lambda(input_channel_swap, output_shape=(img_height, img_width, img_channels), name='input_channel_swap')(x1)
conv1_1 = Conv2D(64, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv1_1')(x1)
conv1_2 = Conv2D(64, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv1_2')(conv1_1)
pool1 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='pool1')(conv1_2)
conv2_1 = Conv2D(128, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv2_1')(pool1)
conv2_2 = Conv2D(128, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv2_2')(conv2_1)
pool2 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='pool2')(conv2_2)
conv3_1 = Conv2D(256, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv3_1')(pool2)
conv3_2 = Conv2D(256, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv3_2')(conv3_1)
conv3_3 = Conv2D(256, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv3_3')(conv3_2)
pool3 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='pool3')(conv3_3)
conv4_1 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_1')(pool3)
conv4_2 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_2')(conv4_1)
conv4_3 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_3')(conv4_2)
pool4 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='pool4')(conv4_3)
conv5_1 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv5_1')(pool4)
conv5_2 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv5_2')(conv5_1)
conv5_3 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv5_3')(conv5_2)
pool5 = MaxPooling2D(pool_size=(3, 3), strides=(1, 1), padding='same', name='pool5')(conv5_3)
fc6 = Conv2D(1024, (3, 3), dilation_rate=(6, 6), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='fc6')(pool5)
fc7 = Conv2D(1024, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='fc7')(fc6)
conv6_1 = Conv2D(256, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv6_1')(fc7)
conv6_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv6_padding')(conv6_1)
conv6_2 = Conv2D(512, (3, 3), strides=(2, 2), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv6_2')(conv6_1)
conv7_1 = Conv2D(128, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv7_1')(conv6_2)
conv7_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv7_padding')(conv7_1)
conv7_2 = Conv2D(256, (3, 3), strides=(2, 2), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv7_2')(conv7_1)
conv8_1 = Conv2D(128, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv8_1')(conv7_2)
conv8_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv8_padding')(conv8_1)
conv8_2 = Conv2D(256, (3, 3), strides=(2, 2), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv8_2')(conv8_1)
conv9_1 = Conv2D(128, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv9_1')(conv8_2)
conv9_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv9_padding')(conv9_1)
conv9_2 = Conv2D(256, (3, 3), strides=(2, 2), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv9_2')(conv9_1)
conv10_1 = Conv2D(128, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv10_1')(conv9_2)
conv10_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv10_padding')(conv10_1)
conv10_2 = Conv2D(256, (4, 4), strides=(1, 1), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv10_2')(conv10_1)
conv4_3_input = Input(tensor = conv4_3, name = 'conv4_3_input')
fc7_input = Input(tensor = fc7, name = 'fc7_input')
conv6_2_input = Input(tensor = conv6_2, name = 'conv6_2_input')
conv7_2_input = Input(tensor = conv7_2, name = 'conv7_2_input')
conv8_2_input = Input(tensor = conv8_2, name = 'conv8_2_input')
conv9_2_input = Input(tensor = conv9_2, name = 'conv9_2_input')
conv10_2_input = Input(tensor = conv10_2, name = 'conv10_2_input')
# Feed conv4_3 into the L2 normalization layer
conv4_3_norm = L2Normalization(gamma_init=20, name='conv4_3_norm')(conv4_3)
### Build the convolutional predictor layers on top of the base network
# We precidt `n_classes` confidence values for each box, hence the confidence predictors have depth `n_boxes * n_classes`
# Output shape of the confidence layers: `(batch, height, width, n_boxes * n_classes)`
conv4_3_norm_mbox_conf = Conv2D(n_boxes[0] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_3_norm_mbox_conf')(conv4_3_norm)
fc7_mbox_conf = Conv2D(n_boxes[1] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='fc7_mbox_conf')(fc7)
conv6_2_mbox_conf = Conv2D(n_boxes[2] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv6_2_mbox_conf')(conv6_2)
conv7_2_mbox_conf = Conv2D(n_boxes[3] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv7_2_mbox_conf')(conv7_2)
conv8_2_mbox_conf = Conv2D(n_boxes[4] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv8_2_mbox_conf')(conv8_2)
conv9_2_mbox_conf = Conv2D(n_boxes[5] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv9_2_mbox_conf')(conv9_2)
conv10_2_mbox_conf = Conv2D(n_boxes[6] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv10_2_mbox_conf')(conv10_2)
# We predict 4 box coordinates for each box, hence the localization predictors have depth `n_boxes * 4`
# Output shape of the localization layers: `(batch, height, width, n_boxes * 4)`
conv4_3_norm_mbox_loc = Conv2D(n_boxes[0] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_3_norm_mbox_loc')(conv4_3_norm)
fc7_mbox_loc = Conv2D(n_boxes[1] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='fc7_mbox_loc')(fc7)
conv6_2_mbox_loc = Conv2D(n_boxes[2] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv6_2_mbox_loc')(conv6_2)
conv7_2_mbox_loc = Conv2D(n_boxes[3] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv7_2_mbox_loc')(conv7_2)
conv8_2_mbox_loc = Conv2D(n_boxes[4] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv8_2_mbox_loc')(conv8_2)
conv9_2_mbox_loc = Conv2D(n_boxes[5] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv9_2_mbox_loc')(conv9_2)
conv10_2_mbox_loc = Conv2D(n_boxes[6] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv10_2_mbox_loc')(conv10_2)
### Generate the anchor boxes (called "priors" in the original Caffe/C++ implementation, so I'll keep their layer names)
# Output shape of anchors: `(batch, height, width, n_boxes, 8)`
conv4_3_norm_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[0], next_scale=scales[1], aspect_ratios=aspect_ratios[0],
two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[0], this_offsets=offsets[0], clip_boxes=clip_boxes,
variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv4_3_norm_mbox_priorbox')(conv4_3_norm_mbox_loc)
fc7_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[1], next_scale=scales[2], aspect_ratios=aspect_ratios[1],
two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[1], this_offsets=offsets[1], clip_boxes=clip_boxes,
variances=variances, coords=coords, normalize_coords=normalize_coords, name='fc7_mbox_priorbox')(fc7_mbox_loc)
conv6_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[2], next_scale=scales[3], aspect_ratios=aspect_ratios[2],
two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[2], this_offsets=offsets[2], clip_boxes=clip_boxes,
variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv6_2_mbox_priorbox')(conv6_2_mbox_loc)
conv7_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[3], next_scale=scales[4], aspect_ratios=aspect_ratios[3],
two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[3], this_offsets=offsets[3], clip_boxes=clip_boxes,
variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv7_2_mbox_priorbox')(conv7_2_mbox_loc)
conv8_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[4], next_scale=scales[5], aspect_ratios=aspect_ratios[4],
two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[4], this_offsets=offsets[4], clip_boxes=clip_boxes,
variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv8_2_mbox_priorbox')(conv8_2_mbox_loc)
conv9_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[5], next_scale=scales[6], aspect_ratios=aspect_ratios[5],
two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[5], this_offsets=offsets[5], clip_boxes=clip_boxes,
variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv9_2_mbox_priorbox')(conv9_2_mbox_loc)
conv10_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[6], next_scale=scales[7], aspect_ratios=aspect_ratios[6],
two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[6], this_offsets=offsets[6], clip_boxes=clip_boxes,
variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv10_2_mbox_priorbox')(conv10_2_mbox_loc)
### Reshape
# Reshape the class predictions, yielding 3D tensors of shape `(batch, height * width * n_boxes, n_classes)`
# We want the classes isolated in the last axis to perform softmax on them
conv4_3_norm_mbox_conf_reshape = Reshape((-1, n_classes), name='conv4_3_norm_mbox_conf_reshape')(conv4_3_norm_mbox_conf)
fc7_mbox_conf_reshape = Reshape((-1, n_classes), name='fc7_mbox_conf_reshape')(fc7_mbox_conf)
conv6_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv6_2_mbox_conf_reshape')(conv6_2_mbox_conf)
conv7_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv7_2_mbox_conf_reshape')(conv7_2_mbox_conf)
conv8_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv8_2_mbox_conf_reshape')(conv8_2_mbox_conf)
conv9_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv9_2_mbox_conf_reshape')(conv9_2_mbox_conf)
conv10_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv10_2_mbox_conf_reshape')(conv10_2_mbox_conf)
# Reshape the box predictions, yielding 3D tensors of shape `(batch, height * width * n_boxes, 4)`
# We want the four box coordinates isolated in the last axis to compute the smooth L1 loss
conv4_3_norm_mbox_loc_reshape = Reshape((-1, 4), name='conv4_3_norm_mbox_loc_reshape')(conv4_3_norm_mbox_loc)
fc7_mbox_loc_reshape = Reshape((-1, 4), name='fc7_mbox_loc_reshape')(fc7_mbox_loc)
conv6_2_mbox_loc_reshape = Reshape((-1, 4), name='conv6_2_mbox_loc_reshape')(conv6_2_mbox_loc)
conv7_2_mbox_loc_reshape = Reshape((-1, 4), name='conv7_2_mbox_loc_reshape')(conv7_2_mbox_loc)
conv8_2_mbox_loc_reshape = Reshape((-1, 4), name='conv8_2_mbox_loc_reshape')(conv8_2_mbox_loc)
conv9_2_mbox_loc_reshape = Reshape((-1, 4), name='conv9_2_mbox_loc_reshape')(conv9_2_mbox_loc)
conv10_2_mbox_loc_reshape = Reshape((-1, 4), name='conv10_2_mbox_loc_reshape')(conv10_2_mbox_loc)
# Reshape the anchor box tensors, yielding 3D tensors of shape `(batch, height * width * n_boxes, 8)`
conv4_3_norm_mbox_priorbox_reshape = Reshape((-1, 8), name='conv4_3_norm_mbox_priorbox_reshape')(conv4_3_norm_mbox_priorbox)
fc7_mbox_priorbox_reshape = Reshape((-1, 8), name='fc7_mbox_priorbox_reshape')(fc7_mbox_priorbox)
conv6_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv6_2_mbox_priorbox_reshape')(conv6_2_mbox_priorbox)
conv7_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv7_2_mbox_priorbox_reshape')(conv7_2_mbox_priorbox)
conv8_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv8_2_mbox_priorbox_reshape')(conv8_2_mbox_priorbox)
conv9_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv9_2_mbox_priorbox_reshape')(conv9_2_mbox_priorbox)
conv10_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv10_2_mbox_priorbox_reshape')(conv10_2_mbox_priorbox)
### Concatenate the predictions from the different layers
# Axis 0 (batch) and axis 2 (n_classes or 4, respectively) are identical for all layer predictions,
# so we want to concatenate along axis 1, the number of boxes per layer
# Output shape of `mbox_conf`: (batch, n_boxes_total, n_classes)
mbox_conf = Concatenate(axis=1, name='mbox_conf')([conv4_3_norm_mbox_conf_reshape,
fc7_mbox_conf_reshape,
conv6_2_mbox_conf_reshape,
conv7_2_mbox_conf_reshape,
conv8_2_mbox_conf_reshape,
conv9_2_mbox_conf_reshape,
conv10_2_mbox_conf_reshape])
# Output shape of `mbox_loc`: (batch, n_boxes_total, 4)
mbox_loc = Concatenate(axis=1, name='mbox_loc')([conv4_3_norm_mbox_loc_reshape,
fc7_mbox_loc_reshape,
conv6_2_mbox_loc_reshape,
conv7_2_mbox_loc_reshape,
conv8_2_mbox_loc_reshape,
conv9_2_mbox_loc_reshape,
conv10_2_mbox_loc_reshape])
# Output shape of `mbox_priorbox`: (batch, n_boxes_total, 8)
mbox_priorbox = Concatenate(axis=1, name='mbox_priorbox')([conv4_3_norm_mbox_priorbox_reshape,
fc7_mbox_priorbox_reshape,
conv6_2_mbox_priorbox_reshape,
conv7_2_mbox_priorbox_reshape,
conv8_2_mbox_priorbox_reshape,
conv9_2_mbox_priorbox_reshape,
conv10_2_mbox_priorbox_reshape])
# The box coordinate predictions will go into the loss function just the way they are,
# but for the class predictions, we'll apply a softmax activation layer first
mbox_conf_softmax = Activation('softmax', name='mbox_conf_softmax')(mbox_conf)
# Concatenate the class and box predictions and the anchors to one large predictions vector
# Output shape of `predictions`: (batch, n_boxes_total, n_classes + 4 + 8)
predictions = Concatenate(axis=2, name='predictions')([mbox_conf_softmax, mbox_loc, mbox_priorbox])
end_model = Model(inputs = [conv4_3_input,fc7_input,conv6_2_input,conv7_2_input,conv8_2_input,conv9_2_input,conv10_2_input], outputs = predictions)
return end_model
So when I try to train the model, it gives me the following error:
ValueError Traceback (most recent call last)
<ipython-input-11-467c36610dec> in <module>()
85 validation_data=val_gen_end,
86 validation_steps=ceil(val_dataset_size/batch_size),
---> 87 initial_epoch=initial_epoch)
88
89 # history = model.fit_generator(generator=train_generator,
c:\python36\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
85 warnings.warn('Update your `' + object_name +
86 '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 87 return func(*args, **kwargs)
88 wrapper._original_function = func
89 return wrapper
c:\python36\lib\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)
2040 outs = self.train_on_batch(x, y,
2041 sample_weight=sample_weight,
-> 2042 class_weight=class_weight)
2043
2044 if not isinstance(outs, list):
c:\python36\lib\site-packages\keras\engine\training.py in train_on_batch(self, x, y, sample_weight, class_weight)
1754 sample_weight=sample_weight,
1755 class_weight=class_weight,
-> 1756 check_batch_axis=True)
1757 if self.uses_learning_phase and not isinstance(K.learning_phase(), int):
1758 ins = x + y + sample_weights + [1.]
c:\python36\lib\site-packages\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_axis, batch_size)
1376 self._feed_input_shapes,
1377 check_batch_axis=False,
-> 1378 exception_prefix='input')
1379 y = _standardize_input_data(y, self._feed_output_names,
1380 output_shapes,
c:\python36\lib\site-packages\keras\engine\training.py in _standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
56 raise ValueError('Error when checking model ' +
57 exception_prefix + ': '
---> 58 'expected no data, but got:', data)
59 return []
60 if data is None:
ValueError: ('Error when checking model input: expected no data, but got:', [array([[[[1.62046947e+01, 0.00000000e+00, 0.00000000e+00, ...
Since 'end_model' has 7 inputs, I am passing a generator which will yield 7 input data appropriately.
Where am I going wrong? Please help!
Thank you.
You don't give x = Input(shape=(img_height, img_width, img_channels)) as input to Model that is why technically your model has no inputs. The other inputs you have are computed from x as you specify the tensor argument for example in Input(tensor = conv4_3, name = 'conv4_3_input') where conv4_3 is computed from x.
So you need specify the original input when creating the model:
end_model = Model(x, predictions)