tony607 / landmark-retrival Goto Github PK

itertools doesnot have any accumulate function. Is there any alternative?

DELF特征的提取匹配的过程，是否可以用于实时的图像检索系统，我实验中发现使用ransac这一步会耗费很长的时间，希望得到你的回复

Hello
I am a newbie to Google Colab and tensorflow.
When I ran your code I always got an error at: Perform geometric verification using RANSAC and visualization

The error says:

ValueError Traceback (most recent call last)
in ()
10 min_samples=3,
11 residual_threshold=20,
---> 12 max_trials=1000)
13 # If no inlier is found for a database candidate image, we continue on to the next one.
14 if inliers is None or len(inliers) == 0:
/usr/local/lib/python3.6/dist-packages/skimage/measure/fit.py in ransac(data, model_class, min_samples, residual_threshold, is_data_valid, is_model_valid, max_trials, stop_sample_num, stop_residuals_sum, stop_probability, random_state, initial_inliers)
797
798 if not (0 < min_samples < num_samples):
--> 799 raise ValueError("min_samples must be in range (0, )")
800
801 if residual_threshold < 0:

ValueError: min_samples must be in range (0, )

I ran the code exactly as it was I only defined the paths to the images etc...
It would be amazing if you could help me here and I would like to say thank you for this great work!

Is there an associated license for use?