replace numpy.all/any to all/any, faster.

theano/sandbox/cuda/opt.py

@@ -185,10 +185,10 @@ def local_gpu_elemwise_0(node):
     """
     if (isinstance(node.op, tensor.Elemwise) and
         dtype_in_elemwise_supported(node.op)):
-        if numpy.any([i.owner and
+        if any([i.owner and
                 isinstance(i.owner.op, HostFromGpu)
                 for i in node.inputs]):
-            if numpy.all([o.type.dtype == 'float32' for o in node.outputs]):
+            if all([o.type.dtype == 'float32' for o in node.outputs]):
                 # Don't set any inplace pattern.
                 # gpu_inplace_elemwise_optimizer will do it later
 
@@ -205,13 +205,13 @@ def local_gpu_elemwise_0(node):
                 upcastable = set(['float32', 'int8', 'int16', 'uint8',
                                   'uint16'])
                 # case 1 - all inputs are already float32
-                if numpy.all([i.type.dtype == 'float32' for i in node.inputs]):
+                if all([i.type.dtype == 'float32' for i in node.inputs]):
                     #TODO: change this when fusion makes Elemwise with multiple
                     # outputs
                     gpu_elemwise = new_op(*(gpu_from_host(i)
                                             for i in node.inputs))
                 # case 2 - it is still ok if some inputs were upcast to float32
-                elif numpy.all([i.type.dtype in upcastable
+                elif all([i.type.dtype in upcastable
                           for i in node.inputs]):
                     # second - establish that a new node with upcasted inputs
                     # has the same outputs types as the original node
@@ -361,7 +361,7 @@ def local_gpu_dot_to_dot22(node):
     if node.op == tensor.basic.dot:
         if node.outputs[0].type.dtype != 'float32':
             return False
-        if numpy.any([i.owner and isinstance(i.owner.op, HostFromGpu)
+        if any([i.owner and isinstance(i.owner.op, HostFromGpu)
                 for i in node.inputs]):
             x, y = node.inputs
             if _is_real_vector(x) and _is_real_matrix(y):
@@ -395,8 +395,8 @@ def local_gpu_lazy_ifelse(node):
         gpu_ifelse = theano.ifelse.IfElse(node.op.n_outs, gpu=True)
         outs_clients = reduce(list.__add__,
                               [out.clients for out in node.outputs])
-        if numpy.any([(i.owner and isinstance(i.owner.op, HostFromGpu))
-                      for i in node.inputs]) or numpy.any(
+        if any([(i.owner and isinstance(i.owner.op, HostFromGpu))
+                for i in node.inputs]) or any(
                     [c != 'output' and c.op == gpu_from_host for c, idx
                      in outs_clients]):
 
@@ -456,7 +456,7 @@ def local_gpu_dot22(node):
             x, y = host_input.owner.inputs
             return [gpu_dot22(gpu_from_host(x), gpu_from_host(y))]
     if isinstance(node.op, tensor.blas.Dot22):
-        if numpy.any([(i.owner and isinstance(i.owner.op, HostFromGpu))
+        if any([(i.owner and isinstance(i.owner.op, HostFromGpu))
                 for i in node.inputs]):
             x, y = node.inputs
             return [host_from_gpu(gpu_dot22(gpu_from_host(x),
@@ -481,7 +481,7 @@ def local_gpu_dot22scalar(node):
             return [gpu_dot22scalar(gpu_from_host(x), gpu_from_host(y),
                                     tensor.blas._as_scalar(scalar))]
     if isinstance(node.op, tensor.blas.Dot22Scalar):
-        if numpy.any([i.owner and isinstance(i.owner.op, HostFromGpu)
+        if any([i.owner and isinstance(i.owner.op, HostFromGpu)
                 for i in node.inputs]):
             x, y, scalar = node.inputs
             return [host_from_gpu(
@@ -1195,7 +1195,7 @@ def local_gpu_join(node):
         #print "OPT: matches =", matches
 
         # if all input tensors are host_from_gpu'ified
-        if numpy.all(matches):
+        if all(matches):
             # the extra gpu_from_host introduced here will
             # be removed by further optimizations
             new_tensors = [gpu_from_host(t) for t in axis_and_tensors[1:]]
@@ -1437,7 +1437,7 @@ def local_gpu_eye(node):
             host_input.owner.op.dtype == "float32"):
             return [gpu_eye(*host_input.owner.inputs)]
     if isinstance(node.op, tensor.Eye) and node.op.dtype == "float32":
-        if numpy.any([(i.owner and isinstance(i.owner.op, HostFromGpu))
+        if any([(i.owner and isinstance(i.owner.op, HostFromGpu))
                 for i in node.inputs]):
             return [host_from_gpu(gpu_eye(*node.inputs))]
     return False
@@ -1606,7 +1606,7 @@ def gpuScanOptimization(node):
     #scan(host_from_gpu) -> host_from_gpu(GPUscan)
     if (type(node.op) == scan_op.Scan
         and not node.op.info['gpu']):
-        if numpy.any([(i.owner and isinstance(i.owner.op, HostFromGpu))
+        if any([(i.owner and isinstance(i.owner.op, HostFromGpu))
                 for i in node.inputs]):
 
             thescan = node.op