FastDup Software, (C) copyright 2022 Dr. Amir Alush and Dr. Danny Bickson.
2023-07-19 17:23:48 [INFO] Going to loop over dir frames
2023-07-19 17:23:48 [INFO] Found total 4325 images to run on, 4325 train, 0 test, name list 4325, counter 4325
FastDup Software, (C) copyright 2022 Dr. Amir Alush and Dr. Danny Bickson.utes
2023-07-19 17:25:58 [INFO] Going to loop over dir /tmp/crops_input.csv
2023-07-19 17:25:58 [INFO] Found total 2601 images to run on, 2601 train, 0 test, name list 2601, counter 2601
2023-07-19 17:26:04 [INFO] Found total 2601 images to run ontimated: 0 Minutes
Finished histogram 0.412
Finished bucket sort 0.421
2023-07-19 17:26:04 [INFO] 74) Finished write_index() NN model
2023-07-19 17:26:04 [INFO] Stored nn model index file work_dir/nnf.index
2023-07-19 17:26:04 [INFO] Total time took 6161 ms
2023-07-19 17:26:04 [INFO] Found a total of 4 fully identical images (d>0.990), which are 0.08 %
2023-07-19 17:26:04 [INFO] Found a total of 26 nearly identical images(d>0.980), which are 0.50 %
2023-07-19 17:26:04 [INFO] Found a total of 1521 above threshold images (d>0.900), which are 29.24 %
2023-07-19 17:26:04 [INFO] Found a total of 260 outlier images (d<0.050), which are 5.00 %
2023-07-19 17:26:04 [INFO] Min distance found 0.515 max distance 0.992
2023-07-19 17:26:04 [INFO] Running connected components for ccthreshold 0.960000
.0
########################################################################################
Dataset Analysis Summary:
Dataset contains 2601 images
Valid images are 100.00% (2,601) of the data, invalid are 0.00% (0) of the data
Similarity: 3.65% (95) belong to 8 similarity clusters (components).
96.35% (2,506) images do not belong to any similarity cluster.
Largest cluster has 28 (1.08%) images.
For a detailed analysis, use `.connected_components()`
(similarity threshold used is 0.9, connected component threshold used is 0.96).
Outliers: 6.34% (165) of images are possible outliers, and fall in the bottom 5.00% of similarity values.
For a detailed list of outliers, use `.outliers()`.