1 npy

Author: yxdragon

cnnumpy/io.py

@@ -98,9 +98,5 @@ def read_onnx(path):
 
 	net = Net()
 	net.load_json(body, flow)
-	if os.path.exists(path+'_bn.npy'):
-		bn = np.load(path+'_bn.npy')
-	else:
-		bn = []
-	net.load_weights(np.load(path+'.npy'), bn)
+	net.load_weights(np.load(path+'.npy'))
 	return net

cnnumpy/layer.py

@@ -126,22 +126,19 @@ def __init__(self, c):
         self.v = np.zeros(c, dtype=np.float32)
 
     def forward(self, x):
-
-        x = (x - self.m.reshape(1, -1, 1, 1))/np.sqrt(self.v.reshape(1, -1, 1, 1)) * self.k.reshape(1, -1, 1, 1) + self.b.reshape(1, -1, 1, 1)
-
+        x = (x - self.m.reshape(1, -1, 1, 1))
+        x /= np.sqrt(self.v.reshape(1, -1, 1, 1))
+        x *= self.k.reshape(1, -1, 1, 1) 
+        x += self.b.reshape(1, -1, 1, 1)
         return x
 
     def load(self, buf):
         c = self.c
-        self.k = buf[:c]
-        self.b = buf[c:2*c]
-        return self.c * 2
-
-    def load_bn(self, buf):
-        c = self.c
-        self.m = buf[:c]
-        self.v = buf[c:2*c]
-        return self.c * 2
+        self.k[:] = buf[0*c:1*c]
+        self.b[:] = buf[1*c:2*c]
+        self.m[:] = buf[2*c:3*c]
+        self.v[:] = buf[3*c:4*c]
+        return self.c * 4
 
 layerkey = {'dense':Dense, 'conv':Conv2d, 'relu':ReLU, 'batchnorm':BatchNorm,
     'flatten':Flatten, 'sigmoid':Sigmoid, 'softmax': Softmax,

cnnumpy/net.py

@@ -66,13 +66,9 @@ def flw2code(self, style='list'):
 				body.append('')
 		return '\n'.join(body)
 
-	def load_weights(self, data, data_bn):
+	def load_weights(self, data):
 		s = 0
-		b = 0
 		for i in self.body: 
-			if 'batchnorm' in i[0]:
-				# print(i[0])
-				b += i[1].load_bn(data_bn[b:])
 			s += i[1].load(data[s:])
 		# print(data.shape, s)
 		# print(data_bn.shape, b)

demo/craft_text_detector/main.py

@@ -1,3 +1,5 @@
+import sys
+sys.path.append('../../')
 from cnnumpy import read_onnx
 import numpy as np
 from matplotlib import pyplot as plt