Im quite new learning machine learning and my first project is the creation of a Neural Network in order to detect key facial points on google colab. Everything has been working ok but today when I wanted to train my neural network I came accross with an error that has never appeared before when I trained my neural network.
The error is:
ModuleNotFoundError Traceback (most recent call last)
<ipython-input-189-47fd3efd0229> in <module>()
5
6
----> 7 X_input = Input(input_shape)
8
9 # Zero-padding
4 frames
/usr/lib/python3.7/importlib/_bootstrap.py in _find_and_load_unlocked(name, import_)
ModuleNotFoundError: No module named 'keras.engine.base_layer_v1'
---------------------------------------------------------------------------
NOTE: If your import is failing due to a missing package, you can
manually install dependencies using either !pip or !apt.
To view examples of installing some common dependencies, click the
"Open Examples" button below.
I don't understand the line ModuleNotFoundError: No module named 'keras.engine.base_layer_v1' because the line that is not working is when I'm using Input from tensorflow.keras.layers.
I really don't know what is going on because I never got this error before. I've seen that it could be the version of TensorFlow or maybe my libraries.
I am using 2.3.0 versions in TensorFlow and Keras and these are the libraries I am importing:
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.applications import DenseNet121
from tensorflow.keras.models import Model, load_model
from tensorflow.keras.initializers import glorot_uniform
from tensorflow.keras.utils import plot_model
from tensorflow.keras.callbacks import ReduceLROnPlateau, EarlyStopping, ModelCheckpoint, LearningRateScheduler
from IPython.display import display
from tensorflow.python.keras import *
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras import layers, optimizers
from tensorflow.keras.applications.resnet50 import ResNet50
from tensorflow.keras.layers import *
from tensorflow.keras import backend as K
from keras import optimizers
I would really appreciate any help :)
Re-installing tensorflow and keras works for me
since the release of version 2.6 of Tensorflow I am having a issue I did not have with version 2.5.
The following code works OK:
from tensorflow.keras.utils import get_custom_objects
from tensorflow.keras.layers import Dense
def my_act(x):
return x
get_custom_objects().update({"my_act": my_act})
dense = Dense(3, activation="my_act")
However, if I try to do the same but with a custom layer instead of Tensorflow built-in layers, I have the error:
ValueError: Unknown activation function: my_act. Please ensure this object is passed to the `custom_objects` argument. See https://www.tensorflow.org/guide/keras/save_and_serialize#registering_the_custom_object for details.
Here you have the minimum code to reproduce plus I show that with version 2.5 works ok (You need to restart the runtime to run it tho).
Try to import activations like this:
from tensorflow.keras import activations
instead of from tensorflow.python.keras import activations.
In tensorflow 2.7 and later versions tensorflow.python will no longer exist, and it seems in TF 2.6 already it is not compatible with some other functions.
enter image description here
Above is the image:
The error is this:
LOCAL.GENERATED_WITH_V2 = tf.__internal__.tf2.enabled()
AttributeError: module 'tensorflow.compat.v2.__internal__' has no attribute 'tf2'
Thanks
From Tensorflow 2.x onward, keras is no longer maintained and it became a part of Tensorflow. I would recommend instead of import keras, you should try from tensorflow import keras or import tensorflow as tf and use tf.keras.
You can import Sequential module from tensorflow as shown below
import tensorflow as tf
from tf.keras import Sequential
For more information you can refer this and this
I'm trying to load a pretrained retinanet model with keras by running:
# import keras
import keras
# import keras_retinanet
from keras_retinanet import models
from keras_retinanet.utils.image import read_image_bgr, preprocess_image, resize_image
from keras_retinanet.utils.visualization import draw_box, draw_caption
from keras_retinanet.utils.colors import label_color
# set tf backend to allow memory to grow, instead of claiming everything
import tensorflow as tf
def get_session():
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
return tf.Session(config=config)
model_path = os.path.join('sample_data/snapshots', sorted(os.listdir('sample_data/snapshots'), reverse=True)[0])
print(model_path)
# load retinanet model
model = models.load_model(model_path, backbone_name='resnet50')
model = models.convert_model(model)
I am facing the following error with both codes:
OSError: SavedModel file does not exist at: sample_data/snapshots/training_5000(640_480).h5/{saved_model.pbtxt|saved_model.pb}
the cause might be some new versions of Keras or tensorflow,
soo I am going to list the versions that I am currently using.
keras.__version__
2.4.3
tf.__version__
2.4.1
Note: I am trying to run this code in my Colab.
Every time I run LSTM network with Keras in jupyter notebook, I got a different result, and I have googled a lot, and I have tried some different solutions, but none of they are work, here are some solutions I tried:
set numpy random seed
random_seed=2017
from numpy.random import seed
seed(random_seed)
set tensorflow random seed
from tensorflow import set_random_seed
set_random_seed(random_seed)
set build-in random seed
import random
random.seed(random_seed)
set PYTHONHASHSEED
import os
os.environ['PYTHONHASHSEED'] = '0'
add PYTHONHASHSEED in jupyter notebook kernel.json
{
"language": "python",
"display_name": "Python 3",
"env": {"PYTHONHASHSEED": "0"},
"argv": [
"python",
"-m",
"ipykernel_launcher",
"-f",
"{connection_file}"
]
}
and the version of my env is:
Keras: 2.0.6
Tensorflow: 1.2.1
CPU or GPU: CPU
and this is my code:
model = Sequential()
model.add(LSTM(16, input_shape=(time_steps,nb_features), return_sequences=True))
model.add(LSTM(16, input_shape=(time_steps,nb_features), return_sequences=False))
model.add(Dense(8,activation='relu'))
model.add(Dense(1,activation='linear'))
model.compile(loss='mse',optimizer='adam')
The seed is definitely missing from your model definition. A detailed documentation can be found here: https://keras.io/initializers/.
In essence your layers use random variables as their basis for their parameters. Therefore you get different outputs every time.
One example:
model.add(Dense(1, activation='linear',
kernel_initializer=keras.initializers.RandomNormal(seed=1337),
bias_initializer=keras.initializers.Constant(value=0.1))
Keras themselves have a section about getting reproduceable results in their FAQ section: (https://keras.io/getting-started/faq/#how-can-i-obtain-reproducible-results-using-keras-during-development). They have the following code snippet to produce reproducable results:
import numpy as np
import tensorflow as tf
import random as rn
# The below is necessary in Python 3.2.3 onwards to
# have reproducible behavior for certain hash-based operations.
# See these references for further details:
# https://docs.python.org/3.4/using/cmdline.html#envvar-PYTHONHASHSEED
# https://github.com/fchollet/keras/issues/2280#issuecomment-306959926
import os
os.environ['PYTHONHASHSEED'] = '0'
# The below is necessary for starting Numpy generated random numbers
# in a well-defined initial state.
np.random.seed(42)
# The below is necessary for starting core Python generated random numbers
# in a well-defined state.
rn.seed(12345)
# Force TensorFlow to use single thread.
# Multiple threads are a potential source of
# non-reproducible results.
# For further details, see: https://stackoverflow.com/questions/42022950/which-seeds-have-to-be-set-where-to-realize-100-reproducibility-of-training-res
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
from keras import backend as K
# The below tf.set_random_seed() will make random number generation
# in the TensorFlow backend have a well-defined initial state.
# For further details, see: https://www.tensorflow.org/api_docs/python/tf/set_random_seed
tf.set_random_seed(1234)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
K.set_session(sess)
Keras + Tensorflow.
Step 1, disable GPU.
import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = ""
Step 2, seed those libraries which are included in your code, say "tensorflow, numpy, random".
import tensorflow as tf
import numpy as np
import random as rn
sd = 1 # Here sd means seed.
np.random.seed(sd)
rn.seed(sd)
os.environ['PYTHONHASHSEED']=str(sd)
from keras import backend as K
config = tf.ConfigProto(intra_op_parallelism_threads=1,inter_op_parallelism_threads=1)
tf.set_random_seed(sd)
sess = tf.Session(graph=tf.get_default_graph(), config=config)
K.set_session(sess)
Make sure these two pieces of code are included at the start of your code, then the result will be reproducible.
I resolved this issue by adding os.environ['TF_DETERMINISTIC_OPS'] = '1'
Here an example:
import os
os.environ['TF_DETERMINISTIC_OPS'] = '1'
#rest of the code
#TensorFlow version 2.3.1