I'm trying to get my first net running. The following error occures:
ValueError: Error when checking input: expected dense_125_input to have 2 dimensions, but got array with shape (192, 192, 1)
# ... images 300 px width/height
def preprocess_image(image):
image = tf.image.decode_jpeg(image, channels=1)
image = tf.image.resize(image, [192, 192])
image /= 255.0 # normalize to [0,1] range
return image
# creating the dataset
def prepare_data_train(path, label_from_filename, show=False):
images = []
labels = []
for file in glob.glob(path + '*.jpg'):
label = label_from_filename(file)
if label != False:
images.append(file)
labels.append(label)
path_ds = tf.data.Dataset.from_tensor_slices(images)
image_ds = path_ds.map(load_and_preprocess_image, num_parallel_calls=AUTOTUNE)
label_ds = tf.data.Dataset.from_tensor_slices(tf.cast(labels, tf.int32))
image_label_ds = tf.data.Dataset.zip((image_ds, label_ds))
# shuffling, batch size
BATCH_SIZE = 20
image_count = len(images)
# Setting a shuffle buffer size as large as the dataset ensures that the data is
# completely shuffled.
ds = image_label_ds.shuffle(buffer_size=image_count)
ds = ds.repeat()
ds = ds.batch(BATCH_SIZE)
# `prefetch` lets the dataset fetch batches, in the background while the model is training.
ds = ds.prefetch(buffer_size=AUTOTUNE)
keras_ds = ds.map(change_range)
image_batch, label_batch = next(iter(keras_ds))
return image_label_ds
# running ...
model = Sequential()
model.add(Dense(100, activation='relu', input_shape=(192,)))
model.add(Dense(2, activation='softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer=RMSprop(),
metrics=['accuracy'])
train_ds = prepare_data_train(path_train, label_from_filename, False)
validation_ds = prepare_data_test(path_test, label_from_filename, False)
# error when fitting
history = model.fit(train_ds,
batch_size=20,
epochs=10,
verbose=2,
validation_steps=2,
steps_per_epoch=2,
validation_data=validation_ds)
How to resolve it? Is reshaping needed, how?
Based on the images the net should predict 1 or 2.
The error comes from this line in your code:
model.add(Dense(100, activation='relu', input_shape=(192,)))
Namely, the shape of your input is 3 dimensional [width, height, channels] or [192, 192, 1]. So, if you really want to have that dense layer at the start, change the model definition to:
model = Sequential()
model.add(Flatten(input_shape=[192, 192, 1]))
model.add(Dense(100, activation='relu'))
model.add(Dense(2, activation='softmax'))
The line model.add(Flatten(input_shape=[192, 192, 1])) will flatten your input to be a single vector for each element in the batch. Then, you can proceed as you want.
This error comes when You put wrong train data to model.fit attribute. Check Your train_ds by print(train_ds) before passing it to model.fit. It should return something like:
<SkipDataset shapes: ((192, 192, 1), ()), types: (tf.float32, tf.int64)>
Related
I have a Keras model that takes an input layer with shape (n, 288, 1), of which 288 is the number of features. I am using a TensorFlow dataset tf.data.experimental.make_batched_features_dataset and my input layer will be (n, 1, 1) which means it gives one feature to the model at a time. How can I make an input tensor with the shape of (n, 288, 1)? I mean how can I use all my features in one tensor?
Here is my code for the model:
def _gzip_reader_fn(filenames):
"""Small utility returning a record reader that can read gzip'ed files."""
return tf.data.TFRecordDataset(filenames, compression_type='GZIP')
def _input_fn(file_pattern, tf_transform_output, batch_size):
"""Generates features and label for tuning/training.
Args:
file_pattern: input tfrecord file pattern.
tf_transform_output: A TFTransformOutput.
batch_size: representing the number of consecutive elements of returned
dataset to combine in a single batch
Returns:
A dataset that contains (features, indices) tuple where features is a
dictionary of Tensors, and indices is a single Tensor of label indices.
"""
transformed_feature_spec = (
tf_transform_output.transformed_feature_spec().copy())
dataset = tf.data.experimental.make_batched_features_dataset(
file_pattern=file_pattern,
batch_size=batch_size,
features=transformed_feature_spec,
reader=_gzip_reader_fn,
label_key=features.transformed_name(features.LABEL_KEY))
return dataset
def _build_keras_model(nb_classes=2, input_shape, learning_rate):
# Keras needs the feature definitions at compile time.
input_shape = (288,1)
input_layer = keras.layers.Input(input_shape)
padding = 'valid'
if input_shape[0] < 60:
padding = 'same'
conv1 = keras.layers.Conv1D(filters=6, kernel_size=7, padding=padding, activation='sigmoid')(input_layer)
conv1 = keras.layers.AveragePooling1D(pool_size=3)(conv1)
conv2 = keras.layers.Conv1D(filters=12, kernel_size=7, padding=padding, activation='sigmoid')(conv1)
conv2 = keras.layers.AveragePooling1D(pool_size=3)(conv2)
flatten_layer = keras.layers.Flatten()(conv2)
output_layer = keras.layers.Dense(units=nb_classes, activation='sigmoid')(flatten_layer)
model = keras.models.Model(inputs=input_layer, outputs=output_layer)
optimizer = keras.optimizers.Adam(lr=learning_rate)
# Compile Keras model
model.compile(loss='mean_squared_error', optimizer=optimizer, metrics=['accuracy'])
model.summary(print_fn=logging.info)
return model
This is the error:
tensorflow:Model was constructed with shape (None, 288, 1) for input Tensor("input_1:0", shape=(None, 288, 1), dtype=float32), but it was called on an input with incompatible shape (128, 1, 1).
Here is my training code:
def train():
#START
img_input = layers.Input(shape=(150, 150, 3))
x = layers.Conv2D(16, 3, activation='relu')(img_input)
x = layers.MaxPooling2D(2)(x)
x = layers.Conv2D(32, 3, activation='relu')(x)
x = layers.MaxPooling2D(2)(x)
x = layers.Conv2D(64, 3, activation='relu')(x)
x = layers.MaxPooling2D(2)(x)
x = layers.Flatten()(x)
x = layers.Dense(512, activation='relu')(x)
output = layers.Dense(1, activation='sigmoid')(x)
model = Model(img_input, output)
model.compile(loss='binary_crossentropy',
optimizer=RMSprop(lr=0.001),
metrics=['acc'])
#END
# All images will be rescaled by 1./255
train_datagen = ImageDataGenerator(rescale=1./255)
val_datagen = ImageDataGenerator(rescale=1./255)
bs = 20
# Flow training images in batches of 20 using train_datagen generator
train_generator = train_datagen.flow_from_directory(
train_dir, # This is the source directory for training images
target_size=(150, 150), # All images will be resized to 150x150
batch_size=bs,
# Since we use binary_crossentropy loss, we need binary labels
class_mode='binary')
# Flow validation images in batches of 20 using val_datagen generator
validation_generator = val_datagen.flow_from_directory(
validation_dir,
target_size=(150, 150),
batch_size=bs,
class_mode='binary')
history = model.fit(
train_generator,
steps_per_epoch=train_steps,
epochs=4,
validation_data=validation_generator,
validation_steps=val_steps,
verbose=1)
model.save_weights("trained_weights.h5")
Here is my prediction code:
def evaluate(imgpath):
if not os.path.isfile(imgpath):
print("No such file: {}".format(imgpath))
sys.exit(-1)
# START
img_input = layers.Input(shape=(150, 150, 3))
x = layers.Conv2D(16, 3, activation='relu')(img_input)
x = layers.MaxPooling2D(2)(x)
x = layers.Conv2D(32, 3, activation='relu')(x)
x = layers.MaxPooling2D(2)(x)
x = layers.Conv2D(64, 3, activation='relu')(x)
x = layers.MaxPooling2D(2)(x)
x = layers.Flatten()(x)
x = layers.Dense(512, activation='relu')(x)
output = layers.Dense(1, activation='sigmoid')(x)
model = Model(img_input, output)
model.compile(loss='binary_crossentropy',
optimizer=RMSprop(lr=0.001),
metrics=['acc'])
# END
model.load_weights("trained_weights.h5")
img = image.load_img(path=imgpath,grayscale=False,target_size=(150,150),color_mode='rgb')
img_arr = image.img_to_array(img)
test_img = np.expand_dims(img_arr, axis=0)
y_prob = model.predict(test_img)
classname = y_prob.argmax(axis=-1)
print("Class: ",classname)
return classname
I have a feeling that the error is somewhere in the last 5-6 lines of the evaluate function, where I am loading the image. The problem is that whenever I run the evaluate function for any image, my output is [0]. Even though the training went well, as seen in the image below.
enter image description here
Am I making some silly mistake somewhere?
since you have a single neuron as the top layer, when you do predictions you will get a single prediction. Since you have a single prediction using argmax will always return 0. What you need to do is to set a threshold value for the prediction for example
if yprob>=.5:
klass=1
else:
klass=0
Also as pointed out by Dr. Snoopy you should rescale your image by 1/255.
I want to convert my GPU model to TPU model. My GPU model takes two input image and has the same output for both images. I use custom data generator for this. There are two parallel networks; one for each input.
From this StackOverflow question, I tried to solve this but I failed.
Here is what I tried
dataset_12 = tf.data.Dataset.from_tensor_slices((left_train_paths, right_train_paths))
dataset_label = tf.data.Dataset.from_tensor_slices(train_labels)
dataset = tf.data.Dataset.zip((dataset_12, dataset_label)).batch(2).repeat()
Problem I am facing is that I am unable to decode the bi-input images.
Here is the decoder function
def decode_image(filename, label=None, image_size=(IMG_SIZE_h, IMG_SIZE_w)):
bits = tf.io.read_file(filename)
image = tf.image.decode_jpeg(bits, channels=3)
image = tf.cast(image, tf.float32) / 255.0
image = tf.image.resize(image, image_size)
#convert to numpy and do some cv2 staff mb?
if label is None:
return image
else:
return image, label
The issue is that I am unable to pass both images to the decoder function at the same time. How can I resolve this?
I also try to decode the image in following way
def decode(img,image_size=(IMG_SIZE_h, IMG_SIZE_w)):
bits = tf.io.read_file(img)
image = tf.image.decode_jpeg(bits, channels=3)
image = tf.cast(image, tf.float32) / 255.0
image = tf.image.resize(image, image_size)
return image
def decode_image(left, right,labels=None ):
if labels is None:
return decode(left),decode(right)
else:
return decode(left),decode(right),labels
image=tf.data.Dataset.from_tensor_slices((left_train_paths,right_train_paths,train_labels ))
dataset=image.map(decode_image, num_parallel_calls=AUTO).repeat().shuffle(512).batch(BATCH_SIZE).prefetch(AUTO)
dataset
The output is of dataset variable is now as
<PrefetchDataset shapes: ((None, 760, 760, 3), (None, 760, 760, 3), (None, 8)), types: (tf.float32, tf.float32, tf.int64)>
How can I pass it to the model now?
Model
def get_model():
left_tensor = Input(shape=(IMG_SIZE_h,IMG_SIZE_w,3))
right_tensor = Input(shape=(IMG_SIZE_h,IMG_SIZE_w,3))
left_model = EfficientNetB3(input_shape = (img_shape,img_shape,3), include_top = False, weights = 'imagenet',input_tensor=left_tensor)
right_model = EfficientNetB3(input_shape = (img_shape,img_shape,3), include_top = False, weights = 'imagenet',input_tensor=right_tensor)
con = concatenate([left_model.output, right_model.output])
GAP= GlobalAveragePooling2D()(con)
out = Dense(8, activation = 'sigmoid')(GAP)
model =Model(inputs=[left_input, right_input], outputs=out)
return model
I found a pretty elegant solution. I will explain step by step since may be a bit different of what you thought:
When decoding the images stack both images in a single tensor so the input tensor will be of shape [2, IMAGE_H, IMAGE_W, 3]
def decode_single(im_path, image_size):
bits = tf.io.read_file(im_path)
image = tf.image.decode_jpeg(bits, channels=3)
image = tf.cast(image, tf.float32) / 255.0
image = tf.image.resize(image, image_size)
return image
# Note that the image paths are packed in a tuple, and we unpack them inside the function
def decode(paths, label=None, image_size=(128, 128)):
image_path1, image_path2 = paths
im1 = decode_single(image_path1, image_size)
im2 = decode_single(image_path2, image_size)
images = tf.stack([im1, im2])
if label is not None:
return images, label
return images
I declare the data pipeline so the paths are packed in a tuple.
label_ds = ...
ds = tf.data.Dataset.from_tensor_slices((left_paths, right_paths))
ds = tf.data.Dataset.zip((ds, label_ds)) # returns as ((im_path1, im_path2), label)) not (im_path1, im_path2, label)
ds = ds.map(decode).batch(4)
print(ds)
# Out: <BatchDataset shapes: ((None, 2, 128, 128, 3), ((None,),)), types: (tf.float32, (tf.int32,))>
Since we are feeding batches of two images (None, 2, 128, 128, 3). Declare the model with a single input of shape (2, HEIGHT, WIDTH, 3) and then we split the input in the two images:
def get_model():
input_layer = Input(shape=(2, IMAGE_H,IMAGE_W,3))
# Split into two images
right_image, left_image = Lambda(lambda x: tf.split(x, 2, axis=1))(input_layer)
right_image = Reshape([IMAGE_H, IMAGE_W, 3])(right_image)
left_image = Reshape([IMAGE_H, IMAGE_W, 3])(left_image)
# Replace by EfficientNets
left_model = Conv2D(64, 3)(left_image)
right_model = Conv2D(64, 3)(right_image)
con = Concatenate(-1)([left_model, right_model])
GAP = GlobalAveragePooling2D()(con)
out = Dense(8, activation = 'sigmoid')(GAP)
model = tf.keras.Model(inputs=input_layer, outputs=out)
return model
Finally compile and train the model as usual:
model = get_model()
model.compile(...)
model.fit(ds, epochs=10)
I am trying to build my first classifier on tensorflow 1.10 using tf.data.dataset as an input to a Keras.sequential but the fit method returns the following error:
ValueError: Error when checking target: expected dense_1 to have 2 dimensions, but got array with shape (None,)
First I initialized 2 tf.data.Dataset with the filenames of my dataset
#Initialize dataset directories location and parameters
image_size=50
batch_size=10
mortys_file_pattern = r'C:\Users\Jonas\Downloads\mortys\*'
ricks_file_pattern = r'C:\Users\Jonas\Downloads\ricks\*'
#Each tensor in those dataset will be a filename for a specific image
mortys_dataset = tf.data.Dataset.list_files(mortys_file_pattern)
ricks_dataset = tf.data.Dataset.list_files(ricks_file_pattern)
Then I used the map method to prepare my datasets
#Now, each dataset entry will contain 2 tensors: image,label
mortys_dataset.map(lambda filename: load_resize_label(filename, "morty"))
ricks_dataset.map(lambda filename: load_resize_label(filename, "rick"))
def load_resize_label(filename, label):
image_string = tf.read_file(filename)
image_decoded = tf.image.decode_jpeg(image_string)
image_resized = tf.image.resize_images(image_decoded, [image_size, image_size])
image_resized=image_resized/255.0
return image_resized, tf.convert_to_tensor(label)
Then, I concatenate the datasets into one final dataset and initialize the batch size
#Merge the datasets
dataset = mortys_dataset.concatenate(ricks_dataset)
dataset = dataset.batch(batch_size)
dataset = dataset.repeat()
In the end, use the compile and fit method of the model object
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit(dataset, epochs=10, steps_per_epoch=30)
(Full code bellow)
I'm using:
Windows 10 64bits
cudnn-9.0-windows10-x64-v7.2.1.38
cuda_9.0.176_win10
tensorflow-gpu 1.10.0
import tensorflow as tf
from tensorflow import keras
image_size=50
batch_size=10
# Reads an image from a file, decodes it into a dense tensor, resizes it
# to a fixed shape.
def load_resize_label(filename, label):
image_string = tf.read_file(filename)
image_decoded = tf.image.decode_jpeg(image_string)
image_resized = tf.image.resize_images(image_decoded, [image_size, image_size])
image_resized=image_resized/255.0
return image_resized, tf.convert_to_tensor(label)
#Initialize dataset directories location
mortys_file_pattern = r'C:\Users\Jonas\Downloads\mortys\*'
ricks_file_pattern = r'C:\Users\Jonas\Downloads\ricks\*'
#Each tensor in those dataset will be a filename for a specific image
mortys_dataset = tf.data.Dataset.list_files(mortys_file_pattern)
ricks_dataset = tf.data.Dataset.list_files(ricks_file_pattern)
#Now, each dataset entry will contain 2 tensors: image,label
mortys_dataset = mortys_dataset.map(lambda filename: load_resize_label(filename, "morty"))
ricks_dataset = ricks_dataset.map(lambda filename: load_resize_label(filename, "rick"))
#Merge the datasets
dataset = mortys_dataset.concatenate(ricks_dataset)
dataset = dataset.batch(batch_size)
dataset = dataset.repeat()
#the CNN architecture
model = keras.Sequential([
keras.layers.Convolution2D(filters=64, kernel_size=2, padding='same', activation='relu', input_shape=(image_size, image_size,3)),
keras.layers.MaxPool2D(pool_size=2),
keras.layers.BatchNormalization(),
keras.layers.Flatten(),
keras.layers.Dense(128, activation=tf.nn.relu),
keras.layers.Dropout(0.3),
keras.layers.Dense(2, activation=tf.nn.softmax)
])
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit(dataset, epochs=10, steps_per_epoch=30)
Traceback:
Traceback (most recent call last):
File "C:/Users/Jonas/PycharmProjects/learning/lesson2.py", line 47, in <module>
model.fit(dataset, epochs=10, steps_per_epoch=30)
File "C:\Users\Jonas\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1278, in fit
validation_split=validation_split)
File "C:\Users\Jonas\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\keras\engine\training.py", line 917, in _standardize_user_data
exception_prefix='target')
File "C:\Users\Jonas\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\keras\engine\training_utils.py", line 182, in standardize_input_data
'with shape ' + str(data_shape))
ValueError: Error when checking target: expected dense_1 to have 2 dimensions, but got array with shape (None,)
You're missing some '=' in your code.
Each dataset operation should be like :
dataset = dataset.some_ops(...)
Here is how your code should look:
import tensorflow as tf
from tensorflow import keras
image_size=50
batch_size=10
# Reads an image from a file, decodes it into a dense tensor, resizes it
# to a fixed shape.
def load_resize_label(filename, label):
image_string = tf.read_file(filename)
image_decoded = tf.image.decode_jpeg(image_string)
image_resized = tf.image.resize_images(image_decoded, [image_size, image_size])
image_resized=image_resized/255.0
if label == 'morty':
label = [0, 1]
elif label == 'rick':
label = [1, 0]
else:
raise ValueError(label)
return image_resized, tf.convert_to_tensor(label)
#Initialize dataset directories location
mortys_file_pattern = r'C:\Users\Jonas\Downloads\mortys\*'
ricks_file_pattern = r'C:\Users\Jonas\Downloads\ricks\*'
#Each tensor in those dataset will be a filename for a specific image
mortys_dataset = tf.data.Dataset.list_files(mortys_file_pattern)
ricks_dataset = tf.data.Dataset.list_files(ricks_file_pattern)
#Now, each dataset entry will contain 2 tensors: image,label
mortys_dataset = mortys_dataset.map(lambda filename: load_resize_label(filename, "morty"))
ricks_dataset = ricks_dataset.map(lambda filename: load_resize_label(filename, "rick"))
#Merge the datasets
dataset = mortys_dataset.concatenate(ricks_dataset)
dataset = dataset.batch(batch_size)
dataset = dataset.repeat()
#the CNN architecture
model = keras.Sequential([
keras.layers.Convolution2D(filters=64, kernel_size=2, padding='same', activation='relu', input_shape=(image_size, image_size, 3)),
keras.layers.MaxPool2D(pool_size=2),
keras.layers.BatchNormalization(),
keras.layers.Flatten(),
keras.layers.Dense(128, activation=tf.nn.relu),
keras.layers.Dropout(0.3),
keras.layers.Dense(2, activation=tf.nn.softmax)
])
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.fit(dataset, epochs=10, steps_per_epoch=30)
Also, I advise you to use dataset.prefetch(None) and use the num_parallel_calls argument in the map function. Here is why. TLDR: it's faster.
I have time series data input 72 value by separate last 6 value for test prediction. I want to use CONV1D with LSTM.
This is my code.
df = pd.read_csv('D://data.csv',
engine='python')
df['DATE_'] = pd.to_datetime(df['DATE_']) + MonthEnd(1)
df = df.set_index('DATE_')
df.head()
split_date = pd.Timestamp('03-01-2015')
train = df.loc[:split_date, ['COLUMN3DATA']]
test = df.loc[split_date:, ['COLUMN3DATA']]
sc = MinMaxScaler()
train_sc = sc.fit_transform(train)
test_sc = sc.transform(test)
X_train = train_sc[:-1]
y_train = train_sc[1:]
X_test = test_sc[:-1]
y_test = test_sc[1:]
################### Convolution #######################
X_train_t = X_train[None,:]
print(X_train_t.shape)
X_test_t = X_test[:, None]
K.clear_session()
model = Sequential()
model.add(Conv1D(6, 3, activation='relu', input_shape=(12,1)))
model.add(LSTM(6, input_shape=(1,3), return_sequences=True))
model.add(LSTM(3))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam' )
model.summary()
model.fit(X_train_t, y_train, epochs=400, batch_size=10, verbose=1)
y_pred = model.predict(X_test_t)
When I run it show error like this
ValueError: Error when checking input: expected conv1d_1_input to have shape (None, 12, 1) but got array with shape (1, 64, 1)
How to use conv1D with lstm
The problem is between your input data and your input shape.
You said in the model that your input shape is (12,1) (= batch_shape=(None,12,1))
But your data X_train_t has shape (1,64,1).
Either you fix the input shape of the model, or you fix your data if this is not the expected shape.
For variable lengths/timesteps, you can use input_shape=(None,1).
You don't need an input_shape in the second layer.