and from urn -h png app 比較 get round

一、基本環境$ pip install flask gevent requests pillow其中 flask不需要解釋gevent 是用於自動切換進程的；pillow 是用來進行python下的圖像處理的；requests 是用來進行python下request處理的。
二、核心代碼解釋# import the necessary packagesfrom keras.applications import ResNet50from keras.preprocessing.image import img_to_arrayfrom keras.applications import imagenet_utilsfrom PIL import Imageimport numpy as npimport flaskimport io引入所需的頭文件。其中註意keras的幾個類庫是很有通用性的；# initialize our Flask application and the Keras modelapp = flask.Flask(__name__)model = None類庫的初始化def load_model(): # load the pre-trained Keras model (here we are using a model # pre-trained on ImageNet and provided by Keras, but you can # substitute in your own networks just as easily) global model model = ResNet50(weights="imagenet")引入model模型，如果想引入自己的模型(CBIR)的話，就在這裏引入。def prepare_image(image, target): # if the image mode is not RGB, convert it if image.mode != "RGB": image = image.convert("RGB")
# resize the input image and preprocess it image = image.resize(target) image = img_to_array(image) image = np.expand_dims(image, axis=0) image = imagenet_utils.preprocess_input(image)
# return the processed image return imageimage的預處理，這裏使用的是keras+PIL，和opencv之間的比較，需要有時間來做。@app.route("/predict", methods=["POST"])def predict(): # initialize the data dictionary that will be returned from the # view data = {"success": False}
# ensure an image was properly uploaded to our endpoint if flask.request.method == "POST": if flask.request.files.get("image"): # read the image in PIL format image = flask.request.files["image"].read() image = Image.open(io.BytesIO(image))
# preprocess the image and prepare it for classification image = prepare_image(image, target=(224, 224))
# classify the input image and then initialize the list # of predictions to return to the client preds = model.predict(image) results = imagenet_utils.decode_predictions(preds) data["predictions"] = []
# loop over the results and add them to the list of # returned predictions for (imagenetID, label, prob) in results[0]: r = {"label": label, "probability": float(prob)} data["predictions"].append(r)
# indicate that the request was a success data["success"] = True
# return the data dictionary as a JSON response return flask.jsonify(data)雖然是核心部分，但是其實非常容易被復用。就是讀取數據，然後進行處理的過程。 # if this is the main thread of execution first load the model and# then start the serverif __name__ == "__main__": print(("* Loading Keras model and Flask starting server..." "please wait until server has fully started")) load_model() app.run()
比不可少的main過程。缺少不可運行。三、運行效果使用VPS能夠更快地得到效果，至少你不需要下載resnet*.h5，一個鏈路不是太好的大物件。

flask的運行效果，使用curl進行處理的效果


從結果上來看，curch排在了第2，而將這張圖片識別為鐘樓或者修道院、城堡，宮殿，似乎也沒有什麽不妥。四、小結反思
真的僅僅是通過了幾行代碼，就實現了flask部署的核心問題。不過光是跑這個簡單的過程，機器就已經發出巨大的熱量了；另一方面，整個的結構是什麽，也需要進一步去研究清楚才對。




來自為知筆記(Wiz)

Building a Keras + deep learning REST API（三部曲之一）