Skip to content

Instantly share code, notes, and snippets.

@kcchien
Created May 1, 2020 01:44
Show Gist options
  • Save kcchien/ceda4aead56a62e58a0129853b329974 to your computer and use it in GitHub Desktop.
Save kcchien/ceda4aead56a62e58a0129853b329974 to your computer and use it in GitHub Desktop.
Create Tensorflow 2 Enviroment with Conda
# 建立一個名稱為 tf2 的虛擬環境,並指定python 版本為 3.6
conda create -n tf2 python=3.6
# 啟動 tf2 虛擬環境
conda activate tf2
# 安裝 tensorflow 2
pip install tensorflow
# 安裝 PIL 套件
conda install pillow
import tensorflow.keras
from PIL import Image, ImageOps
import numpy as np
# Disable scientific notation for clarity
np.set_printoptions(suppress=True)
# Load the model
model = tensorflow.keras.models.load_model('keras_model.h5')
# Create the array of the right shape to feed into the keras model
# The 'length' or number of images you can put into the array is
# determined by the first position in the shape tuple, in this case 1.
data = np.ndarray(shape=(1, 224, 224, 3), dtype=np.float32)
# Replace this with the path to your image
image = Image.open('test_photo.jpg')
#resize the image to a 224x224 with the same strategy as in TM2:
#resizing the image to be at least 224x224 and then cropping from the center
size = (224, 224)
image = ImageOps.fit(image, size, Image.ANTIALIAS)
#turn the image into a numpy array
image_array = np.asarray(image)
# display the resized image
image.show()
# Normalize the image
normalized_image_array = (image_array.astype(np.float32) / 127.0) - 1
# Load the image into the array
data[0] = normalized_image_array
# run the inference
prediction = model.predict(data)
print(prediction)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment