diff --git a/paddle/operators/conv_op.cc b/paddle/operators/conv_op.cc index 424eccdb7dc57195d20f75460032a99c76e6adcd..d6882b275b22b9a2a2b6ff8cfb53a3462bbdbefe 100644 --- a/paddle/operators/conv_op.cc +++ b/paddle/operators/conv_op.cc @@ -70,6 +70,13 @@ void ConvOp::InferShape(framework::InferShapeContext* ctx) const { framework::OpKernelType ConvOp::GetExpectedKernelType( const framework::ExecutionContext& ctx) const { bool use_cudnn = ctx.Attr("use_cudnn"); + use_cudnn &= platform::is_gpu_place(ctx.GetPlace()); +#ifdef PADDLE_WITH_CUDA + if (platform::is_gpu_place(ctx.GetPlace())) { + auto& dev_ctx = ctx.template device_context(); + use_cudnn &= dev_ctx.cudnn_handle() != nullptr; + } +#endif framework::LibraryType library_; if (use_cudnn) { library_ = framework::LibraryType::kCUDNN; @@ -283,6 +290,14 @@ void ConvOpGrad::InferShape(framework::InferShapeContext* ctx) const { framework::OpKernelType ConvOpGrad::GetExpectedKernelType( const framework::ExecutionContext& ctx) const { bool use_cudnn = ctx.Attr("use_cudnn"); + use_cudnn &= platform::is_gpu_place(ctx.GetPlace()); +#ifdef PADDLE_WITH_CUDA + if (platform::is_gpu_place(ctx.GetPlace())) { + auto& dev_ctx = ctx.template device_context(); + use_cudnn &= dev_ctx.cudnn_handle() != nullptr; + } +#endif + framework::LibraryType library_; if (use_cudnn) { library_ = framework::LibraryType::kCUDNN; diff --git a/paddle/operators/conv_transpose_op.cc b/paddle/operators/conv_transpose_op.cc index cf4e8c0a303d6888c3b1f2475a483c4bfc90981b..a2382a7e42eb9c5c6a8f13265b0e6173e6b05f76 100644 --- a/paddle/operators/conv_transpose_op.cc +++ b/paddle/operators/conv_transpose_op.cc @@ -61,6 +61,13 @@ void ConvTransposeOp::InferShape(framework::InferShapeContext* ctx) const { framework::OpKernelType ConvTransposeOp::GetExpectedKernelType( const framework::ExecutionContext& ctx) const { bool use_cudnn = ctx.Attr("use_cudnn"); + use_cudnn &= platform::is_gpu_place(ctx.GetPlace()); +#ifdef PADDLE_WITH_CUDA + if (platform::is_gpu_place(ctx.GetPlace())) { + auto& dev_ctx = ctx.template device_context(); + use_cudnn &= dev_ctx.cudnn_handle() != nullptr; + } +#endif framework::LibraryType library_; if (use_cudnn) { library_ = framework::LibraryType::kCUDNN; @@ -263,6 +270,13 @@ void ConvTransposeOpGrad::InferShape(framework::InferShapeContext* ctx) const { framework::OpKernelType ConvTransposeOpGrad::GetExpectedKernelType( const framework::ExecutionContext& ctx) const { bool use_cudnn = ctx.Attr("use_cudnn"); + use_cudnn &= platform::is_gpu_place(ctx.GetPlace()); +#ifdef PADDLE_WITH_CUDA + if (platform::is_gpu_place(ctx.GetPlace())) { + auto& dev_ctx = ctx.template device_context(); + use_cudnn &= dev_ctx.cudnn_handle() != nullptr; + } +#endif framework::LibraryType library_; if (use_cudnn) { library_ = framework::LibraryType::kCUDNN; diff --git a/paddle/operators/pool_op.cc b/paddle/operators/pool_op.cc index 3e567efd082ed913ce3c19f87c93a2868ebe8864..b97333bb1a13a0170c325520b86ac73e68282f91 100644 --- a/paddle/operators/pool_op.cc +++ b/paddle/operators/pool_op.cc @@ -64,6 +64,13 @@ void PoolOp::InferShape(framework::InferShapeContext *ctx) const { framework::OpKernelType PoolOp::GetExpectedKernelType( const framework::ExecutionContext &ctx) const { bool use_cudnn = ctx.Attr("use_cudnn"); + use_cudnn &= platform::is_gpu_place(ctx.GetPlace()); +#ifdef PADDLE_WITH_CUDA + if (platform::is_gpu_place(ctx.GetPlace())) { + auto &dev_ctx = ctx.template device_context(); + use_cudnn &= dev_ctx.cudnn_handle() != nullptr; + } +#endif framework::LibraryType library_; if (use_cudnn) { library_ = framework::LibraryType::kCUDNN; @@ -88,6 +95,13 @@ void PoolOpGrad::InferShape(framework::InferShapeContext *ctx) const { framework::OpKernelType PoolOpGrad::GetExpectedKernelType( const framework::ExecutionContext &ctx) const { bool use_cudnn = ctx.Attr("use_cudnn"); + use_cudnn &= platform::is_gpu_place(ctx.GetPlace()); +#ifdef PADDLE_WITH_CUDA + if (platform::is_gpu_place(ctx.GetPlace())) { + auto &dev_ctx = ctx.template device_context(); + use_cudnn &= dev_ctx.cudnn_handle() != nullptr; + } +#endif framework::LibraryType library_; if (use_cudnn) { library_ = framework::LibraryType::kCUDNN; diff --git a/python/paddle/v2/fluid/layers/nn.py b/python/paddle/v2/fluid/layers/nn.py index 65e731b6a13631ad987a08e2f59cce465b37ac31..fc4c22e1526be3cbdf683c67649dd369d09114bf 100644 --- a/python/paddle/v2/fluid/layers/nn.py +++ b/python/paddle/v2/fluid/layers/nn.py @@ -676,6 +676,7 @@ def conv2d(input, groups=None, param_attr=None, bias_attr=None, + use_cudnn=True, act=None): """ **Convlution2D Layer** @@ -739,6 +740,8 @@ def conv2d(input, connected to the second half of the input channels. Default: groups=1 param_attr(ParamAttr): The parameters to the Conv2d Layer. Default: None bias_attr(ParamAttr): Bias parameter for the Conv2d layer. Default: None + use_cudnn(bool): Use cudnn kernel or not, it is valid only when the cudnn + library is installed. Default: True act(str): Activation type. Default: None Returns: @@ -774,6 +777,8 @@ def conv2d(input, stride = [stride, stride] if isinstance(padding, int): padding = [padding, padding] + if not isinstance(use_cudnn, bool): + raise ValueError("use_cudnn should be True or False") input_shape = input.shape filter_shape = [num_filters, num_filter_channels] + filter_size @@ -797,9 +802,12 @@ def conv2d(input, 'Filter': filter_param, }, outputs={"Output": pre_bias}, - attrs={'strides': stride, - 'paddings': padding, - 'groups': groups}) + attrs={ + 'strides': stride, + 'paddings': padding, + 'groups': groups, + 'use_cudnn': use_cudnn + }) pre_act = helper.append_bias_op(pre_bias, dim_start=1, dim_end=2) @@ -948,6 +956,7 @@ def pool2d(input, pool_stride=None, pool_padding=None, global_pooling=False, + use_cudnn=True, name=None): """ This function adds the operator for pooling in 2 dimensions, using the @@ -967,6 +976,8 @@ def pool2d(input, pool_stride = [pool_stride, pool_stride] if isinstance(pool_padding, int): pool_padding = [pool_padding, pool_padding] + if not isinstance(use_cudnn, bool): + raise ValueError("use_cudnn should be True or False") helper = LayerHelper('pool2d', **locals()) dtype = helper.input_dtype() @@ -981,7 +992,8 @@ def pool2d(input, "ksize": pool_size, "global_pooling": global_pooling, "strides": pool_stride, - "paddings": pool_padding + "paddings": pool_padding, + "use_cudnn": use_cudnn }) return pool_out @@ -1096,6 +1108,7 @@ def conv2d_transpose(input, stride=None, dilation=None, param_attr=None, + use_cudnn=True, name=None): """ The transpose of conv2d layer. @@ -1123,6 +1136,8 @@ def conv2d_transpose(input, contain two integers, (dilation_H, dilation_W). Otherwise, the dilation_H = dilation_W = dilation. param_attr: Parameter Attribute. + use_cudnn(bool): Use cudnn kernel or not, it is valid only when the cudnn + library is installed. Default: True name(str|None): A name for this layer(optional). If set None, the layer will be named automatically. @@ -1151,6 +1166,10 @@ def conv2d_transpose(input, elif dilation is not None: op_attr['dilations'] = dilation + if not isinstance(use_cudnn, bool): + raise ValueError("use_cudnn should be True or False") + op_attr['use_cudnn'] = use_cudnn + if filter_size is None: if output_size is None: raise ValueError("output_size must be set when filter_size is None") diff --git a/python/paddle/v2/fluid/nets.py b/python/paddle/v2/fluid/nets.py index ee6f70b89940a1daa076c5617b05e5a845078d14..c53fbd280fd79dc0d598fda2b5796886abee4ed4 100644 --- a/python/paddle/v2/fluid/nets.py +++ b/python/paddle/v2/fluid/nets.py @@ -28,19 +28,22 @@ def simple_img_conv_pool(input, pool_stride, act, param_attr=None, - pool_type='max'): + pool_type='max', + use_cudnn=True): conv_out = layers.conv2d( input=input, num_filters=num_filters, filter_size=filter_size, param_attr=param_attr, - act=act) + act=act, + use_cudnn=use_cudnn) pool_out = layers.pool2d( input=conv_out, pool_size=pool_size, pool_type=pool_type, - pool_stride=pool_stride) + pool_stride=pool_stride, + use_cudnn=use_cudnn) return pool_out @@ -54,7 +57,8 @@ def img_conv_group(input, conv_with_batchnorm=False, conv_batchnorm_drop_rate=None, pool_stride=1, - pool_type=None): + pool_type=None, + use_cudnn=True): """ Image Convolution Group, Used for vgg net. """ @@ -85,7 +89,8 @@ def img_conv_group(input, filter_size=conv_filter_size[i], padding=conv_padding[i], param_attr=param_attr[i], - act=local_conv_act) + act=local_conv_act, + use_cudnn=use_cudnn) if conv_with_batchnorm[i]: tmp = layers.batch_norm(input=tmp, act=conv_act) @@ -97,7 +102,8 @@ def img_conv_group(input, input=tmp, pool_size=pool_size, pool_type=pool_type, - pool_stride=pool_stride) + pool_stride=pool_stride, + use_cudnn=use_cudnn) return pool_out