I have read a related question's answer about this on stackoverflow which explains the difference between tensorflow.keras.layers and tensorflow.layers, link:
What is the difference between tf.keras.layers versus tf.layers?
But, it doesn't answer the difference between tensorflow.keras.layers and keras.layers, whereas I noticed I can import them also.
So, what is the difference between them?
Keras used to be able to support different backends (tensorflow, theano and CNTK). Since keras 2.3, there is no difference between keras and tf.keras.
An excerpt from the Readme of the keras repository on github :
Multi-backend Keras and tf.keras
Multi-backend Keras has been discontinued. At this time, we recommend that Keras users who use multi-backend Keras with the TensorFlow backend switch to tf.keras in TensorFlow 2.0.
Keras 2.2.5 was the last release of Keras implementing the 2.2.* API. It was the last release to only support TensorFlow 1 (as well as Theano and CNTK).
The current release is Keras 2.4.0, which simply redirects to tf.keras.
I want to train a sequential tensorflow (version 2.3.0) model on a single NVIDIA graphic card (RTX 2080 super). I am using the following code snippet to build and train the model. However, everytime I am running this code I do not see any GPU utilization. Any suggestion how to modify my code so I can run it on 1 GPU?
strategy = tf.distribute.OneDeviceStrategy(device="/GPU:0")
with strategy.scope():
num_classes=len(pd.unique(cats.No))
model = BuildModel((image_height, image_width, 3), num_classes)
model.summary()
model=train_model(model,valid_generator,train_generator,EPOCHS,BATCH_SIZE)
run the code below to see if tensorflow detects your GPU.
import tensorflow as tf
from tensorflow.python.client import device_lib
print(device_lib.list_local_devices())
print(tf.__version__)
print("Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU')))
tf.test.is_gpu_available()
!python --version
On every question and tutorial I have found, tf.data.Dataset is used for CSV files, but I am not using tensorflow, I am using PlaidML because my AMD GPU is not supported in ROCm. I have tried using the same code by doing
os.environ["KERAS_BACKEND"] = "plaidml.keras.backend"
from tensorflow import keras
but that still does not use the plaidml backend. How do I load this dataset: https://www.kaggle.com/keplersmachines/kepler-labelled-time-series-data into keras without tensorflow? Thank you. I check if the plaidml backend is used by looking at the output. If it says "Using plaidml.keras.backend backend", then it is using plaidml. Also, only plaidml recognizes my GPU, so tensorflow will use my CPU.
I have a set of weights from a model developed in keras 1.10 with theano backend.
Right now I would like to use those weights in a more recent version of keras (2.2.4).
Just by loading them on the more recent version of keras the results are not the same (in 2.2.4 the results are not accurate). I can retrain the model but it would take some time. Is there some way to use the weights?
I tried to load the weights from 1.10 to 2.2.4 and it did not work. Also found a project on git:
https://gist.github.com/davecg/e33b9b29d218b5966fb8e2f617e90399
To update the weights from Keras 1.x to 2.x and also did not work.
Thanks for the answers.
I'm quite new in deep learning and, in order to improve my knowledge, I've been reading some books and following a video course on line.
In this videocourse I have to do an exercise with convolution neaural network.
I've builded a CNN with 10.000 images with dimension 64x64 pixels. (to recognize cats and dogs images)
from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
# Initialising the CNN
classifier = Sequential()
# Step 1 - Convolution
classifier.add(Convolution2D(32,3,3,input_shape=(64,64,3),activation='relu'))
# Step 2 - Pooling
classifier.add(MaxPooling2D(pool_size = (2,2)))
classifier.add(Convolution2D(32,3,3,activation='relu'))
classifier.add(MaxPooling2D(pool_size = (2,2)))
# Step 3 - Flattening
classifier.add(Flatten())
#step 4 - Full Connection CNN
classifier.add(Dense(output_dim = 128 ,activation='relu'))
classifier.add(Dense(output_dim = 1 ,activation='sigmoid'))
# Compiling the CNN
classifier.compile(optimizer = 'adam' , loss = 'binary_crossentropy', metrics = ['accuracy'])
# Fitting the CNN to the images
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
traininig_set = train_datagen.flow_from_directory(
'dataset/training_set',
target_size=(64, 64),
batch_size=32,
class_mode='binary')
test_set = test_datagen.flow_from_directory(
'dataset/test_set',
target_size=(64, 64),
batch_size=32,
class_mode='binary')
classifier.fit_generator(traininig_set,
steps_per_epoch=8000,
epochs=25,
validation_data=test_set,
validation_steps=2000)
The first time I installed Anaconda I didn't install the GPU module and when I started fitting my CNN
I had to wait 1190 seconds per epoch with the CPU working at 70%.
For your information my computer is quite fast. It's an i7 6800k overclocked to 4.2ghz an MSI GTX1080 video cards and 32gb 3333Mhz.
I've tought that with this computer installing the tensorflow gpu module was almost compulsory.
I watched in some posts how to check if the tensorflow is correctly configured to use GPU
and launching:
In [1]: from tensorflow.python.client import device_lib
In [2]: print(device_lib.list_local_devices())
I have this result:
2017-10-16 10:41:25.780983: W C:\tf_jenkins\home\workspace\rel-win\M\windows-gpu\PY\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-10-16 10:41:25.781067: W C:\tf_jenkins\home\workspace\rel-win\M\windows-gpu\PY\35\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-16 10:41:26.635590: I C:\tf_jenkins\home\workspace\rel-win\M\windows-gpu\PY\35\tensorflow\core\common_runtime\gpu\gpu_device.cc:955] Found device 0 with properties:
name: GeForce GTX 1080
major: 6 minor: 1 memoryClockRate (GHz) 1.8225
pciBusID 0000:03:00.0
Total memory: 8.00GiB
Free memory: 6.61GiB
2017-10-16 10:41:26.635807: I C:\tf_jenkins\home\workspace\rel-win\M\windows-gpu\PY\35\tensorflow\core\common_runtime\gpu\gpu_device.cc:976] DMA: 0
2017-10-16 10:41:26.636324: I C:\tf_jenkins\home\workspace\rel-win\M\windows-gpu\PY\35\tensorflow\core\common_runtime\gpu\gpu_device.cc:986] 0: Y
2017-10-16 10:41:26.637179: I C:\tf_jenkins\home\workspace\rel-win\M\windows-gpu\PY\35\tensorflow\core\common_runtime\gpu\gpu_device.cc:1045] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:03:00.0)
[name: "/cpu:0"
device_type: "CPU"
memory_limit: 268435456
locality {
}
incarnation: 16495731140373557390
, name: "/gpu:0"
device_type: "GPU"
memory_limit: 6740156088
locality {
bus_id: 1
}
incarnation: 6266244792178813148
physical_device_desc: "device: 0, name: GeForce GTX 1080, pci bus id: 0000:03:00.0"
]
With gpu:0, I read in the documentation that TensorFlow automatically will use GPU for computation.
Launching the fit method with this configuration I have to wait 950 sec per epoch, well better than 1190 seconds. The cpu never gets over 10% and, strangely, the GPU never gets over 10-13%.
I assume there is something wrong with my configuration because, the teacher in the course, with a MacBook notebook (I don't know the exact configuration actually) without tensorflow GPU module takes approximately 90 seconds per epoch.
I'm not a python or tensorflow expert, but it really seems there is something wrong or something else to understand.
Could someone give some advice, something to read, some tests to do to understand better where is the bottleneck?
Thank you
I don't have a GPU on windows, but I got a really good deal installing the Intel Distribution of Python with Anaconda: https://software.intel.com/en-us/articles/using-intel-distribution-for-python-with-anaconda.
For tensorflow, the best seems to be a python 3.5 environment (in the previous link, use python=3.5)
I then installed tensorflow with pip inside this environment made with anaconda. Follow installing with anaconda.
Then Keras with conda install keras. (But make sure it won't replace previous numpy and other installations, find proper installation commands not to replace these optimal packages). Maybe pip install keras could be better in case the conda version doesn't work. (Again, use the proper options not to replace your existing packages) - Don't let this keras installation replace your numpy packages or your tensorflow packages!
This gave me all processors absolutely 100% (according to windows resource monitor)
If this doesn't solve your problem, you can also try getting the numpy and scipy packages from here. Unfortunately I had no success at all with the keras and tensorflow packages from this source, but numpy is quality stuff.
With GPU, your problem may be the lack of a proper CUDA driver and the CUDNN library?
Follow this and this.
Unfortunatelly these things vary a lot from computer to computer. I followed strictly the instructions in these sites, and in tensorflow site, for a linux machine, and the results were astonishing.
On top of Daniel's answer (check CUDA & cuDNN) - it is never a good idea to have both tensorflow and tensorflow-gpu packages installed side by side; most probably, you are using the tensorflow (i.e. the CPU) one.
To avoid this, you should uninstall both packages, and then re-install tensorflow-gpu, i.e.:
pip uninstall tensorflow tensorflow-gpu
pip install tensorflow-gpu
See also accepted answer (and comment) here, on a similar issue.