1
我已經從kaggle下載了一個由keras8分類器工作的DL模型。顯然，它有密集的（8）在model.and的頂部，我想用它作爲2分類器，所以我修改了從密集（8）到密集（2）的頂部完整連接。我認爲這對我很有用。但是，終端會在運行腳本時報告錯誤，感謝您的耐心和幫助。 錯誤下面我已經從kaggle下載了一個DL模型，用於keras的8分類器工作
Error when checking model target: expected dense_3 to have shape (None, 2) but got array with shape (1333L, 8L)
和這裏是代碼，也許長
# %load kaggle_dog_cat_classifier.py
__author__ = 'JeofuHuang: https://www.kaggle.com/jeofuhuang'
import numpy as np
np.random.seed(2016)
import os
import glob
import cv2
import datetime
import pandas as pd
import time
import warnings
warnings.filterwarnings("ignore")
from sklearn.cross_validation import KFold
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.optimizers import SGD
from keras.callbacks import EarlyStopping
from keras.utils import np_utils
from sklearn.metrics import log_loss
from keras import __version__ as keras_version
def get_im_cv2(path):
img = cv2.imread(path)
resized = cv2.resize(img, (32, 32), cv2.INTER_LINEAR)
return resized
def load_train():
X_train = []
X_train_id = []
y_train = []
start_time = time.time()
print('Read train images')
folders = ['dog', 'cat']
for fld in folders:
index = folders.index(fld)
print('Load folder {} (Index: {})'.format(fld, index))
path = os.path.join('.', 'input', 'train', fld, '*.jpg')
files = glob.glob(path)
for fl in files:
flbase = os.path.basename(fl)
img = get_im_cv2(fl)
X_train.append(img)
X_train_id.append(flbase)
y_train.append(index)
print('Read train data time: {} seconds'.format(round(time.time() - start_time, 2)))
return X_train, y_train, X_train_id
def load_test():
path = os.path.join('.', 'input', 'test', '*.jpg')
files = sorted(glob.glob(path))
X_test = []
X_test_id = []
for fl in files:
flbase = os.path.basename(fl)
img = get_im_cv2(fl)
X_test.append(img)
X_test_id.append(flbase)
return X_test, X_test_id
def create_submission(predictions, test_id, info):
result1 = pd.DataFrame(predictions, columns=['dog', 'cat'])
result1.loc[:, 'image'] = pd.Series(test_id, index=result1.index)
now = datetime.datetime.now()
sub_file = 'submission_' + info + '_' + str(now.strftime("%Y-%m-%d-%H-%M")) + '.csv'
result1.to_csv(sub_file, index=False)
def read_and_normalize_train_data():
train_data, train_target, train_id = load_train()
print('Convert to numpy...')
train_data = np.array(train_data, dtype=np.uint8)
train_target = np.array(train_target, dtype=np.uint8)
print('Reshape...')
train_data = train_data.transpose((0, 3, 1, 2))
print('Convert to float...')
train_data = train_data.astype('float32')
train_data = train_data/255
train_target = np_utils.to_categorical(train_target, 8)
print('Train shape:', train_data.shape)
print(train_data.shape[0], 'train samples')
return train_data, train_target, train_id
def read_and_normalize_test_data():
start_time = time.time()
test_data, test_id = load_test()
test_data = np.array(test_data, dtype=np.uint8)
test_data = test_data.transpose((0, 3, 1, 2))
test_data = test_data.astype('float32')
test_data = test_data/255
print('Test shape:', test_data.shape)
print(test_data.shape[0], 'test samples')
print('Read and process test data time: {} seconds'.format(round(time.time() - start_time, 2)))
return test_data, test_id
def dict_to_list(d):
ret = []
for i in d.items():
ret.append(i[1])
return ret
def merge_several_folds_mean(data, nfolds):
a = np.array(data[0])
for i in range(1, nfolds):
a += np.array(data[i])
a /= nfolds
return a.tolist()
def create_model():
model = Sequential()
model.add(ZeroPadding2D((1, 1), input_shape=(3, 32, 32), dim_ordering='th'))
model.add(Convolution2D(4, 3, 3, activation='relu', dim_ordering='th'))
model.add(ZeroPadding2D((1, 1), dim_ordering='th'))
model.add(Convolution2D(4, 3, 3, activation='relu', dim_ordering='th'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), dim_ordering='th'))
model.add(ZeroPadding2D((1, 1), dim_ordering='th'))
model.add(Convolution2D(8, 3, 3, activation='relu', dim_ordering='th'))
model.add(ZeroPadding2D((1, 1), dim_ordering='th'))
model.add(Convolution2D(8, 3, 3, activation='relu', dim_ordering='th'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), dim_ordering='th'))
model.add(Flatten())
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))
sgd = SGD(lr=1e-2, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd, loss='categorical_crossentropy')
return model
def get_validation_predictions(train_data, predictions_valid):
pv = []
for i in range(len(train_data)):
pv.append(predictions_valid[i])
return pv
def run_cross_validation_create_models(nfolds=10):
# input image dimensions
batch_size = 16
nb_epoch = 30
random_state = 51
train_data, train_target, train_id = read_and_normalize_train_data()
yfull_train = dict()
kf = KFold(len(train_id), n_folds=nfolds, shuffle=True,
random_state=random_state)
num_fold = 0
sum_score = 0
models = []
for train_index, test_index in kf:
model = create_model()
X_train = train_data[train_index]
Y_train = train_target[train_index]
X_valid = train_data[test_index]
Y_valid = train_target[test_index]
num_fold += 1
print('Start KFold number {} from {}'.format(num_fold, nfolds))
print('Split train: ', len(X_train), len(Y_train))
print('Split valid: ', len(X_valid), len(Y_valid))
callbacks = [
EarlyStopping(monitor='val_loss', patience=3, verbose=0),
]
model.fit(X_train, Y_train, batch_size=batch_size,
nb_epoch=nb_epoch,shuffle=True, verbose=2, validation_data=
(X_valid, Y_valid), callbacks=callbacks)
predictions_valid = model.predict(X_valid.astype('float32'),
batch_size=batch_size, verbose=2)
score = log_loss(Y_valid, predictions_valid)
print('Score log_loss: ', score)
sum_score += score*len(test_index)
# Store valid predictions
for i in range(len(test_index)):
yfull_train[test_index[i]] = predictions_valid[i]
models.append(model)
score = sum_score/len(train_data)
print("Log_loss train independent avg: ", score)
info_string = 'loss_' + str(score) + '_folds_' + str(nfolds) + '_ep_' +
str(nb_epoch)
return info_string, models
def run_cross_validation_process_test(info_string, models):
batch_size = 16
num_fold = 0
yfull_test = []
test_id = []
nfolds = len(models)
for i in range(nfolds):
model = models[i]
num_fold += 1
print('Start KFold number {} from {}'.format(num_fold, nfolds))
test_data, test_id = read_and_normalize_test_data()
test_prediction = model.predict(test_data, batch_size=batch_size,
verbose=2)
yfull_test.append(test_prediction)
test_res = merge_several_folds_mean(yfull_test, nfolds)
info_string = 'loss_' + info_string \ + '_folds_' + str(nfolds)
create_submission(test_res, test_id, info_string)
if __name__ == '__main__':
print('Keras version: {}'.format(keras_version))
num_folds = 3
info_string, models = run_cross_validation_create_models(num_folds)
run_cross_validation_process_test(info_string, models)