class Model(ModelBase):
def __init__(self):
# load config file
config = json.load(open("model/config.json"))
# get the image processor
self._imageProcessor = ImageProcessor(config)
# load the DL model
self._model = Xception()
self._model.load_weights('model/model.h5')
self._model._make_predict_function()
def infer(self, input):
# load preprocessed input
inputAsNpArr = self._imageProcessor.loadAndPreprocess(input)
# Run inference with caffe2
results = self._model.predict(inputAsNpArr)
# postprocess results into output
output = self._imageProcessor.computeOutput(results)
return output
steps_per_epoch=x_train.shape[0] //
batch_size)
else:
History = model.fit_generator(datagen.flow(x_train,
y_train,
batch_size=batch_size),
epochs=epochs,
verbose=1,
steps_per_epoch=x_train.shape[0] //
batch_size)
#generate submission
if (options.save_submission):
print("generate submission...")
predict = np.argmax(model.predict(test), axis=1)
output = pd.DataFrame(le.inverse_transform(predict))
output.columns
output.columns = ['Expected']
output.index.name = "Id"
output.to_csv("../submission/submission_" + options.model + versioninfo +
".csv")
#save weight
if (options.save_weight):
print("save weight...")
model.save_weights("../weight/" + options.model + versioninfo + ".h5")
#save history
if (options.save_history):
print("save history...")