def main() -> None:
if len(sys.argv) <= 1:
print(
'Usage: python main.py [1 or 2 for 2b part 1 and 2 respectively]')
exit(-1)
sim_to_run = sys.argv[1]
factors = [
Factor(['Trav'], [], [0.05, 0.95]),
Factor(['Fraud'], ['Trav'], [0.01, 0.99, 0.004, 0.996]),
Factor(['OC'], [], [0.7, 0.3]),
Factor(['CRP'], ['OC'], [0.1, 0.9, 0.001, 0.999]),
Factor(['FP'], ['Trav', 'Fraud'],
[0.9, 0.1, 0.9, 0.1, 0.1, 0.9, 0.01, 0.99]),
Factor(['IP'], ['OC', 'Fraud'],
[0.02, 0.98, 0.01, 0.99, 0.011, 0.989, 0.001, 0.999])
]
if sim_to_run == '1':
inference(factors, ['Fraud'], ['Trav', 'FP', 'IP', 'OC', 'CRP'], [])
else:
inference(factors, ['Fraud'], ['Trav', 'OC'], [('FP', Sign.POSITIVE),
('IP', Sign.NEGATIVE),
('CRP', Sign.POSITIVE)])
def main():
root = tkinter.Tk()
root.geometry('300x400')
frame = tkinter.Frame(root, width=256, height=256)
frame.pack_propagate(0)
frame.pack(side='top')
canvas1 = MyCanvas(frame)
infer = inference()
def inference_click():
img = canvas1.image1
result = infer.predict(img)
result = int(result)
canvas1.canvas.delete("all")
canvas1.image1 = Image.new("RGB", (256, 256), "black")
canvas1.draw = ImageDraw.Draw(canvas1.image1)
label2["text"] = str(result)
botton_Inference = tkinter.Button(root,
text="Inference",
width=7,
height=1,
command=inference_click)
botton_Inference.pack()
label1 = tkinter.Label(root, justify="center", text="Inference result is")
label1.pack()
label2 = tkinter.Label(root, justify="center")
label2["font"] = ("Arial, 48")
label2.pack()
root.mainloop()
def main():
root = tkinter.Tk()
root.geometry('300x400')
frame = tkinter.Frame(root, width=256, height=256)
frame.pack_propagate(0)
frame.pack(side='top')
canvas1 = MyCanvas(frame)
infer = inference()
def inference_click():
img = canvas1.image1
result = infer.predict(img)
result = int(result)
canvas1.canvas.delete("all")
canvas1.image1 = Image.new("RGB", (256, 256), "black")
canvas1.draw = ImageDraw.Draw(canvas1.image1)
label2["text"] = str(result)
botton_Inference = tkinter.Button(root,
text="Inference",
width=7,
height=1,
command=inference_click
)
botton_Inference.pack()
label1 = tkinter.Label(root, justify="center", text="Inference result is")
label1.pack()
label2 = tkinter.Label(root, justify="center")
label2["font"] = ("Arial, 48")
label2.pack()
root.mainloop()
def inference_click():
img = canvas1.image1
result = inference(img)
result = int(result)
canvas1.canvas.delete("all")
canvas1.image1 = Image.new("RGB", (256, 256), "black")
canvas1.draw = ImageDraw.Draw(canvas1.image1)
label2["text"] = str(result)
def main():
# ................................产生随机数.................................
ram_x_t_data1 = np.random.rand(50, 10)
ram_x_t_data2 = np.random.rand(50, 256)
ram_y_t_data = np.ones([500, 1])
path = './vgg_output/Data1_fc2_D_no_D1.txt'
path1 = './vgg_output/Data1_fc1_D_no_D1.txt'
input = np.loadtxt(path)
input1 = np.loadtxt(path1)
Inter = inference()
result, accuracy = Inter.predict(input, input1, ram_y_t_data)
print('The result of predicting is \n', result)
print('accuracy is ', accuracy)
#!/usr/bin/python3.6
"""
@Author: xiaxianyi<*****@*****.**>
@Time: 2021/4/5 9:11
@File: test.py
Description:
"""
import tensorflow as tf
from Inference import inference
import tensorflow_core.examples.tutorials.mnist.input_data as input_data
if __name__ == '__main__':
mnist = input_data.read_data_sets("MNIST_data/", one_hot=False)
infer = inference()
test_data = mnist.test
num_examples = test_data._num_examples
count = 0
for i in range(num_examples):
batch = mnist.train.next_batch(1)
pred = infer.predict(batch[0])
label = batch[1]
if pred[0] == label[0]:
count += 1
print("test data accuracy: ", count / 10000)
with open(Name_list, "r") as f:
lines = f.read().splitlines()
lines_shuffled = np.random.permutation(lines)
Sample_size = 500
lines_sampled = lines_shuffled[0:Sample_size]
iou_vec = np.zeros((21, 3, 3))
for i, theta1 in enumerate(np.linspace(1, 121, 3)):
for j, theta2 in enumerate(np.linspace(1, 21, 3)):
int_vec = np.zeros((21, Sample_size))
union_vec = np.zeros((21, Sample_size))
theta = np.array([theta1, theta2])
for ptr, line in enumerate(lines_sampled):
Q = inference(theta, line, Image_dir, Unary_dir, Prediction_dir,
False)
img_truth_name = os.path.join(Ground_truth_dir, line) + '.png'
img_truth = imread(img_truth_name)
truth_data = utils.convert_from_color_segmentation(img_truth)
for class_idx in range(0, 21):
int_i, uni_i = eval.int_uni_cls(truth_data, Q, class_idx)
int_vec[class_idx, ptr] = int_i
union_vec[class_idx, ptr] = uni_i
iou_vec[:, i, j] = [
np.sum(int_vec[i]) / np.sum(union_vec[i]) for i in range(21)
]
scipy.io.savemat(
os.path.join(output_path, "grid_search_" + str(i * 3 + j)),
{"grid_search": iou_vec[:, i, j]})
scipy.io.savemat(os.path.join(output_path, "grid_search"),
{"grid_search": iou_vec})