#print "after resize and gray:",type(img),img.shape,img.dtype
#show the gray img
#cv2.imshow("w2",img)
#cv2.waitKey(0)
#reshape (h,w) to (h*w,)
img=img.reshape(w*h)
feature= []
feature.append(img_label(img_name))
for f_v in img:
feature.append(f_v)
features_list.append(feature)
print len(features_list),len(features_list[0]),len(features_list[-1])
train_index_list = random.sample(range(len(features_list)), len(features_list)/2 )
train_features_list = []
for i in train_index_list:
train_features_list.append(features_list[i])
valid_features_list = []
for i in range(len(features_list)):
if i in train_index_list:
continue
valid_features_list.append(features_list[i])
print len(train_features_list)
print len(valid_features_list)
# write / cover content to file
tdtf.wr_content_to_csv(train_features_list,train_feature_filename)
tdtf.wr_content_to_csv(valid_features_list,valid_feature_filename)
return int(img_name.split(".")[0])
features_list = []
img_name_list = os.listdir(DataHome + src_img_route)
for img_name in img_name_list:
img = cv2.imread(DataHome + src_img_route + img_name)
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# to resize
w, h = (50, 50)
img = cv2.resize(img, (w, h), interpolation=cv2.INTER_LINEAR)
#print "after resize and gray:",type(img),img.shape,img.dtype
#show the gray img
#cv2.imshow("w2",img)
#cv2.waitKey(0)
#reshape (h,w) to (h*w,)
img = img.reshape(w * h)
feature = []
feature.append(img_label(img_name))
for f_v in img:
feature.append(f_v)
features_list.append(feature)
features_list.sort()
print len(features_list), len(features_list[0]), len(features_list[-1])
print features_list[0][0], features_list[-1][0]
tdtf.wr_content_to_csv(features_list, test_feature_filename)
def img_label(img_name):
return int(img_name.split(".")[0])
features_list = []
img_name_list = os.listdir(DataHome + src_img_route)
for img_name in img_name_list:
img = cv2.imread(DataHome + src_img_route + img_name)
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# to resize
w,h=(50,50)
img = cv2.resize(img,(w,h),interpolation=cv2.INTER_LINEAR)
#print "after resize and gray:",type(img),img.shape,img.dtype
#show the gray img
#cv2.imshow("w2",img)
#cv2.waitKey(0)
#reshape (h,w) to (h*w,)
img=img.reshape(w*h)
feature= []
feature.append(img_label(img_name))
for f_v in img:
feature.append(f_v)
features_list.append(feature)
features_list.sort()
print len(features_list),len(features_list[0]),len(features_list[-1])
print features_list[0][0], features_list[-1][0]
tdtf.wr_content_to_csv(features_list,test_feature_filename)
#print "after resize and gray:",type(img),img.shape,img.dtype
#show the gray img
#cv2.imshow("w2",img)
#cv2.waitKey(0)
#reshape (h,w) to (h*w,)
img=img.reshape(w*h)
feature= []
feature.append(img_label(img_name))
for f_v in img:
feature.append(f_v)
features_list.append(feature)
print len(features_list),len(features_list[0]),len(features_list[-1])
'''
train_index_list = random.sample(range(len(features_list)), len(features_list)/2 )
train_features_list = []
for i in train_index_list:
train_features_list.append(features_list[i])
valid_features_list = []
for i in range(len(features_list)):
if i in train_index_list:
continue
valid_features_list.append(features_list[i])
print len(train_features_list)
print len(valid_features_list)
# write / cover content to file
tdtf.wr_content_to_csv(train_features_list,train_feature_filename)
tdtf.wr_content_to_csv(valid_features_list,valid_feature_filename)
