import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD
import matplotlib.pyplot as plt
(x_train, y_train), (x_test, y_test) = mnist.load_data()
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)
im = plt.imshow(x_train[0], cmap="gray")
plt.show()
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train/255
x_test = x_test/255
y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)
model = Sequential()
model.add(Dense(512, activation='relu', input_shape=(784,)))
model.add(Dense(256, activation='relu'))
model.add(Dense(10, activation='softmax'))
model.summary()
model.compile(optimizer=SGD(), loss='categorical_crossentropy', metics=['accuracy'])
model.fit(x_train, y_train, batch_size=64, epochs=5, validation_data=(x_test, y_test))
I tried several different versions of the combination, but still reported an error about
AttributeError: module 'tensorflow_core.compat.v2' has no attribute 'internal'
AttributeError: module 'tensorflow_core.compat.v2' has no attribute '__internal__'
Generally you will get above error due to incompatibility between Tensorflow and Keras. You can import keras without any issues by upgrade to latest version. For more details you can refer this solution.
Coming to your code, have couple of issues and it can be resolved
1.to_categorical has now packed in np_utils. You need to add import as shown below
from keras.utils.np_utils import to_categorical
2.Typo mistake, replace metics to metrics in model.compile
Working code as shown below
import keras
print(keras.__version__)
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD
import matplotlib.pyplot as plt
from keras.utils.np_utils import to_categorical
(x_train, y_train), (x_test, y_test) = mnist.load_data()
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)
im = plt.imshow(x_train[0], cmap="gray")
plt.show()
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train/255
x_test = x_test/255
y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)
model = Sequential()
model.add(Dense(512, activation='relu', input_shape=(784,)))
model.add(Dense(256, activation='relu'))
model.add(Dense(10, activation='softmax'))
model.summary()
model.compile(optimizer=SGD(), loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=64, epochs=5, validation_data=(x_test, y_test))
Output:
2.5.0
(60000, 28, 28) (60000,)
(10000, 28, 28) (10000,)
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense (Dense) (None, 512) 401920
_________________________________________________________________
dense_1 (Dense) (None, 256) 131328
_________________________________________________________________
dense_2 (Dense) (None, 10) 2570
=================================================================
Total params: 535,818
Trainable params: 535,818
Non-trainable params: 0
_________________________________________________________________
Epoch 1/5
938/938 [==============================] - 21s 8ms/step - loss: 1.2351 - accuracy: 0.6966 - val_loss: 0.3644 - val_accuracy: 0.9011
Epoch 2/5
938/938 [==============================] - 7s 7ms/step - loss: 0.3554 - accuracy: 0.9023 - val_loss: 0.2943 - val_accuracy: 0.9166
Epoch 3/5
938/938 [==============================] - 7s 7ms/step - loss: 0.2929 - accuracy: 0.9176 - val_loss: 0.2553 - val_accuracy: 0.9282
Epoch 4/5
938/938 [==============================] - 7s 7ms/step - loss: 0.2538 - accuracy: 0.9281 - val_loss: 0.2309 - val_accuracy: 0.9337
Epoch 5/5
938/938 [==============================] - 7s 8ms/step - loss: 0.2313 - accuracy: 0.9355 - val_loss: 0.2096 - val_accuracy: 0.9401
<keras.callbacks.History at 0x7f615c82d090>
You can refer this gist,for the above use case in tensorflow version.
Error:
AttributeError: module 'tensorflow_core.compat.v2' has no attribute '__internal__'
Solution:
Install Libraries
!pip install tensorflow==2.1
!pip install keras==2.3.1
Import
from tensorflow.keras.models import load_model
Related
I've been trying to train this CNN Model, It's a Tensorflow tutorial and I just changed the dataset ( I used fruit 360 dataset) without altering the core of the code. When it finishes training the accuracy stays constant at 0.8565 it doesn't change and when I try and test some images it almost always wrong.
What am I doing wrong?
Code output after executing
Here's the code I used
[enter image description here][1]import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf
import tarfile
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
from tensorflow.keras import datasets, layers, models
from tensorflow import keras
import pathlib
dataset_url = "https://file.io/z5JM3sYAWXv4"
data_dir = tf.keras.utils.get_file(origin=dataset_url,
fname='tomatos',
untar=True,
extract=True)
data_dir = pathlib.Path(data_dir)
print(data_dir)
file_count = sum(len(files) for _, _, files in os.walk(r'tomatos'))
print(file_count)
batch_size = 32
img_height = 180
img_width = 180
train_ds = tf.keras.utils.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="training",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)
val_ds = tf.keras.utils.image_dataset_from_directory(
data_dir,
validation_split=0.2,
subset="validation",
seed=123,
image_size=(img_height, img_width),
batch_size=batch_size)
class_names = train_ds.class_names
print(class_names)
AUTOTUNE = tf.data.AUTOTUNE
train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
num_classes = len(class_names)
model = Sequential([
layers.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
layers.Conv2D(16, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(64, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Flatten(),
layers.Dense(128, activation='relu'),
layers.Dense(num_classes)
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
model.summary()
epochs=2
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)
data_augmentation = keras.Sequential(
[
layers.RandomFlip("horizontal",
input_shape=(img_height,
img_width,
3)),
layers.RandomRotation(0.1),
layers.RandomZoom(0.1),
]
)
model = Sequential([
data_augmentation,
layers.Rescaling(1./255),
layers.Conv2D(16, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(32, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Conv2D(64, 3, padding='same', activation='relu'),
layers.MaxPooling2D(),
layers.Dropout(0.2),
layers.Flatten(),
layers.Dense(128, activation='relu'),
layers.Dense(num_classes)
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
model.summary()
epochs = 4
history = model.fit(
train_ds,
validation_data=val_ds,
epochs=epochs
)
sunflower_url = "https://puffycarrot.com/wp-content/uploads/2017/04/Green-tomatoes.jpg"
sunflower_path = tf.keras.utils.get_file('tomato2', origin=sunflower_url)
img = tf.keras.utils.load_img(
sunflower_path, target_size=(img_height, img_width)
)
img_array = tf.keras.utils.img_to_array(img)
img_array = tf.expand_dims(img_array, 0) # Create a batch
predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])
print(
"This image most likely belongs to {} with a {:.2f} percent confidence."
.format(class_names[np.argmax(score)], 100 * np.max(score))
)
#Yaman Tarawneh, I tried replicating your above mentioned code in Google colab (using TF 2.8) and in Pycharm (using TF 2.7) and did not find the error.
Please check the output image for Pycharm :
and got the same output in Google colab :
Total params: 3,988,898
Trainable params: 3,988,898
Non-trainable params: 0
_________________________________________________________________
Epoch 1/4
78/78 [==============================] - 8s 41ms/step - loss: 0.0309 - accuracy: 0.9835 - val_loss: 5.6374e-07 - val_accuracy: 1.0000
Epoch 2/4
78/78 [==============================] - 2s 25ms/step - loss: 5.7533e-07 - accuracy: 1.0000 - val_loss: 2.7360e-07 - val_accuracy: 1.0000
Epoch 3/4
78/78 [==============================] - 2s 25ms/step - loss: 3.0400e-07 - accuracy: 1.0000 - val_loss: 1.3978e-07 - val_accuracy: 1.0000
Epoch 4/4
78/78 [==============================] - 2s 25ms/step - loss: 1.7403e-07 - accuracy: 1.0000 - val_loss: 7.2102e-08 - val_accuracy: 1.0000
This image most likely belongs to Tomato not Ripened with a 100.00 percent confidence.
For further analysis if the issue still persists, Please let us know which Python and Tensorflow version are you using.
When I execute my model.fit(x_train_lstm, y_train_lstm, epochs=3, shuffle=False, verbose=2)
I always get loss as nan:
Epoch 1/3
73/73 - 5s - loss: nan - accuracy: 0.5417 - 5s/epoch - 73ms/step
Epoch 2/3
73/73 - 5s - loss: nan - accuracy: 0.5417 - 5s/epoch - 74ms/step
Epoch 3/3
73/73 - 5s - loss: nan - accuracy: 0.5417 - 5s/epoch - 73ms/step
My x_training is shaped (2475, 48), y_train is shaped (2475,)
I derive my input train set in (2315, 160, 48), so 2315 sets of training data, 160 as my loopback timewindow, 48 features
corresspondingly, the y_train is 0 or 1 in shape of (2315, 1)
All in range of (-1,1):
My model is like this:
Model: "sequential_2"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_6 (LSTM) (None, 160, 128) 90624
dropout_4 (Dropout) (None, 160, 128) 0
lstm_7 (LSTM) (None, 160, 64) 49408
dropout_5 (Dropout) (None, 160, 64) 0
lstm_8 (LSTM) (None, 32) 12416
dense_2 (Dense) (None, 1) 33
=================================================================
Total params: 152,481
Trainable params: 152,481
Non-trainable params: 0
I tried different LSTM units: 48, 60, 128, 160, none of them work
I check my training data, all of them are in the range of (-1,1)
There is no 'null' in my dataset, x_train.isnull().values.any() outputs False
Now I have no clue where can I try more~
My model code is:
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LSTM
from tensorflow.keras.layers import Dropout
def create_model(win = 100, features = 9):
model = Sequential()
model.add(LSTM(units=128, activation='relu', input_shape=(win, features),
return_sequences=True))
model.add(Dropout(0.1))
model.add(LSTM(units=64, activation='relu', return_sequences=True))
model.add(Dropout(0.2))
# no need return sequences from 'the last layer'
model.add(LSTM(units=32))
# adding the output layer
model.add(Dense(units=1, activation='sigmoid'))
# may also try mean_squared_error
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
return model
here I plot some train_y samples:
Two things: try normalizing your time series data and using relu as the activation function for lstm layers is not 'conventional'. Check this post for further insights. An example:
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LSTM
from tensorflow.keras.layers import Dropout
import tensorflow as tf
layer = tf.keras.layers.Normalization(axis=-1)
x = tf.random.normal((500, 100, 9))
y = tf.random.uniform((500, ), dtype=tf.int32, maxval=2)
layer.adapt(x)
def create_model(win = 100, features = 9):
model = Sequential()
model.add(layer)
model.add(LSTM(units=128, activation='tanh', input_shape=(win, features),
return_sequences=True))
model.add(Dropout(0.1))
model.add(LSTM(units=64, activation='tanh', return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(units=32))
model.add(Dense(units=1, activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
return model
model = create_model()
model.fit(x, y, epochs=20)
2022.Mar.17 update
After further debugging, I eventually found out the problem is actually because of my newly added feature contains np.inf, after I remove those rows, my problem resolved, I can see the loss value now
6/6 [==============================] - 2s 50ms/step - loss: 0.6936 - accuracy: 0.5176
Note, np.inf has symbol, so make sure both np.inf and -np.inf are removed:
all_dataset = all_dataset[all_dataset.feature_issue != np.inf]
all_dataset = all_dataset[all_dataset.feature_issue != -np.inf]
2022.Mar.16
After some debugging, I addressed 2 of my new added features actually cause the problem. So, the problem comes from data, but unlike the others, my data contains no nan, no out of range(originally I thought all the data needs to be normalized)
But I can't tell the reason yet, as they looks good
I will continue research more on it tomorrow, any advice is appreciated!
I am using Keras' pre-trained VGGNet16 as my base model, but I need to add layers on the end to make it work for my data. I've got the data pre-processed and formatted, so I'll jump to the part of the code actually involving the CNN.
import tensorflow as tf
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D, AveragePooling2D
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
import tensorflow.keras as K
.
.
.
input_t = K.Input(shape=(224,224,3))
base_model = K.applications.VGG16(include_top=False,weights="imagenet",input_tensor=input_t)
for layer in base_model.layers:
layer.trainable = False
model = K.models.Sequential()
model.add(base_model)
model.add(Flatten())
model.add(Dense(num_classes,activation='softmax'))
#Training
model.compile(loss = 'binary_crossentropy',
optimizer = Adam(learning_rate=1e-5),
metrics = ['accuracy'])
#Fit
model.fit(x_train,
y_train,
epochs = 3,
validation_split = 0.1,
validation_data =(x_test,y_test))
model.summary()
This code yields the following output.
Epoch 1/3
14/14 [==============================] - 48s 3s/step - loss: 0.5887 - accuracy: 0.2287 - val_loss: 0.4951 - val_accuracy: 0.3000
Epoch 2/3
14/14 [==============================] - 48s 3s/step - loss: 0.5170 - accuracy: 0.2220 - val_loss: 0.4972 - val_accuracy: 0.2800
Epoch 3/3
14/14 [==============================] - 48s 3s/step - loss: 0.4982 - accuracy: 0.2265 - val_loss: 0.4975 - val_accuracy: 0.2200
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
vgg16 (Functional) (None, 7, 7, 512) 14714688
_________________________________________________________________
flatten (Flatten) (None, 25088) 0
_________________________________________________________________
dense (Dense) (None, 5) 125445
=================================================================
Total params: 14,840,133
Trainable params: 125,445
Non-trainable params: 14,714,688
_________________________________________________________________
Test loss: 0.4997282326221466
Test accuracy: 0.2720000147819519
All of my test images are being classified into the same class. Is there any reason for this?
Edit: Modified question upon realizing the model is running properly
Perhaps this isn't a great solution, but I fixed this by making the last six layers trainable with the others trainable
for layer in base_model.layers[:-6]:
layer.trainable = False
from keras import layers
from keras import models
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
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.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))
from keras.datasets import mnist
from keras.utils import to_categorical
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32') / 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32') / 255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(train_images, train_labels, epochs=5, batch_size=64)
I am getting an error:
ValueError: Input 0 of layer sequential_22 is incompatible with the layer: expected ndim=4, found ndim=3. Full shape received: [28, 28, 1]
I tried using the Keras 2.8, fashion_mnist dataset and it is working.
import keras
print(keras.__version__)
from keras import layers
from keras import models
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
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.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))
from keras.datasets import fashion_mnist
from tensorflow.keras.utils import to_categorical
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32') / 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32') / 255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(train_images, train_labels, epochs=5, batch_size=64)
Output:
2.8.0
Epoch 1/5
938/938 [==============================] - 53s 55ms/step - loss: 0.5523 - accuracy: 0.7965
Epoch 2/5
938/938 [==============================] - 51s 55ms/step - loss: 0.3333 - accuracy: 0.8780
Epoch 3/5
938/938 [==============================] - 54s 58ms/step - loss: 0.2832 - accuracy: 0.8968
Epoch 4/5
938/938 [==============================] - 52s 55ms/step - loss: 0.2508 - accuracy: 0.9079
Epoch 5/5
938/938 [==============================] - 51s 55ms/step - loss: 0.2264 - accuracy: 0.9168
<keras.callbacks.History at 0x7f1c1b0a5390>
I try to implement object detector like yolo. It uses complex custom loss function. So I need to print/debug its tensors. I understand, that python code only builds computing graph so standard print won't work in not eager mode.
tensorflow 1.12.0
keras 2.2.4
I tried all methods from these posts Keras custom loss function not printing value of tensor, Debugging keras tensor values and nothing works. I tried tf.Print, tf.print, callback, K.tensor_print - the same result. In console i see only standart output messages. I`m not even sure if loss function been called. The answer from this post Keras - printing intermediate tensors in loss function (tf.Print and K.print_tensor do not work...) says that loss function sometimes doesn't even called! Ok, but how to use tf.contrib.eager.defun decorator then? The example is for pure tensorflow and dont't understand how to use it in keras.
import tensorflow as tf
from keras.datasets import fashion_mnist
import matplotlib.pyplot as plt
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.layers import Flatten, Dense, Dropout
from keras.models import Sequential
from keras import optimizers
import numpy as np
from random import randrange
from keras.callbacks import LambdaCallback
import keras.backend as K
import keras
print(tf.__version__)
print(keras.__version__)
num_filters = 64
(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()
x_train = x_train.astype('float32') / 255
x_test = x_test.astype('float32') / 255
#reshape
x_train = x_train.reshape(60000,28,28,1)[:1000,...]
x_test = x_test.reshape(10000,28,28,1)[:100,...]
# One-hot encode the labels
y_train = tf.keras.utils.to_categorical(y_train, 10)[:1000,...]
y_test = tf.keras.utils.to_categorical(y_test, 10)[:100,]
labels = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
model = Sequential()
model.add(Conv2D(input_shape=(28,28,1), filters=num_filters,kernel_size=3,strides=(1, 1),padding="valid", activation='relu', use_bias=True))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.3))
model.add(Conv2D(filters=num_filters,kernel_size=3,strides=(1, 1),padding="valid", activation='relu', use_bias=True))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.3))
model.add(Flatten())
model.add(Dense(256, activation = 'relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation = 'softmax'))
#model.summary()
#loss 1
def customLoss(yTrue,yPred):
d = yPred-yTrue
d = K.print_tensor(d)
return K.mean(K.square(d), axis=-1)
#loss 2
def cat_loss(y_true, y_pred):
d = y_true - y_pred
d = tf.Print(d, [d], "Inside loss function")
return tf.reduce_mean(tf.square(d))
model.compile(loss=customLoss,
optimizer='adam')
import keras.callbacks as cbks
# 3 try to print with callback
class CustomMetrics(cbks.Callback):
def on_epoch_end(self, epoch, logs=None):
for k in logs:
if k.endswith('cat_loss'):
print(logs[k])
#checkpointer = ModelCheckpoint(filepath='model.weights.best.hdf5', verbose = 1, save_best_only=True)
model.fit(x_train,
y_train,
#verbose=1,
batch_size=16,
epochs=10,
validation_data=(x_test, y_test),
callbacks=[CustomMetrics()])
# Evaluate the model on test set
score = model.evaluate(x_test, y_test, verbose=0)
# Print test accuracy
print('\n', 'Test accuracy:', score)
rand_img = randrange(100)
result = np.argmax(model.predict(x_test[rand_img].reshape(1,28,28,1)))
plt.imshow(x_test[rand_img].reshape(28,28), cmap='gray')
plt.title(labels[result])
==========>......] - ETA: 0s - loss: 0.0243
832/1000 [=======================>......] - ETA: 0s - loss: 0.0242
Warning (from warnings module):
File "C:\Python36\lib\site-packages\keras\callbacks.py", line 122
% delta_t_median)
UserWarning: Method on_batch_end() is slow compared to the batch update (0.101474). Check your callbacks.
976/1000 [============================>.] - ETA: 0s - loss: 0.0238
992/1000 [============================>.] - ETA: 0s - loss: 0.0236
1000/1000 [==============================] - 3s 3ms/step - loss: 0.0239 - val_loss: 0.0352
Test accuracy: 0.035189545452594756```
The truth was somewhere near. Idle doesn't output tf.Print and therefore K.print_tensor() to it's shell, so when i used cmd.exe python train.py, i saw tensor output.