[BACKPORT][BUGFIX][FEATURE] Add oneDNN 1D and 3D deconvolution support and fix bias

python/mxnet/ndarray/numpy_extension/_op.py

@@ -617,9 +617,9 @@ def convolution(data=None, weight=None, bias=None, kernel=None, stride=None, dil
 @set_module('mxnet.ndarray.numpy_extension')
 def deconvolution(data=None, weight=None, bias=None, kernel=None, stride=None, dilate=None,
                   pad=None, adj=None, target_shape=None, num_filter=1, num_group=1,
-                  workspace=512, no_bias=False, cudnn_tune=None,
+                  workspace=1024, no_bias=False, cudnn_tune=None,
                   cudnn_off=False, layout=None):
-    r"""Computes 1D or 2D transposed convolution (aka fractionally strided convolution) of
+    r"""Computes 1D, 2D or 3D transposed convolution (aka fractionally strided convolution) of
     the input tensor. This operation can be seen as the gradient of Convolution operation
     with respect to its input. Convolution usually reduces the size of the input.
     Transposed convolution works the other way, going from a smaller input

python/mxnet/numpy_extension/_op.py

@@ -586,9 +586,9 @@ def convolution(data=None, weight=None, bias=None, kernel=None, stride=None, dil
 @set_module('mxnet.numpy_extension')
 def deconvolution(data=None, weight=None, bias=None, kernel=None, stride=None, dilate=None,
                   pad=None, adj=None, target_shape=None, num_filter=1, num_group=1,
-                  workspace=512, no_bias=False, cudnn_tune=None,
+                  workspace=1024, no_bias=False, cudnn_tune=None,
                   cudnn_off=False, layout=None):
-    r"""Computes 1D or 2D transposed convolution (aka fractionally strided convolution) of
+    r"""Computes 1D, 2D or 3D transposed convolution (aka fractionally strided convolution) of
     the input tensor. This operation can be seen as the gradient of Convolution operation
     with respect to its input. Convolution usually reduces the size of the input.
     Transposed convolution works the other way, going from a smaller input

src/operator/deformable_convolution-inl.h

@@ -347,7 +347,7 @@ class DeformableConvolutionOp : public Operator {
   index_t num_kernels_col2im_;
   bool bias_term_;  // has bias term?
   bool is_1x1_;
-};  // class ConvolutionOp
+};  // class DeformableConvolutionOp
 
 template <typename xpu>
 Operator* CreateOp(DeformableConvolutionParam param,

src/operator/modulated_deformable_convolution-inl.h

@@ -408,7 +408,7 @@ class ModulatedDeformableConvolutionOp : public Operator {
   index_t im2col_step_;
   bool bias_term_;  // has bias term?
   bool is_1x1_;
-};  // class ConvolutionOp
+};  // class ModulatedDeformableConvolutionOp
 
 template <typename xpu>
 Operator* CreateOp(ModulatedDeformableConvolutionParam param,

src/operator/nn/deconvolution.cc

@@ -98,12 +98,6 @@ static bool DeconvolutionShape(const nnvm::NodeAttrs& attrs,
                                mxnet::ShapeVector* in_shape,
                                mxnet::ShapeVector* out_shape) {
   const DeconvolutionParam& param_ = nnvm::get<DeconvolutionParam>(attrs.parsed);
-#if MXNET_USE_CUDNN == 0
-  if (param_.kernel.ndim() > 2) {
-    LOG(FATAL) << "If not using CUDNN, only 1D or 2D Deconvolution is supported";
-    return false;
-  }
-#endif  // CUDNN
 
   using namespace mshadow;
   if (!param_.no_bias) {
@@ -413,9 +407,9 @@ DMLC_REGISTER_PARAMETER(DeconvolutionParam);
 NNVM_REGISTER_OP(Deconvolution)
     .add_alias("_npx_deconvolution")
     .describe(
-        "Computes 1D or 2D transposed convolution (aka fractionally strided convolution) of the "
-        "input tensor. This operation can be seen as the gradient of Convolution operation with "
-        "respect to its input. Convolution usually reduces the size of the input. Transposed "
+        "Computes 1D, 2D or 3D transposed convolution (aka fractionally strided convolution) of "
+        "the input tensor. This operation can be seen as the gradient of Convolution operation "
+        "with respect to its input. Convolution usually reduces the size of the input. Transposed "
         "convolution works the other way, going from a smaller input to a larger output while "
         "preserving the connectivity pattern.")
     .set_num_inputs([](const NodeAttrs& attrs) {