def seeResult(self):
image_list = os.listdir(self.images_path)
image_list.sort(key=lambda x: int(x[:-4]))
for all_i, name in enumerate(image_list):
try:
print("当前查看的图片为:", name)
filename = name[:-4]
image_path = os.path.join(self.images_path, name)
txt_path = os.path.join(self.annotations_path,
filename + ".txt")
image = cv.imread(image_path)
txt_file = open(txt_path)
txt_info = txt_file.readlines()
txt_file.close()
ann_infos = []
for line in txt_info:
ann = line.split(',')[:-1]
ann_int = map(int, ann)
number_ann = list(ann_int)
category_id, x1, y1, x2, y2 = number_ann
print("当前的bbox的size为:", (x2 - x1) * (y2 - y1))
print("*************")
ann_infos.append((category_id, x1, y1, x2, y2))
tools.visualize(ann_infos, image)
cv.waitKey(0)
except:
print("发生错误,错误位置在名称{}".format(name))
cv.waitKey(1)
cv.destroyAllWindows()
def refresh_data(self, game, parent):
for row in range(0, settings.ROWS):
for column in range(0, settings.COLUMNS):
text = str(game.display_board[row][column])
self.element = QTableWidgetItem(text)
if text != '':
tools.visualize(self.element, text)
self.setItem(row, column, self.element)
if game.status != settings.GAME_STATUS['playing']:
parent.popup(game.status)
self.game.display_board = game.display_board
def main(img_path, json_path=None, viz=True, renderer=None, config=None):
sess = tf.Session()
model = RunModel(config, sess=sess)
cropped_imgs, params, og_imgs = preprocess_image(img_path, config.img_size,
json_path)
# Add batch dimension: 1 x D x D x 3
input_imgs = [np.expand_dims(input_img, 0) for input_img in cropped_imgs]
# Theta is the 85D vector holding [camera, pose, shape]
# where camera is 3D [s, tx, ty]
# pose is 72D vector holding the rotation of 24 joints of SMPL in axis angle format
# shape is 10D shape coefficients of SMPL
for k in range(len(input_imgs)):
joints, verts, cams, joints3d, theta = model.predict(input_imgs[k],
get_theta=True)
print(joints.shape)
print(verts.shape)
print(cams.shape)
print(joints3d.shape)
print(theta.shape)
if viz:
visualize(og_imgs[k], params[k], joints[0], verts[0], cams[0],
renderer)
from tools import preprocess, confusion, visualize
import matplotlib.pyplot as plt
images_train, images_test, images_valid, labels_train, labels_test, labels_valid = preprocess(
)
neigh = KNeighborsClassifier(n_neighbors=9, weights='distance')
neigh.fit(images_train, labels_train)
result = neigh.predict(images_test)
matrix = confusion(labels_test, result)
print(matrix)
print(accuracy_score(labels_test, result))
figure, ax = plt.subplots()
plt.ylabel('Predictions')
plt.xlabel('Actual')
plt.title('Confusion Matrix for KNearestNeighbor')
plt.xticks([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
plt.yticks([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
ax.matshow(matrix, cmap=plt.cm.Spectral)
x = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
for i in x:
for j in x:
c = matrix[j, i]
ax.text(i, j, str(c), va='center', ha='center')
plt.show()
visualize(images_test, labels_test, result)
def showPrediction(coposition):
visualize(coposition, category_id_to_name)
import argparse
import yaml
import tools
parser = argparse.ArgumentParser()
parser.add_argument('-visualize', action='store_true')
parser.add_argument('-predict', action='store_true')
parser.add_argument('-slice', action='store_true')
parser.add_argument('-evaluate', action='store_true')
args = parser.parse_args()
with open('./configs.yaml', 'r') as stream:
try:
configs = yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
if args.visualize:
tools.visualize(configs)
elif args.predict:
tools.predict(configs)
elif args.slice:
tools.slice_vids(configs)
elif args.evaluate:
tools.evaluate(configs)
else:
raise ValueError(
'Did not set flag: -visualize, -predict, -slice, -evaluate')
bas_predict = basTree.predict(images_test)
mod_predict = modTree.predict(images_test)
cust_predict = custTree.predict(cimg_test)
# create the confusion matrix for the base tree
cm_bas = tools.confusion(labels_test, bas_predict)
print('Classification Report for Basic Tree')
print('Basic Tree Test Accuracy')
print(accuracy_score(labels_test, bas_predict))
print(classification_report(labels_test, bas_predict))
tools.dispMatrix(cm_bas, 'Base Decision Tree Confusion Matrix')
# Look at visualizations for base decision tree
print('Visualization of 3 mistakes made in base tree')
tools.visualize(images_test, labels_test, bas_predict)
# create the confusion matrix for the modified tree
cm_mod = tools.confusion(labels_test, mod_predict)
print('Classification Report for Modified Tree')
print('Modified Tree Test Accuracy')
print(accuracy_score(labels_test, mod_predict))
print(classification_report(labels_test, mod_predict))
tools.dispMatrix(cm_mod, 'Modified Decision Tree Confusion Matrix')
# Look at the visualizations for the modified decision tree
print('Visualization of 3 mistakes made in modified tree')
tools.visualize(images_test, labels_test, mod_predict)
# create the confusion matrix for the Custom Features Tree
cm_cust = tools.confusion(labels_test, cust_predict)
print(cm_cust)