average pool python code

theano/sandbox/cuda/dnn.py

@@ -1606,7 +1606,7 @@ if True:
 
     @register_opt('cudnn')
     @local_optimizer([DownsampleFactorMax])
-    def local_pool_dnn_stride(node):
+    def local_pool_dnn_alternative(node):
         if not dnn_available():
             return
         if isinstance(node.op, DownsampleFactorMax):
@@ -1616,9 +1616,10 @@ if True:
             ds = node.op.ds
             stride = node.op.st
             pad = node.op.padding
+            mode = node.op.mode
             if (img.owner and isinstance(img.owner.op, HostFromGpu)):
                 ret = dnn_pool(gpu_contiguous(img.owner.inputs[0]),
-                               ds, stride=stride, pad=pad)
+                               ds, stride=stride, pad=pad, mode=mode)
                 return [host_from_gpu(ret)]
 
     @register_opt('cudnn')
@@ -1648,12 +1649,13 @@ if True:
             ds = node.op.ds
             st = node.op.st
             pad = node.op.padding
+            mode = node.op.mode
 
             if ((inp.owner and isinstance(inp.owner.op, HostFromGpu)) or
                 (out.owner and isinstance(out.owner.op, HostFromGpu)) or
                 (inp_grad.owner and isinstance(inp_grad.owner.op,
                                                HostFromGpu))):
-                desc = GpuDnnPoolDesc(ws=ds, stride=st, mode="max", pad=pad)()
+                desc = GpuDnnPoolDesc(ws=ds, stride=st, mode=mode, pad=pad)()
                 if not node.op.ignore_border:
                     return
                 ret = GpuDnnPoolGrad()(gpu_contiguous(inp),

theano/sandbox/cuda/opt.py

@@ -1643,8 +1643,9 @@ import theano.tensor.signal.downsample as downsample
 def local_gpu_downsample_factor_max(node):
     if (isinstance(node.op, downsample.DownsampleFactorMax)
         and node.op.ds == node.op.st):
-        assert node.op.__props__ == ('ds', 'ignore_border', 'st', 'padding')
-        if node.op.padding != (0, 0):
+        assert node.op.__props__ == ('ds', 'ignore_border', 'st', 'padding',
+                                     'mode')
+        if node.op.padding != (0, 0) or node.op.mode != 'max':
             return
         x, = node.inputs
         if (x.owner and isinstance(x.owner.op, HostFromGpu)):
@@ -1657,8 +1658,9 @@ def local_gpu_downsample_factor_max(node):
 def local_gpu_downsample_factor_max_grad(node):
     if (isinstance(node.op, downsample.DownsampleFactorMaxGrad) and
         node.op.ds == node.op.st):
-        assert node.op.__props__ == ('ds', 'ignore_border', 'st', 'padding')
-        if node.op.padding != (0, 0):
+        assert node.op.__props__ == ('ds', 'ignore_border', 'st', 'padding',
+                                     'mode')
+        if node.op.padding != (0, 0) or node.op.mode != 'max':
             return
         x, z, gz = node.inputs
         if (x.owner and isinstance(x.owner.op, HostFromGpu)):
@@ -1673,6 +1675,8 @@ def local_gpu_downsample_factor_max_grad(node):
 @local_optimizer([downsample.DownsampleFactorMaxGradGrad])
 def local_gpu_downsample_factor_max_grad_grad(node):
     if isinstance(node.op, downsample.DownsampleFactorMaxGradGrad):
+        assert node.op.__props__ == ('ds', 'ignore_border', 'st')
+
         x, z, gx = node.inputs
         if (x.owner and isinstance(x.owner.op, HostFromGpu)):
             op = GpuDownsampleFactorMaxGradGrad(node.op.ds,

theano/sandbox/cuda/tests/test_dnn.py

@@ -90,6 +90,10 @@ def test_pooling():
     x = T.ftensor4()
     for func, pad in product((T.max, T.mean),
                              ((0, 0), (1, 0), (1, 0), (2, 3), (3, 2))):
+        if func is T.max:
+            mode = 'max'
+        else:
+            mode = 'average'
         if pad != (0, 0) and cuda.dnn.version() == -1:
             continue
 
@@ -100,7 +104,6 @@ def test_pooling():
             for stride in (2, 3):
                 if stride > ws:
                     continue
-                if func is T.max:
                 if pad[0] > stride or pad[1] > stride:
                     # Not implemented
                     continue
@@ -108,21 +111,16 @@ def test_pooling():
                 out1 = max_pool_2d(x, (ws, ws),
                                    st=(stride, stride),
                                    ignore_border=True,
-                                       padding=pad)
-                else:
-                    out1 = cuda.dnn.dnn_pool(
-                        x, ws=(ws, ws),
-                        stride=(stride, stride),
-                        pad=pad,
-                        mode='max' if func is T.max else "average")
+                                   padding=pad, mode=mode)
                 out2 = pool_2d_i2n(x, ds=(ws, ws), strides=(stride, stride),
                                    pad=pad,
                                    pool_function=func)
-
+                mode_without_gpu2 = mode_without_gpu.including()
+                mode_without_gpu2.check_isfinite = False
                 f1 = theano.function([x], out1, mode=mode_with_gpu)
                 assert any([isinstance(node.op, cuda.dnn.GpuDnnPool)
                             for node in f1.maker.fgraph.apply_nodes])
-                f2 = theano.function([x], out2, mode=mode_without_gpu)
+                f2 = theano.function([x], out2, mode=mode_without_gpu2)
                 assert not any([isinstance(node.op, cuda.dnn.GpuDnnPool)
                                 for node in f2.maker.fgraph.apply_nodes])
                 for shp in [(1, 10, 100, 100),
@@ -150,7 +148,7 @@ def test_pooling():
             # This test the CPU grad + opt + GPU implemtentation
             def fn(x):
                 return max_pool_2d(x, (ws, ws), ignore_border=True,
-                                   padding=pad)
+                                   padding=pad, mode=mode)
             theano.tests.unittest_tools.verify_grad(fn, [data],
                                                     cast_to_output_type=False,
                                                     mode=mode_with_gpu)
@@ -179,11 +177,11 @@ def test_pooling():
                         for node in fg.maker.fgraph.toposort()])
             g_out = fg(data)
 
-            if func is T.max:
+            if True:
                 # Compare again the CPU result
                 out = max_pool_2d(x, (ws, ws),
                                   padding=pad,
-                                  ignore_border=True)
+                                  ignore_border=True, mode=mode)
                 fc = theano.function([x], theano.grad(out.sum(), x),
                                      mode=mode_without_gpu)
                 assert any([isinstance(node.op, DownsampleFactorMaxGrad)