From 8404d93880bcb8a0bd614c70e46c0757cd031519 Mon Sep 17 00:00:00 2001
From: c <lianghongkey@gmail.com>
Date: Wed, 18 Dec 2019 18:22:59 +0800
Subject: [PATCH] Speed up by multi cpu to handle histogram

---
 FilterEvaluator/EvaluatorUnsuper.py | 77 +++++++++++++++++++++++------
 1 file changed, 63 insertions(+), 14 deletions(-)

diff --git a/FilterEvaluator/EvaluatorUnsuper.py b/FilterEvaluator/EvaluatorUnsuper.py
index 964534b..608a878 100644
--- a/FilterEvaluator/EvaluatorUnsuper.py
+++ b/FilterEvaluator/EvaluatorUnsuper.py
@@ -179,12 +179,15 @@ def UnsuperLearnFindBestWeight(netmodel, layer, weight, dataloader, databatchs=1
     interationbar.close()
     return bestweight,indexs[sortindex]
 
+
+
+
+
 # search best weight from random data
 def UnsuperLearnSearchBestWeight(netmodel, layer, dataloader, databatchs=128, stepsize=1000, interation=1000):
     interationbar = tqdm(total=interation)    
     forwardlayer = layer -1
-    bestweight = []
-    bestentropy = 100.0
+
     netmodel.eval()
     tl = netmodel.features[layer]
     outchannels = tl.out_channels
@@ -208,7 +211,41 @@ def UnsuperLearnSearchBestWeight(netmodel, layer, dataloader, databatchs=128, st
     for i in range(outchannels):
         shift.append(1<<i)
     shift = utils.SetDevice(torch.from_numpy(np.array(shift).astype("uint8")))
+    # shift = torch.from_numpy(np.array(shift).astype("uint8"))
     
+    bestweight = []
+    bestentropy = [100.0]
+    bittedset = []
+    bittedLock = threading.Lock()
+    bestLock = threading.Lock()
+
+    class CPU (threading.Thread):  
+        def __init__(self):
+            threading.Thread.__init__(self)
+        def run(self):
+            hasdata = 0
+            bittedLock.acquire()
+            if len(bittedset)>0:
+                bitted = bittedset.pop()
+                hasdata = 1
+            bittedLock.release()
+            if hasdata > 0:
+                entropys = []
+                for i in range(len(indexs)):
+                    histced = bitted[:,i].histc(256,0,255).type(torch.float32)
+                    histced = histced[histced>0]
+                    histced = histced/histced.sum()
+                    entropy = (histced.log2()*histced).sum()
+                    entropys.append(entropy.numpy())
+                argmin = np.argmin(entropys)
+
+                bestLock.acquire()
+                if entropys[argmin] < bestentropy[0]:
+                    bestweight = newweight[indexs[argmin]]
+                    bestentropy[0] = entropys[argmin]
+                    print("finded better entropy")
+                bestLock.release()
+
     for j in range(interation):
         newweightshape = list(newlayer.weight.data.shape)
         newweightshape[0] = stepsize
@@ -228,21 +265,33 @@ def UnsuperLearnSearchBestWeight(netmodel, layer, dataloader, databatchs=128, st
         # 1000 8
         meaned = reshaped.mean(0)
         # 102400 1000
-        bitted = ((reshaped > meaned)* shift).sum(2).type(torch.float32)
+        bitted = ((reshaped > meaned)* shift).sum(2).type(torch.float32).detach().cpu()
         
-        entropys = []
-        for i in range(len(indexs)):
-            histced = bitted[:,i].histc(256,0,255).type(torch.float32)
-            histced = histced[histced>0]
-            histced = histced/histced.sum()
-            entropy = (histced.log2()*histced).sum()
-            entropys.append(entropy.detach().cpu().numpy())
+        bittedLock.acquire()
+        bittedset.append(bitted)
+        bittedLock.release()
+        threadcpu = CPU()
+        threadcpu.start()
+
+        # entropys = []
+        # for i in range(len(indexs)):
+        #     histced = bitted[:,i].histc(256,0,255).type(torch.float32)
+        #     histced = histced[histced>0]
+        #     histced = histced/histced.sum()
+        #     entropy = (histced.log2()*histced).sum()
+        #     entropys.append(entropy.detach().cpu().numpy())
         
-        argmin = np.argmin(entropys)
-        if entropys[argmin] < bestentropy:
-            bestweight = newweight[indexs[argmin]]
-            bestentropy = entropys[argmin]
+        # argmin = np.argmin(entropys)
+        # if entropys[argmin] < bestentropy:
+        #     bestweight = newweight[indexs[argmin]]
+        #     bestentropy = entropys[argmin]
+
         interationbar.update(1)
+        interationbar.set_description("left:"+str(len(bittedset)))
+
+    while bittedset:
+        time.sleep(100)
+    
     interationbar.close()
     return bestweight