How to fine tune VGG16 with ImageNet dataset without error? - python

I am new in computer vision, and I want to fine tune VGG16 with imagenet64 dataset. But after downloading imagenet64 dataset with below code and then fine tuning, I got an error. Please help me to solve this error. thank you very much.
import os
import shutil
from keras.preprocessing.image import ImageDataGenerator
from keras.applications import VGG16
from keras import models, layers, optimizers
import matplotlib.image as mpimg
import math
checkpoints = '/content/drive/MyDrive/colab_files/imagenet64/'
if not os.path.exists('imagenet64'):
if not os.path.exists(checkpoints + 'imagenet64.tar'):
print("Downloading archive...")
os.chdir(checkpoints)
!wget https://pjreddie.com/media/files/imagenet64.tar
os.chdir('/content/')
print("Copying to local runtime...")
shutil.copy(checkpoints + 'imagenet64.tar', './imagenet64.tar')
print("Uncompressing...")
!tar -xf imagenet64.tar
print("Data ready!")
train_dir='/content/imagenet64/train'
val_dir='/content/imagenet64/val'
batch_size=40
epochs=30
train_datagen= ImageDataGenerator()
val_datagen= ImageDataGenerator()
train_generator = train_datagen.flow_from_directory(
train_dir,
target_size = (224,224),
batch_size = batch_size,
class_mode = 'categorical',
subset='training'
)
validation_generator = val_datagen.flow_from_directory(
val_dir,
target_size = (224,224),
batch_size = batch_size,
class_mode = 'categorical',
subset='training'
)
model_fine=model_n
model_fine.trainable = True
set_trainable = False
for layer in model_fine.layers:
if layer.name=='block5_conv1':
set_trainable = True
if set_trainable == True:
layer.trainable = True
else:
layer.trainable = False
model_fine.compile(loss='categorical_crossentropy', optimizer=optimizers.Nadam(lr=1e-5), metrics=['acc'])
h = model_fine.fit(
train_generator,
steps_per_epoch = train_generator.samples // batch_size,
epochs = epochs,
validation_data = validation_generator,
validation_steps = validation_generator.samples // batch_size,
)
I tried to fine tune VGG16 with imagenet64 dataset and I expect to fine tune model. But I got an error:
Found 1281166 images belonging to 1000 classes.
Found 50000 images belonging to 1000 classes.
/usr/local/lib/python3.8/dist-packages/keras/optimizers/optimizer_v2/nadam.py:78: UserWarning: The lr argument is deprecated, use learning_rate instead.
super(Nadam, self).init(name, **kwargs)
Epoch 1/30
StagingError Traceback (most recent call last)
in
34
35 model_fine.compile(loss='categorical_crossentropy', optimizer=optimizers.Nadam(lr=1e-5), metrics=['acc'])
---> 36 h = model_fine.fit(
37 train_generator,
38 steps_per_epoch = train_generator.samples // batch_size,
1 frames
/usr/local/lib/python3.8/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
1125 except Exception as e: # pylint:disable=broad-except
1126 if hasattr(e, "ag_error_metadata"):
-> 1127 raise e.ag_error_metadata.to_exception(e)
1128 else:
1129 raise
StagingError: in user code:
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1051, in train_function *
return step_function(self, iterator)
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1040, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 1030, in run_step **
outputs = model.train_step(data)
File "/usr/local/lib/python3.8/dist-packages/keras/engine/training.py", line 893, in train_step
self.optimizer.minimize(loss, self.trainable_variables, tape=tape)
File "/usr/local/lib/python3.8/dist-packages/keras/optimizers/optimizer_v2/optimizer_v2.py", line 539, in minimize
return self.apply_gradients(grads_and_vars, name=name)
File "/usr/local/lib/python3.8/dist-packages/keras/optimizers/optimizer_v2/optimizer_v2.py", line 646, in apply_gradients
self._create_all_weights(var_list)
File "/usr/local/lib/python3.8/dist-packages/keras/optimizers/optimizer_v2/optimizer_v2.py", line 860, in _create_all_weights
self._create_slots(var_list)
File "/usr/local/lib/python3.8/dist-packages/keras/optimizers/optimizer_v2/nadam.py", line 87, in _create_slots
var_dtype = var_list[0].dtype.base_dtype
IndexError: list index out of range

Related

ValueError of Input and Output values during LSTM training

I was trying to implement a basic LSTM network using some random data, and I got the following error during execution of the code
'''
Traceback (most recent call last):
File "C:/Users/dell/Desktop/test run for LSTM thingy.py", line 39, in <module>
history = model.fit(x_train, y_train, epochs=1, batch_size=16, verbose=1)
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\dell\AppData\Local\Temp\__autograph_generated_fileu1zdna1b.py", line 15, in tf__train_function
retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
ValueError: in user code:
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 1051, in train_function *
return step_function(self, iterator)
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 1040, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 1030, in run_step **
outputs = model.train_step(data)
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 890, in train_step
loss = self.compute_loss(x, y, y_pred, sample_weight)
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training.py", line 948, in compute_loss
return self.compiled_loss(
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\compile_utils.py", line 201, in __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\losses.py", line 139, in __call__
losses = call_fn(y_true, y_pred)
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\losses.py", line 243, in call **
return ag_fn(y_true, y_pred, **self._fn_kwargs)
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\losses.py", line 1787, in categorical_crossentropy
return backend.categorical_crossentropy(
File "C:\Users\dell\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\backend.py", line 5119, in categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
ValueError: Shapes (None, 133, 1320) and (None, 133, 5) are incompatible
'''
This is how my code looks like at the moment:
import tensorflow as tf
x_train = tf.random.normal((28, 133, 1320))
y_train = tf.random.normal((28, 133, 1320))
model = tf.keras.Sequential()
model.add(tf.keras.layers.LSTM(5,activation='tanh',recurrent_activation='sigmoid', input_shape=(x_train.shape[1],x_train.shape[2]),return_sequences=True))
model.add(tf.keras.layers.Dense(5, activation= "softmax"))
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001), loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()
history = model.fit(x_train, y_train, epochs=1, batch_size=16, verbose=1)
Could anyone help me in debugging this code, as I need to use something similar in another side project which involves both X and Y input data of similar shapes, and I was not able to find a solution to the problem. I know it has something to do with the loss function, but thats all.
Shape of Y - (28, 133, 1320)
Shape of X - (28, 133, 1320)
Categories needed - 5

You are currently trying to do categorical classification with 5 classes but y has the shape (28, 133, 1320). It does not work like that. Also, when you use categorical_crossentropy, you need one-hot-encoded labels. Here is a working example as orientation:
import tensorflow as tf
x_train = tf.random.normal((28, 133, 1320))
# one-hot encoded labels
y_train = tf.keras.utils.to_categorical(tf.random.uniform((28,), maxval=5, dtype=tf.int32))
model = tf.keras.Sequential()
model.add(tf.keras.layers.LSTM(5,activation='tanh',recurrent_activation='sigmoid', input_shape=(x_train.shape[1],x_train.shape[2]), return_sequences=False))
model.add(tf.keras.layers.Dense(5, activation= "softmax"))
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001), loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()
history = model.fit(x_train, y_train, epochs=1, batch_size=16, verbose=1)

Using Keras Without GPU

I want to train a Neural Network using Keras but when I want to build the model I get the following error
2022-03-14 09:38:10.526372: E tensorflow/stream_executor/cuda/cuda_driver.cc:271] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
2022-03-14 09:38:10.526465: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (HSKP02): /proc/driver/nvidia/version does not exist
2022-03-14 09:38:10.527391: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
I tried to solve this error by writing
import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ['CUDA_VISIBLE_DEVICES'] = "-1"
before importing Keras but I still get this error. After this error my code fits the data with the validation set with model.fit() but I get another error
Traceback (most recent call last):
File "shallownet_ex.py", line 44, in <module>
H = model.fit(trainX, trainY, validation_data=(testX, testY), batch_size=32, epochs=100, verbose=1)
File ".../venv/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File ".../venv/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 1147, in autograph_handler
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 1021, in train_function *
return step_function(self, iterator)
File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 1010, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 1000, in run_step **
outputs = model.train_step(data)
File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 860, in train_step
loss = self.compute_loss(x, y, y_pred, sample_weight)
File ".../venv/lib/python3.8/site-packages/keras/engine/training.py", line 918, in compute_loss
return self.compiled_loss(
File ".../venv/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 201, in __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
File ".../venv/lib/python3.8/site-packages/keras/losses.py", line 141, in __call__
losses = call_fn(y_true, y_pred)
File ".../venv/lib/python3.8/site-packages/keras/losses.py", line 245, in call **
return ag_fn(y_true, y_pred, **self._fn_kwargs)
File ".../venv/lib/python3.8/site-packages/keras/losses.py", line 1789, in categorical_crossentropy
return backend.categorical_crossentropy(
File ".../venv/lib/python3.8/site-packages/keras/backend.py", line 5083, in categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
ValueError: Shapes (None, 4) and (None, 3) are incompatible
The code I'm using looks like this
import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ['CUDA_VISIBLE_DEVICES'] = "-1"
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from preprocesing import ImageToArrayPreprocessor, SimplePreprocesssor
from datasets import SimpleDatasetLoader
from neuralnetworks.conv import ShallowNet
from keras.optimizers import gradient_descent_v2
from imutils import paths
import argparse
ap = argparse.ArgumentParser()
ap.add_argument("-d", "--dataset", required=True, help="path to input dataset")
args = vars(ap.parse_args())
imagePaths = list(paths.list_images(args["dataset"]))
sp = SimplePreprocesssor(32, 32)
iap = ImageToArrayPreprocessor()
sdl = SimpleDatasetLoader(preprocessors=[sp, iap])
(data, labels) = sdl.load(imagePaths, verbose=500)
data = data.astype("float") / 255.0
(trainX, testX, trainY, testY) = train_test_split(data, labels, test_size=0.25, random_state=42)
trainY = LabelBinarizer().fit_transform(trainY)
testY = LabelBinarizer().fit_transform(testY)
opt = gradient_descent_v2.SGD(learning_rate=0.005)
model = ShallowNet.build(width=32, height=32, depth=3, classes=3)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=['acc'])
H = model.fit(trainX, trainY, validation_data=(testX, testY), batch_size=32, epochs=100, verbose=1)
The simpleloader is a function that just loads the images and the simplepreprocesor just resizes the images and I think the error is inside the shallownet.py that looks like this
import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
from keras.models import Sequential
from keras.layers.convolutional import Conv2D
from keras.layers.core import Activation, Flatten, Dense
from keras import backend as K
class ShallowNet():
#staticmethod
def build(width, height, depth, classes):
model = Sequential()
inputShape = (height, width, depth)
if K.image_data_format() == "channels_first":
inputShape = (depth, height, width)
model.add(Conv2D(32, (3, 3), padding="same", input_shape=inputShape))
model.add(Activation("relu"))
model.add(Flatten())
model.add(Dense(classes))
model.add(Activation("softmax"))
return model
What I deduce is that as my computer doesn't have a GPU I can't perform the training and then I can't fit the model. There is a way to perform this training?

Convolution neural network for image segmentation with tensorflow

I am trying to make my first neural network using Tensorflow. I have some medical images and my goal is to segment them. I can't find what I am doing wrong. Here is the error :
2021-05-08 14:33:15.249134: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (registered 2)
Epoch 1/50
Traceback (most recent call last):
File "C:/Users/tompi/PycharmProjects/ProjetDeepLearning/test.py", line 185, in <module>
history = model.fit(X_train, Y_train, epochs=epochs,
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1100, in fit
tmp_logs = self.train_function(iterator)
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\eager\def_function.py", line 828, in __call__
result = self._call(*args, **kwds)
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\eager\def_function.py", line 871, in _call
self._initialize(args, kwds, add_initializers_to=initializers)
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\eager\def_function.py", line 725, in _initialize
self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\eager\function.py", line 2969, in _get_concrete_function_internal_garbage_collected
graph_function, _ = self._maybe_define_function(args, kwargs)
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\eager\function.py", line 3361, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\eager\function.py", line 3196, in _create_graph_function
func_graph_module.func_graph_from_py_func(
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\framework\func_graph.py", line 990, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\eager\def_function.py", line 634, in wrapped_fn
out = weak_wrapped_fn().__wrapped__(*args, **kwds)
File "C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\framework\func_graph.py", line 977, in wrapper
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\keras\engine\training.py:805 train_function *
return step_function(self, iterator)
C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\keras\engine\training.py:795 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\keras\engine\training.py:788 run_step **
outputs = model.train_step(data)
C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\keras\engine\training.py:754 train_step
y_pred = self(x, training=True)
C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:998 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
C:\Users\tompi\anaconda3\envs\tf2.4\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:204 assert_input_compatibility
raise ValueError('Layer ' + layer_name + ' expects ' +
ValueError: Layer sequential expects 1 input(s), but it received 44 input tensors. Inputs received: ...
Below my code :
import tensorflow as tf
import pandas as pd
import numpy as np
import tensorflow.keras
import segmentation_models as sm
import os
import cv2
import Metrics as metrics # a python file
import matplotlib.pyplot as plt
from tensorflow.keras import datasets, layers, models
from sklearn.model_selection import train_test_split
width = 672
height = 448
dataframe = []
def normalize(path):
image = cv2.imread(path)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image = cv2.resize(image, (width, height))
# newSize = np.zeros((height, width, 3))
# newSize[:, :, 0] = image[:, :]
# newSize[:, :, 1] = image[:, :]
# newSize[:, :, 2] = image[:, :]
return image
def createDataset():
for folder in os.listdir(imagesPath):
for imageName in os.listdir(imagesPath + folder):
image = normalize(imagesPath + folder + "/" + imageName)
dataframe.append([folder, imageName, image])
createDataset()
df = pd.DataFrame(dataframe, columns=['Folder', 'Name', 'Image'])
def getImagesFromFolder(folder):
L = []
n, p = np.shape(df)
for i in range(n):
if df['Folder'][i] == folder:
L.append(df.iloc[i][2])
return L
originalImages = getImagesFromFolder('Original')
maskImages = getImagesFromFolder('Mask')
X_train, X_test, Y_train, Y_test = train_test_split(originalImages, maskImages, train_size=0.8, random_state=42)
classes = 3
activation = "softmax"
lr = 0.0001
loss = sm.losses.jaccard_loss
metrics = training_metrics = [
sm.metrics.IOUScore(threshold=0.5),
sm.metrics.FScore(threshold=0.5),
sm.metrics.Precision(),
sm.metrics.Recall(),
metrics.dice_coef
]
batch_size = 3
epochs = 50
callbacks = [tensorflow.keras.callbacks.ReduceLROnPlateau()]
I am using a very simple Unet :
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(height, width, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.summary()
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10))
model.summary()
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
history = model.fit(X_train, Y_train, epochs=epochs,
validation_data=(X_test, Y_test))
The error says that the input receives 44 tensors which is the number of images in X_train and Y_train (44, 448, 672, 3) but I don't know what I am doing wrong, I saw several posts having the same shape and it worked. Can anyone help we. It would be greatly appreciated.
Thanks.

I found out what was the error. The type of my variables X_train, Y_train, X_test, Y_test was list and not numpy.ndarray because of my function getImagesFromFolder. I had to return np.array(L) to make it run.

Input 0 of layer dense is incompatible with the layer: expected axis -1 of input shape to have value 8192 but received input with shape (None, 61608)

I am trying to create an image processing CNN. I am using VGG16 to speed up some of the learning process. The creation of my CNN below works to the point of training and saving the model & weights. The issue occurs when I try to run a predict function after loading in the model.
image_gen = ImageDataGenerator()
train = image_gen.flow_from_directory('./data/train', class_mode='categorical', shuffle=False, batch_size=10, target_size=(151, 136))
val = image_gen.flow_from_directory('./data/validate', class_mode='categorical', shuffle=False, batch_size=10, target_size=(151, 136))
pretrained_model = VGG16(include_top=False, input_shape=(151, 136, 3), weights='imagenet')
pretrained_model.summary()
vgg_features_train = pretrained_model.predict(train)
vgg_features_val = pretrained_model.predict(val)
train_target = to_categorical(train.labels)
val_target = to_categorical(val.labels)
model = Sequential()
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dropout(0.5))
model.add(BatchNormalization())
model.add(Dense(2, activation='softmax'))
model.compile(optimizer='rmsprop', metrics=['accuracy'], loss='categorical_crossentropy')
target_dir = './models/weights-improvement'
if not os.path.exists(target_dir):
os.mkdir(target_dir)
checkpoint = ModelCheckpoint(filepath=target_dir + 'weights-improvement-{epoch:02d}-{val_accuracy:.2f}.hdf5', monitor='val_accuracy', verbose=1, save_best_only=True, mode='max')
callbacks_list = [checkpoint]
model.fit(vgg_features_train, train_target, epochs=100, batch_size=8, validation_data=(vgg_features_val, val_target), callbacks=callbacks_list)
model.save('./models/model')
model.save_weights('./models/weights')
I have this predict function, that I would like to load in an image, and then return the categorisation of this image that the model gives.
from keras.preprocessing.image import load_img, img_to_array
def predict(file):
x = load_img(file, target_size=(151,136,3))
x = img_to_array(x)
print(x.shape)
print(x.shape)
x = np.expand_dims(x, axis=0)
array = model.predict(x)
result = array[0]
if result[0] > result[1]:
if result[0] > 0.9:
print("Predicted answer: Buy")
answer = 'buy'
print(result)
print(array)
else:
print("Predicted answer: Not confident")
answer = 'n/a'
print(result)
else:
if result[1] > 0.9:
print("Predicted answer: Sell")
answer = 'sell'
print(result)
else:
print("Predicted answer: Not confident")
answer = 'n/a'
print(result)
return answer
The issue I am experiencing is when I run this predict function, I get the following error.
File "predict-binary.py", line 24, in predict
array = model.predict(x)
File ".venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1629, in predict
tmp_batch_outputs = self.predict_function(iterator)
File ".venv\lib\site-packages\tensorflow\python\eager\def_function.py", line 828, in __call__
result = self._call(*args, **kwds)
File ".venv\lib\site-packages\tensorflow\python\eager\def_function.py", line 871, in _call
self._initialize(args, kwds, add_initializers_to=initializers)
File ".venv\lib\site-packages\tensorflow\python\eager\def_function.py", line 725, in _initialize
self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
File ".venv\lib\site-packages\tensorflow\python\eager\function.py", line 2969, in _get_concrete_function_internal_garbage_collected
graph_function, _ = self._maybe_define_function(args, kwargs)
File ".venv\lib\site-packages\tensorflow\python\eager\function.py", line 3361, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File ".venv\lib\site-packages\tensorflow\python\eager\function.py", line 3196, in _create_graph_function
func_graph_module.func_graph_from_py_func(
File ".venv\lib\site-packages\tensorflow\python\framework\func_graph.py", line 990, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File ".venv\lib\site-packages\tensorflow\python\eager\def_function.py", line 634, in wrapped_fn
out = weak_wrapped_fn().__wrapped__(*args, **kwds)
File ".venv\lib\site-packages\tensorflow\python\framework\func_graph.py", line 977, in wrapper
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
.venv\lib\site-packages\tensorflow\python\keras\engine\training.py:1478 predict_function *
return step_function(self, iterator)
.venv\lib\site-packages\tensorflow\python\keras\engine\training.py:1468 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
.venv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
.venv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
.venv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
.venv\lib\site-packages\tensorflow\python\keras\engine\training.py:1461 run_step **
outputs = model.predict_step(data)
.venv\lib\site-packages\tensorflow\python\keras\engine\training.py:1434 predict_step
return self(x, training=False)
.venv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:1012 __call__
outputs = call_fn(inputs, *args, **kwargs)
.venv\lib\site-packages\tensorflow\python\keras\engine\sequential.py:375 call
return super(Sequential, self).call(inputs, training=training, mask=mask)
.venv\lib\site-packages\tensorflow\python\keras\engine\functional.py:424 call
return self._run_internal_graph(
.venv\lib\site-packages\tensorflow\python\keras\engine\functional.py:560 _run_internal_graph
outputs = node.layer(*args, **kwargs)
.venv\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:998 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
.venv\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:255 assert_input_compatibility
raise ValueError(
ValueError: Input 0 of layer dense is incompatible with the layer: expected axis -1 of input shape to have value 8192 but received input with shape (None, 61608)
I'm assuming I need to change something between the Flatten() and Dense() layers of my model, but I'm not sure what. I attempted to add model.add(Dense(61608, activation='relu)) between these two as that seemed to be what was suggested in another post I saw (cannot find link now), but it lead to the same error. (I tried it with 8192 instead of 61608 as well). Any help is appreciated, thanks.
EDIT #1:
Changing the model creation/training code as I think it was suggested by Gerry P to this
img_shape = (151,136,3)
base_model=VGG19( include_top=False, input_shape=img_shape, pooling='max', weights='imagenet' )
x=base_model.output
x=Dense(100, activation='relu')(x)
x=Dropout(0.5)(x)
x=BatchNormalization(axis=-1, momentum=0.99, epsilon=0.001)(x)
output=Dense(2, activation='softmax')(x)
model=Model(inputs=base_model.input, outputs=output)
image_gen = ImageDataGenerator()
train = image_gen.flow_from_directory('./data/train', class_mode='categorical', shuffle=False, batch_size=10, target_size=(151, 136))
val = image_gen.flow_from_directory('./data/validate', class_mode='categorical', shuffle=False, batch_size=10, target_size=(151, 136))
vgg_features_train = base_model.predict(train)
vgg_features_val = base_model.predict(val)
train_target = to_categorical(train.labels)
val_target = to_categorical(val.labels)
model.compile(optimizer='rmsprop', metrics=['accuracy'], loss='categorical_crossentropy')
model.fit(vgg_features_train, train_target, epochs=100, batch_size=8, validation_data=(vgg_features_val, val_target), callbacks=callbacks_list)
This resulted in a different input shape error of File "train-binary.py", line 37, in <module> model.fit(vgg_features_train, train_target, epochs=100, batch_size=8, validation_data=(vgg_features_val, val_target), callbacks=callbacks_list) ValueError: Input 0 is incompatible with layer model: expected shape=(None, 151, 136, 3), found shape=(None, 512)

your model is expecting to see an input for model.predict that has the same dimensions as it was trained on. In this case it is the dimensions of vgg_features_train.The input to model.predict that you are generating is for the input to the VGG model. You are essentially trying to do transfer learning so I suggest you proceed as below
base_model=tf.keras.applications.VGG19( include_top=False, input_shape=img_shape, pooling='max', weights='imagenet' )
x=base_model.output
x=Dense(100, activation='relu'))(x)
x=Dropout(0.5)(x)
x=BatchNormalization(axis=-1, momentum=0.99, epsilon=0.001)(x)
output=Dense(2, activation='softmax')(x)
model=Model(inputs=base_model.input, outputs=output)
model.fit( train, epochs=100, batch_size=8, validation_data=val, callbacks=callbacks_list)
now for prediction you can use the same dimensions as you used to train the model.

I'm trying to adapt the example of a cnn-lstm for a univariate time series from a tutorial blog to an airline passenger problem written with LSTM

I'm trying to adapt the example of a cnn-lstm for a univariate time series from https://machinelearningmastery.com/how-to-develop-lstm-models-for-time-series-forecasting/ to an airline passenger problem written in LSTM,in another blog https://machinelearningmastery.com/time-series-prediction-lstm-recurrent-neural-networks-python-keras/ but receievd the following error
This the entire code and error message received
# LSTM for international airline passengers problem with window regression framing
import numpy
import matplotlib.pyplot as plt
import pandas
import math
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Flatten
from keras.layers import TimeDistributed
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import MaxPooling1D
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
# convert an array of values into a dataset matrix
def create_dataset(dataset, look_back=1):
dataX, dataY = [], []
for i in range(len(dataset)-look_back-1):
a = dataset[i:(i+look_back), 0]
dataX.append(a)
dataY.append(dataset[i + look_back, 0])
return numpy.array(dataX), numpy.array(dataY)
# fix random seed for reproducibility
numpy.random.seed(7)
# load the dataset
dataframe = pandas.read_csv('dummy_timeseries.csv' , usecols=[1],
engine= 'python' , skipfooter=3)
dataset = dataframe.values
dataset = dataset.astype('float32' )
# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
# split into train and test sets
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
# reshape into X=t and Y=t+1
look_back = 3
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
# reshape input to be [samples, time steps, features]
n_features = 1
trainX = numpy.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
# define model
model = Sequential()
model.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'),input_shape=(None,look_back, n_features)))
model.add(TimeDistributed(MaxPooling1D(pool_size=2)))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(50, activation='relu'))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)
# make predictions
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
# invert predictions
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])
# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print( 'Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print( 'Test Score: %.2f RMSE' % (testScore))
# shift train predictions for plotting
trainPredictPlot = numpy.empty_like(dataset)
trainPredictPlot[:, :] = numpy.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict
# shift test predictions for plotting
testPredictPlot = numpy.empty_like(dataset)
testPredictPlot[:, :] = numpy.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict
# plot baseline and predictions
plt.plot(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()
Error Message
Epoch 1/100
Traceback (most recent call last):
File "C:\Users\cisco4gud\Desktop\spider\LSTMwindowairline.py", line 62, in <module>
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py", line 108, in _method_wrapper
return method(self, *args, **kwargs)
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1098, in fit
tmp_logs = train_function(iterator)
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\def_function.py", line 780, in __call__
result = self._call(*args, **kwds)
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\def_function.py", line 823, in _call
self._initialize(args, kwds, add_initializers_to=initializers)
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\def_function.py", line 697, in _initialize
*args, **kwds))
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\function.py", line 2855, in _get_concrete_function_internal_garbage_collected
graph_function, _, _ = self._maybe_define_function(args, kwargs)
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\function.py", line 3213, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\function.py", line 3075, in _create_graph_function
capture_by_value=self._capture_by_value),
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\framework\func_graph.py", line 986, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\eager\def_function.py", line 600, in wrapped_fn
return weak_wrapped_fn().__wrapped__(*args, **kwds)
File "C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\framework\func_graph.py", line 973, in wrapper
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function *
return step_function(self, iterator)
C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py:796 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
return fn(*args, **kwargs)
C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py:789 run_step **
outputs = model.train_step(data)
C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\training.py:747 train_step
y_pred = self(x, training=True)
C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:976 __call__
self.name)
C:\Users\cisco4gud\Anaconda31\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:180 assert_input_compatibility
str(x.shape.as_list()))
ValueError: Input 0 of layer sequential_46 is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: [1, 1, 3]

Try to change this line (remove batch dimension from input shape):
model.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(look_back, n_features)))

I changed the reshape input from [samples, time steps, features] to [samples,subsequence, time steps, features] and the code for that section changes to
n_features = 1
n_seq = 1
n_steps = 3
trainX = trainX.reshape((trainX.shape[0], n_seq, n_steps, n_features))
testX = testX.reshape((testX.shape[0], n_seq, n_steps, n_features))

Categories

Resources