5
我試圖出稱爲「Factorized CNN」最近的arXiv工作,tf.nn.depthwise_conv2d太慢了。這是正常的嗎?
主要認爲在空間上分離卷積(深度方向卷積),與信道分段線性投影(1x1conv)一起,可以加快卷積運算。
this is the figure for their conv layer architecture
我發現我可以實現這個架構tf.nn.depthwise_conv2d和1x1的卷積,或tf.nn.separable_conv2d。下面
是我實現:
#conv filter for depthwise convolution
depthwise_filter = tf.get_variable("depth_conv_w", [3,3,64,1], initializer=tf.random_normal_initializer(stddev=np.sqrt(2.0/9/32)))
#conv filter for linear channel projection
pointwise_filter = tf.get_variable("point_conv_w", [1,1,64,64], initializer=tf.random_normal_initializer(stddev=np.sqrt(2.0/1/64)))
conv_b = tf.get_variable("conv_b", [64], initializer=tf.constant_initializer(0))
#depthwise convolution, with multiplier 1
conv_tensor = tf.nn.relu(tf.nn.depthwise_conv2d(tensor, depthwise_filter, [1,1,1,1], padding='SAME'))
#linear channel projection with 1x1 convolution
conv_tensor = tf.nn.bias_add(tf.nn.conv2d(conv_tensor, pointwise_filter, [1,1,1,1], padding='VALID'), conv_b)
#residual
tensor = tf.add(tensor, conv_tensor)
這應該是更快的約9倍,比原來的3x3x64 - > 64通道卷積。
但是,我無法體驗到任何性能改進。
我必須假設我做錯了,或者張量流的實現出了問題。
由於使用depthwise_conv2d的例子很少,所以我在這裏留下這個問題。
這是慢速正常嗎?或者有什麼錯誤?