Created
May 12, 2019 12:29
-
-
Save philographer/d2a2253d34890b2697c7278b3b99a5b1 to your computer and use it in GitHub Desktop.
민식이 과제
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
from keras.models import Sequential | |
from keras.layers import Dense | |
from sklearn.model_selection import train_test_split | |
import pandas as pd | |
import numpy as np | |
import tensorflow as tf | |
seed=0 | |
np.random.seed(seed) | |
tf.set_random_seed(seed) | |
df=pd.read_csv("./dataset.csv") | |
df.head() | |
dataset=df.values | |
x=dataset[:,1:6] | |
y=dataset[:,0] | |
x_train, x_test, y_train, y_test = train_test_split(x,y, test_size=0.3, random_state=seed) | |
model=Sequential() | |
model.add(Dense(30, input_dim=5, activation='relu')) | |
model.add(Dense(8, activation='relu')) | |
model.add(Dense(4, activation='relu')) | |
model.add(Dense(1)) | |
model.compile(loss='mean_squared_error', optimizer='adam') | |
model.fit(x_train, y_train, epochs=500, batch_size=20) | |
y_prediction=model.predict(x_test).flatten() | |
for i in range(20): | |
label=y_test[i] | |
prediction=y_prediction[i] | |
print("실제DISP : {:.3f}, 예상DISP : {:.3f}".format(label, prediction)) | |
model.save('it.h5') | |
model.to_json() | |
with open('model.json', 'w') as f: | |
f.write(model.to_json()) | |
from keras.models import load_model | |
model = load_model('./it.h5') | |
ship_element=np.array([141.1,24.2,13.2,9.714,0.9866]) | |
ship_element=np.expand_dims(ship_element, axis=0) | |
model.predict(ship_element) | |
import os | |
import os.path as osp | |
import argparse | |
import tensorflow as tf | |
from keras.models import load_model | |
from keras import backend as K | |
def convertGraph( modelPath, outdir, numoutputs, prefix, name): | |
if not os.path.isdir(outdir): | |
os.mkdir(outdir) | |
K.set_learning_phase(0) | |
net_model = load_model(modelPath) | |
pred = [None]*numoutputs | |
pred_node_names = [None]*numoutputs | |
for i in range(numoutputs): | |
pred_node_names[i] = prefix+'_'+str(i) | |
pred[i] = tf.identity(net_model.output[i], name=pred_node_names[i]) | |
print('Output nodes names are: ', pred_node_names) | |
sess = K.get_session() | |
f = 'graph_def_for_reference.pb.ascii' | |
tf.train.write_graph(sess.graph.as_graph_def(), outdir, f, as_text=True) | |
print('Saved the graph definition in ascii format at: ', osp.join(outdir, f)) | |
from tensorflow.python.framework import graph_util | |
from tensorflow.python.framework import graph_io | |
constant_graph = graph_util.convert_variables_to_constants(sess, sess.graph.as_graph_def(), pred_node_names) | |
graph_io.write_graph(constant_graph, outdir, name, as_text=False) | |
print('Saved the constant graph (ready for inference) at: ', osp.join(outdir, name)) | |
convertGraph("it.h5","./",2,"k2tfout","output_graph.pb") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment