yawc

flag_videos_to_keep.py

@@ -1,11 +1,15 @@
 import json
 import shutil
 import os
+import numpy as np
 source_path = '/srv/ftp/hummingbird/2021'
 #target_path = '/home/thebears/Videos/ftp'
-target_path = '/home/thebears/ftp_links'
-
+target_path = '/home/thebears/data/ftplinks'
+import scipy.stats
+target_mean = 0.4
+target_std = 1
 
+gauss = scipy.stats.norm(target_mean, target_std)
 
 have_json = set()
 for di, _, fns in os.walk(source_path):
@@ -16,38 +20,69 @@ for di, _, fns in os.walk(source_path):
 
 
 
+def box_area(box):
+   return  (box[3]-box[1]) * (box[2] - box[0]) / 100000
 
 
 do_stop = False
 fracs = dict()
 
+saveo = None
+saveb = None
+
+def gaussian(x, mu = target_mean, sig = target_std):
+    return np.exp(-np.power(x - mu, 2.) / (2 * np.power(sig, 2.)))
+
+scc = list()
 for c_js in have_json:
     hits = 0
     total = 0
     o = json.load(open(c_js,'r'))
+    if c_js.endswith('Hummingbird_01_20210701105440.json'):
+        saveo = o
+
+    if c_js.endswith('Hummingbird_01_20210627111405.json'):
+        saveb = o
+
+    avg = 0
+    max_sc = 0
+
     for i in o:
-        total += 1
-#        if len([x for x in i['scores'] if x > 0.1]) > 0:
-        if len(i['boxes']) > 0:
-            hits += 1
-
-    fracs[c_js] = [hits, total]
+#        for x,b in zip(i['scores'], i['boxes']):
+#            scc.append((x,box_area(b)))
+        
+        if len(i['scores']) > 0:
+            css = max(i['scores']) 
+            mf = gaussian(box_area(i['boxes'][0]))
+            avg += css * mf / len(o)
 
 
-    if do_stop:
-        break
+    fracs[c_js] = avg
+
 
 
 
 ratios = dict()
 for x,y in fracs.items():
-    ratios[x] = y[0]/y[1]
-# %%
+    ratios[x] = y
+
+
+
+    
+sorted_ratios = {x:ratios[x] for x in sorted(ratios, key=lambda x: ratios[x])}
+
+
+import shutil
+for d in os.listdir(target_path):
+    shutil.rmtree(target_path + '/' + d)
+
+
+
 import math
 dir_created = set()
-for fname, ratio in ratios.items():
-    cr = math.floor(ratio * 10)/10
-    target_dir = os.path.join(target_path, str(cr))
+for idx, (fname, ratio) in enumerate(sorted_ratios.items()):
+    cr = math.floor(100*ratio)
+    target_dir = os.path.join(target_path, '{0:02g}'.format(cr))
     if not os.path.exists(target_dir) and target_dir not in dir_created:
         os.mkdir(target_dir)
         dir_created.add(target_dir)
@@ -58,5 +93,31 @@ for fname, ratio in ratios.items():
     
     source_file = fname.replace('.json','.mp4')
     target_file = os.path.join(target_dir, os.path.basename(source_file))
-
+  
+    
     os.symlink(source_file, target_file)
+
+    source_file = fname.replace('.json','.json')
+    target_file = os.path.join(target_dir, os.path.basename(source_file))
+    os.symlink(source_file, target_file)
+# %%
+
+if False:
+    plt.close('all')
+    inp = saveo
+
+    sco = list()
+    for x in inp:
+        if len(x['scores']) > 0:
+            cscore = max(x['scores'])
+            ar = box_area(x['boxes'][0])/ 100000
+        else:
+            cscore = 0
+            ar = 0
+        sco.append((cscore, ar))
+
+    plt.plot(sco)
+ 
+# %%
+    distr = np.asarray(scc)
+