Created
April 24, 2018 00:46
-
-
Save ura14h/c91f1dafd30cc029f58cf0bb5e74386c to your computer and use it in GitHub Desktop.
How to install TensorFlow and Keras on Windows 10
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
See also: http://starpentagon.net/analytics/tensorflow_cpu_mode_windows_install/ | |
How to install TensorFlow and Keras on Windows 10 | |
* Install... https://repo.anaconda.com/archive/Anaconda3-5.1.0-Windows-x86_64.exe | |
* Open... 'Anaconda3' > 'Anaconda Prompt' | |
* Type commands... | |
--- | |
(base) > conda create -n tensorflow pip python=3.6 | |
(base) > conda activate tensorflow | |
(tensorflow) > python | |
>>> import tensorflow as tf | |
>>> hello = tf.constant('Hello, world') | |
>>> sess = tf.Session() | |
>>> print(sess.run(hello)) | |
>>> quit() | |
(tensorflow) > python -m pip install --upgrade pip | |
(tensorflow) > pip install keras | |
(tensorflow) > conda install notebook ipykernel | |
(tensorflow) > ipython kernel install --user --name tensorflow | |
(tensorflow) > pip install h5py pillow | |
--- | |
* Prepare Image... | |
* Open Jupyter notebook... | |
* Open 'New' > 'tensorflow' | |
* Type a script... | |
--- | |
from keras.applications.resnet50 import ResNet50 | |
from keras.preprocessing import image | |
from keras.applications.resnet50 import preprocess_input, decode_predictions | |
import numpy as np | |
model = ResNet50(weights='imagenet') | |
img_path = 'C:/free/profile.png' | |
img = image.load_img(img_path, target_size=(224, 224)) | |
img | |
x = image.img_to_array(img) | |
x = np.expand_dims(x, axis=0) | |
x = preprocess_input(x) | |
preds = model.predict(x) | |
print('Predicted:', decode_predictions(preds, top=3)[0]) | |
--- | |
* Run the script... | |
Thanks. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment