Skip to content

Instantly share code, notes, and snippets.

@nesterione
Created July 7, 2017 20:35
Show Gist options
  • Select an option

  • Save nesterione/25d4a0e01dc441b72f1350afc782e6e4 to your computer and use it in GitHub Desktop.

Select an option

Save nesterione/25d4a0e01dc441b72f1350afc782e6e4 to your computer and use it in GitHub Desktop.
import pandas as pd
from keras.models import load_model
model = load_model('./nn_dence.h5')
model.load_weights('./nn_dence_weights.h5')
# model = load_model('./nn_cnn.h5')
# model.load_weights('./nn_cnn_weights.h5')
# ImageId,Label
# np.array(tk.texts_to_sequences(text))
data = pd.read_csv("./data/test.csv")
data_set = data.as_matrix()
X_test = data_set
# X_test = np.reshape(X_test,(X_test.shape[0],28,28,1))
print(X_test.shape)
# normalize
x_train = X_test.astype('float32')
x_train /= 255
prediction = model.predict_classes(x_train)
with open('result.csv', 'w') as f:
f.write('ImageId,Label\n')
for i, v in enumerate(prediction):
f.write(str(i+1)+","+str(v)+"\n")
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment