def roipooling_infer(node: Node): """ Sets shape of output node according specified parameters input blobs and node Sets number from the first input blob, channels from the second one, height and width are specified Parameters ---------- node """ shapes = [node.in_node(i).shape for i in range(len(node.in_nodes()))] if any(s is None for s in shapes): return if len(node.in_nodes()) == 4: # TensorFlow case of CropAndResize operation crop_size = node.in_node(3).value if crop_size is None: log.error('The ROIPooling size is not known for node {}'.format( node.soft_get('name'))) return if not isinstance(crop_size, np.ndarray) or len(crop_size) != 2: log.error( 'The ROIPooling size is should have 2 elements for node {}'. format(node.soft_get('name'))) node.pooled_h = crop_size[0] node.pooled_w = crop_size[1] node.graph.remove_edge(node.in_node(3).id, node.id) node.graph.remove_edge(node.in_node(2).id, node.id) layout = node.graph.graph['layout'] assert len(layout) == 4 node.out_port(0).data.set_shape( shape_for_layout(layout, batch=shapes[1][get_batch_dim(layout, 4)], features=shapes[0][get_features_dim(layout, 4)], height=node.pooled_h, width=node.pooled_w))
def insert_pre_processing(graph: Graph, input_node: Node, node_mean_scale_values: np.array, preprocessing_name: str): assert preprocessing_name in ['scale', 'mean'] if node_mean_scale_values.get(preprocessing_name) is None: return user_value = node_mean_scale_values[preprocessing_name] value = 1 / user_value if preprocessing_name == 'scale' else user_value * (-1) optimize_value = int(preprocessing_name == 'scale') op = Mul if preprocessing_name == 'scale' else Add if all([x == optimize_value for x in value]): return assert input_node.has_valid('shape') features_dim_idx = get_features_dim(graph.graph['layout'], len(input_node.shape)) assert compatible_dims(value.size, input_node.shape[features_dim_idx]) or value.size == 1 shape = np.ones(len(input_node.shape), dtype=np.int64) shape[features_dim_idx] = value.size value = value.reshape(shape) name = input_node.soft_get('name', input_node.id) + '/' + preprocessing_name preprocessing = create_op_with_const_inputs(graph, op=op, port_value_dict={1: value}, op_attrs={'name': name}) for dst in input_node.out_port(0).get_destinations(): if dst.node.soft_get('type') != 'ShapeOf': # After the insertion of additional operations model optimizer # should keep the link to the input layer. Parameter node in framework # should map to parameter node in IR. # For this reason 'fw_tensor_debug_info' should be kept in data node. dst.get_connection().set_source(preprocessing.out_port(0), "source") input_node.out_port(0).connect(preprocessing.in_port(0))
def infer(node: Node): in_shape = node.in_port(0).data.get_shape() if in_shape.size != 4: raise Error('TensorFlow DepthToSpace operation is supported for 4D \'NHWC\' input layout only. ' 'Current input shape is \'{}\''.format(in_shape)) layout = node.graph.graph['layout'] N = in_shape[get_batch_dim(layout, 4)] H = in_shape[get_height_dim(layout, 4)] W = in_shape[get_width_dim(layout, 4)] C = in_shape[get_features_dim(layout, 4)] block_size = node['block_size'] if C is not dynamic_dimension and C % (block_size ** 2): raise Error('Feature dimensions of input tensor of DepthToSpace operation have to be divisible by square ' 'of DepthToSpace \'block_size\' parameter. Input tensor shape = {}. Feature dimension = {}. ' 'block_size = {}'.format(in_shape, C, block_size)) out_shape = shape_for_layout(layout, batch=N, features=C // (block_size * block_size), height=H * block_size, width=W * block_size) if is_fully_defined(in_shape) and is_fully_defined(out_shape) and np.prod(in_shape) != np.prod(out_shape): raise Error('Number of input elements "{}" is not equal to number of output elements "" for node "{}"' ''.format(in_shape, out_shape, node.soft_get('name', node.id))) node.out_port(0).data.set_shape(out_shape)
def replace_pattern(self, graph: Graph, match: dict): bias_add = match['BiasAdd'] # Replace BiasAdd by Add operation new_add = Add(graph, {'name': bias_add.id + '/Add'}).create_node() bias_add.in_port(0).get_connection().set_destination(new_add.in_port(0)) bias_add.in_port(1).get_connection().set_destination(new_add.in_port(1)) bias_add.out_port(0).get_connection().set_source(new_add.out_port(0)) if bias_add.data_format != 'NCHW': return input_shape = new_add.in_port(0).data.get_shape() bias_shape = new_add.in_port(1).data.get_shape() assert len(bias_shape) == 1 unsqueeze_dims = np.arange(len(input_shape)) channel_dim = get_features_dim('NCHW', len(input_shape)) unsqueeze_dims = np.delete(unsqueeze_dims, channel_dim, 0) unsqueeze_node = Unsqueeze(graph, {'name': new_add.id + '/BiasUnsqueeze'}).create_node() unsqueeze_dims_node = Const(graph, {'name': new_add.id + '/Dims', 'value': unsqueeze_dims}).create_node() # Reconnecting nodes unsqueeze_node.in_port(1).connect(unsqueeze_dims_node.out_port(0)) unsqueeze_node['override_output_shape'] = True new_add.in_port(1).get_connection().insert_node(unsqueeze_node)
def infer(node: Node): in_shape = node.in_node().shape if in_shape.size != 4: raise Error('TensorFlow SpaceToDepth operation is supported for 4D \'NHWC\' input layout only. ' 'Current input shape is \'{}\''.format(in_shape)) layout = node.graph.graph['layout'] N = in_shape[get_batch_dim(layout, 4)] H = in_shape[get_height_dim(layout, 4)] W = in_shape[get_width_dim(layout, 4)] C = in_shape[get_features_dim(layout, 4)] block_size = node['block_size'] if (H is not dynamic_dimension and H % block_size) or (W is not dynamic_dimension and W % block_size): raise Error('Spatial dimensions of input tensor of SpaceToDepth operation have to be divisible by ' 'SpaceToDepth \'block_size\' parameter. Input tensor shape = {}. Spatial dimensions = {},{}. ' 'block_size = {}'.format(in_shape, H, W, block_size)) out_shape = shape_for_layout(layout, batch=N, features=C * (block_size ** 2), height=H // block_size, width=W // block_size) node.out_port(0).data.set_shape(out_shape)
def infer(node: Node): assert [port.idx for port in node.in_ports().values() if not port.disconnected()] == [0], \ 'Wrong input nodes number for node {} with type ExtractImagePatches'.format(node.soft_get('name', node.id)) input_shape = node.in_port(0).data.get_shape() name = node.soft_get('name', node.id) assert input_shape is not None, 'Input shape is not set for node {} with type ExtractImagePatches'.format( name) assert len( input_shape ) == 4, 'ExtractImagePatches operation supports only 4D tensors' layout = node.graph.graph['layout'] N = input_shape[get_batch_dim(layout, 4)] C = input_shape[get_features_dim(layout, 4)] size_spatial = shape_array(node.sizes)[node.spatial_dims] input_spatial_shape = input_shape[node.spatial_dims] stride_spatial_shape = node.strides[node.spatial_dims] size_extent = node.rates[node.spatial_dims] * (size_spatial - 1) + 1 pad_spatial_shape, output_spatial_shape = tf_window_op_pad_infer( input_spatial_shape, size_extent, stride_spatial_shape, node.auto_pad, False) out_shape = shape_for_layout(layout, batch=N, features=C * np.prod(size_spatial), height=output_spatial_shape[0], width=output_spatial_shape[1]) node.out_port(0).data.set_shape(out_shape)
def infer(node): layout = node.graph.graph['layout'] node_name = node.soft_get('name', node.id) assert len([port for port in node.in_ports().values() if not port.disconnected()]) == 3, \ 'The node "{}" must 3 inputs'.format(node_name) assert node.has_valid('pooled_w'), '"pooled_w" attribute is not set for node "{}"'.format(node_name) assert node.has_valid('pooled_h'), '"pooled_h" attribute is not set for node "{}"'.format(node_name) assert node.has_valid('mode'), '"mode" attribute is not set for node "{}"'.format(node_name) assert node.mode in ['avg', 'max'], \ '"mode" attribute range of values is ["avg", "max"], got {} for node "{}"'.format(node.mode, node_name) input_shape = node.in_port(0).data.get_shape() rois_shape = node.in_port(1).data.get_shape() indices_shape = node.in_port(2).data.get_shape() assert input_shape is not None and rois_shape is not None and indices_shape is not None, \ 'The node "{}" input shape is None'.format(node_name) assert compatible_dims(rois_shape[0], indices_shape[0]), 'The number of batch indices does not correspond ' \ 'to number of ROIs for node "{}"'.format(node_name) assert compatible_dims(rois_shape[1], 4), 'The size of ROI element must be 4 for node "{}"'.format(node_name) assert len(input_shape) == 4, 'The rank of port 0 input tensor of node "{}" must be 4.'.format(node_name) node.out_port(0).data.set_shape( shape_for_layout(layout, batch=rois_shape[0], features=input_shape[get_features_dim(layout, 4)], height=node.pooled_h, width=node.pooled_w) )
def insert_pre_processing(graph: Graph, input_node: Node, node_mean_scale_values: np.array, preprocessing_name: str): assert preprocessing_name in ['scale', 'mean'] if node_mean_scale_values.get(preprocessing_name) is None: return user_value = node_mean_scale_values[preprocessing_name] value = 1 / user_value if preprocessing_name == 'scale' else user_value * ( -1) optimize_value = int(preprocessing_name == 'scale') op = Mul if preprocessing_name == 'scale' else Add if all([x == optimize_value for x in value]): return assert input_node.has_valid('shape') features_dim_idx = get_features_dim(graph.graph['layout'], len(input_node.shape)) assert compatible_dims( value.size, input_node.shape[features_dim_idx]) or value.size == 1 shape = np.ones(len(input_node.shape), dtype=np.int64) shape[features_dim_idx] = value.size value = value.reshape(shape) name = input_node.soft_get('name', input_node.id) + '/' + preprocessing_name preprocessing = create_op_with_const_inputs(graph, op=op, port_value_dict={1: value}, op_attrs={'name': name}) if input_node.is_out_port_connected(0) and len( input_node.out_port(0).get_destinations()) == 1: # There are models with pattern Parameter(uint8) -> Convert(float). # Adding mean/scale leads to the following: # Parameter(uint8) -> Mean/Scale -> Convert(float) which is incorrect. # To fix this mean and scale preprocessing node is inserted after Convert(float) node. out_node = input_node.out_port(0).get_destination().node convert_type = out_node.soft_get('dst_type') if out_node.soft_get('type') == "Convert" and (convert_type in [ np.float32, np.float16 ]): input_node = out_node if convert_type != value.dtype: new_value = value.astype(convert_type) const_node = preprocessing.in_port( 1).get_connection().get_source().node const_node['value'] = new_value for dst in input_node.out_port(0).get_destinations(): if dst.node.soft_get('type') != 'ShapeOf': # After the insertion of additional operations model optimizer # should keep the link to the input layer. Parameter node in framework # should map to parameter node in IR. # For this reason 'fw_tensor_debug_info' should be kept in data node. dst.get_connection().set_source(preprocessing.out_port(0), "source") input_node.out_port(0).connect(preprocessing.in_port(0))
def find_and_replace_pattern(self, graph: Graph): layout = graph.graph['layout'] for eltwise_op_node in graph.get_op_nodes(is_eltwise=True): out_shape = eltwise_op_node.out_port().data.get_shape() if 4 <= len(out_shape) <= 5: out_features = out_shape[get_features_dim(layout, len(out_shape))] for port, node in eltwise_op_node.in_nodes().items(): if len(node.shape) != len(out_shape) and len(node.shape) == 1 and out_features == node.shape[0]: new_shape = shape_for_layout(layout, batch=1, features=out_features, height=1, width=1, depth=1 if len(out_shape) == 5 else None) dim_const = Const(graph, {'value': new_shape, 'name': node.id + '/Dim'}).create_node() reshape_op = Reshape(graph, attrs={'dim': new_shape, 'name': node.id + '/Broadcast'}).create_node() eltwise_op_node.in_port(port).get_source().node.out_port(0).get_connection().set_destination(reshape_op.in_port(0)) reshape_op.in_port(1).connect(dim_const.out_port(0)) reshape_op.out_port(0).connect(eltwise_op_node.in_port(port))
def upsample_infer(node: Node): node_name = node.soft_get('name', node.id) layout = node.graph.graph['layout'] assert len( layout ) == 4, 'Input tensor rank must be equal to 4 for node "{}"'.format( node_name) input_shape = node.in_port(0).data.get_shape() if len(node.in_nodes()) == 1: in_height = input_shape[get_height_dim(layout, 4)] in_width = input_shape[get_width_dim(layout, 4)] assert node.has('width_scale') is not None and node.has( 'height_scale') is not None if in_height is not dynamic_dimension: out_height = math.floor(in_height * node.height_scale) else: out_height = dynamic_dimension if in_width is not dynamic_dimension: out_width = math.floor(in_width * node.width_scale) else: out_width = dynamic_dimension node.out_port(0).data.set_shape( shape_for_layout(layout, batch=input_shape[get_batch_dim(layout, 4)], features=input_shape[get_features_dim( layout, 4)], height=out_height, width=out_width)) else: scales = node.in_port(1).data.get_value() assert scales is not None, 'The input with scales for node "{}" is not constant'.format( node_name) eps = 1e-5 # This is to make rounding in case of very close number to round to closest instead of down # generic output shape calculation to support 5D input shape case output_shape = shape_array( [dynamic_dimension for _ in range(len(input_shape))]) for idx in range(len(output_shape)): if input_shape[idx] is not dynamic_dimension: output_shape[idx] = int( (input_shape[idx] + eps) * scales[idx]) else: output_shape[idx] = dynamic_dimension_value node.out_port(0).data.set_shape(output_shape)
def pad_op_transform(graph: Graph, match: dict): op = match['op'] pad_op = match['pad_op'] input_data = pad_op.in_node(0) if pad_op.mode != 'constant': log.info( 'The pad node "{}" with pad mode "{}" cannot be fused.'.format( pad_op.soft_get('name'), pad_op.mode)) return if op.type == 'Pooling' and op.pool_method == 'max': return if pad_op.mode == 'constant': fill_value = pad_op.in_port(3).data.get_value() if fill_value is None or fill_value != 0.0: log.info( 'The pad node "{}" with non-zero fill value cannot be fused.'. format(pad_op.soft_get('name'))) return input_tensor_dims = len(match['pad_output'].shape) for in_port in [1, 2]: pads = pad_op.in_port(in_port).data.get_value() if pads[get_features_dim(op.graph.graph['layout'], input_tensor_dims)] != 0 or \ pads[get_batch_dim(op.graph.graph['layout'], input_tensor_dims)] != 0: log.info( 'The pad node "{}" with padding over feature/batch dimension cannot be fused.' .format(pad_op.soft_get('name'))) return op.pad += np.concatenate([ pad_op.in_port(1).data.get_value().reshape([-1, 1]), pad_op.in_port(2).data.get_value().reshape([-1, 1]) ], axis=1) op.pad_spatial_shape = op.pad[op.spatial_dims] op['auto_pad'] = None if op.type == 'Pooling': op['exclude_pad'] = False assert (graph[match['pad_output'].node][match['op'].node][0]['in'] == 0) edge_attrs = graph.get_edge_data(match['pad_output'].id, match['op'].id)[0] graph.remove_edge(match['pad_output'].id, match['op'].id) graph.add_edge(input_data.id, match['op'].id, **{'in': 0, **edge_attrs})
def get_channel_index(node: Node) -> int: guessed_layout = 'NCHW' if node.has_valid('rt_info'): rt_info = node.rt_info if rt_info.contains('old_api_map_order'): old_api_map_version = rt_info.get_attribute_version( 'old_api_map_order') old_api_map = rt_info.info['old_api_map_order', old_api_map_version] if 'inverse_order' in old_api_map.info: order = old_api_map.info['inverse_order'] assert len(order) == len(guessed_layout) guessed_layout = np.array(list(guessed_layout))[order] guessed_layout = ''.join(guessed_layout) idx, has_layout = get_dim_from_layout(node, 'C') if has_layout: return idx else: return get_features_dim(guessed_layout, len(node.shape))
def pad_op_transform(graph: Graph, match: dict): op = match['op'] pad_op: Node = match['pad_op'] # to keep reshape-ability if Pad receives pads_begin/pads_end from shape subgraph if pad_op.in_port(1).get_source().node.soft_get('can_be_fused') is False: return if pad_op.mode != 'constant': log.info('The pad node "{}" with pad mode "{}" cannot be fused.'.format(pad_op.soft_get('name'), pad_op.mode)) return if op.type == 'Pooling' and op.pool_method == 'max': return if pad_op.mode == 'constant': fill_value = pad_op.in_port(3).data.get_value() if fill_value is None or fill_value != 0.0: log.info('The pad node "{}" with non-zero fill value cannot be fused.'.format(pad_op.soft_get('name'))) return input_tensor_dims = len(match['pad_output'].shape) for in_port in [1, 2]: pads = pad_op.in_port(in_port).data.get_value() if pads[get_features_dim(op.graph.graph['layout'], input_tensor_dims)] != 0 or \ pads[get_batch_dim(op.graph.graph['layout'], input_tensor_dims)] != 0: log.info('The pad node "{}" with padding over feature/batch dimension cannot be fused.'.format( pad_op.soft_get('name'))) return op.pad += np.concatenate([pad_op.in_port(1).data.get_value().reshape([-1, 1]), pad_op.in_port(2).data.get_value().reshape([-1, 1])], axis=1) op.pad_spatial_shape = op.pad[op.spatial_dims] op['auto_pad'] = None if op.type == 'Pooling': op['exclude_pad'] = False assert (graph[match['pad_output'].node][match['op'].node][0]['in'] == 0) match['op'].in_port(0).disconnect() pad_op.in_port(0).get_connection().add_destination(match['op'].in_port(0))
def get_suitable_channel_index(node: Node, shape): if len(shape) != 4: return None guessed_layout = 'NCHW' if node.has_valid('rt_info'): rt_info = node.rt_info if rt_info.contains('old_api_map_order'): old_api_map_version = rt_info.get_attribute_version('old_api_map_order') old_api_map = rt_info.info['old_api_map_order', old_api_map_version] if 'inverse_order' in old_api_map.info: order = old_api_map.info['inverse_order'] assert len(order) == len(guessed_layout) guessed_layout = np.array(list(guessed_layout))[order] guessed_layout = ''.join(guessed_layout) idx, has_layout = get_dim_from_layout(node, 'C') if not has_layout: idx = get_features_dim(guessed_layout, len(node.shape)) if compatible_dims(shape[idx], 3): return idx else: return None
def replace_pattern(self, graph: Graph, match: dict): y = match['maximum'].in_port(0).data.get_value() if y is None: y = match['maximum'].in_port(1).data.get_value() if y is None or y.shape != (): log.debug( 'The value of the "maximum_y_data" is not defined or is not constant' ) return # We need to check axes which performed reduction because IE supports only 2D, 3D, 4D inputs and # reduction only along spatial and channel dimensions. input_rank = len(match['sum'].in_port(0).data.get_shape()) if input_rank not in [2, 3, 4]: log.debug( 'IE supports L2 normalization only for 2D, 3D and 4D tensors.') return axes = match['sum'].in_port(1).data.get_value() axes = int64_array(axes) if axes.shape == (): axes = int64_array([axes]) axes = int64_array( [axis if axis >= 0 else axis + input_rank for axis in axes]) axes.sort() transformation_applicable = False # check for case C + all spatial dims. Works for 2D (NC), 3D (NCH) and 4D (NCHW and NHWC) if len(axes) + 1 == input_rank and np.array_equal( axes, int64_array(np.arange(start=1, stop=input_rank))): transformation_applicable = True # check for pure C channel normalization if len(axes) == 1 and ((input_rank == 4 and get_features_dim( graph.graph['layout'], input_rank) == axes[0]) or (input_rank != 4 and axes[0] == 1)): transformation_applicable = True if not transformation_applicable: log.debug( 'IE doesn\'t support l2 normalization with reduction along axes {}.' .format(axes)) return output_name = match['l2_normalize'].soft_get('name', match['l2_normalize'].id) normalize_node = create_op_node_with_second_input( graph, NormalizeL2Op, axes, { 'name': output_name, 'eps_mode': 'max', 'eps': y }) match['square'].in_port(0).get_source().connect( normalize_node.in_port(0)) match['square'].in_port(0).disconnect() if match['l2_normalize'].in_port( 0).get_source().node.id == match['rsqrt'].id: match['l2_normalize'].in_port(1).disconnect() else: match['l2_normalize'].in_port(0).disconnect() match['l2_normalize'].out_port(0).get_connection().set_source( normalize_node.out_port(0)) rename_nodes([(match['l2_normalize'], output_name + "/TBR"), (normalize_node, output_name)])
def interp_infer(node: Node): layout = node.graph.graph['layout'] assert len(layout) == 4 if len(node.in_nodes()) == 2: src_shape = node.in_node(0).shape dst_shape = node.in_node(1).shape # in Caffe can be 2 inputs too, but shape should be got from shape of the second input if node.parse_2nd_input == 'shape': dst_shape = [dst_shape[get_height_dim(layout, 4)], dst_shape[get_width_dim(layout, 4)]] else: # it is TF case dst_shape = node.in_node(1).value if src_shape is None or dst_shape is None or len(src_shape) != 4 or len(dst_shape) != 2: log.error( 'Node {} with op {} cannot be converted to Resample layer because there is no enough info about ' 'src/dst shapes: src_shape = {}, dst_shape = {}'.format(node.name, node.op, src_shape, dst_shape)) node.type = None # prevent translation to a valid IE layer return in_height = src_shape[get_height_dim(layout, 4)] in_width = src_shape[get_width_dim(layout, 4)] out_height = dst_shape[0] out_width = dst_shape[1] node.factor = factor_update( node.factor, [float(out_height) / in_height, float(out_width) / in_width], [in_height, in_width], [out_height, out_width], node.soft_get('name') ) if node.factor is None: node['width'] = out_width node['height'] = out_height node.out_node().shape = shape_for_layout(layout, batch=src_shape[get_batch_dim(layout, 4)], features=src_shape[get_features_dim(layout, 4)], height=out_height, width=out_width) node.graph.remove_edge(node.in_node(1).id, node.id) else: outn = node.out_node(0) in_shape = node.in_node(0) num_ = in_shape.shape[get_batch_dim(layout, 4)] channels_ = in_shape.shape[get_features_dim(layout, 4)] height_in_ = in_shape.shape[get_height_dim(layout, 4)] width_in_ = in_shape.shape[get_width_dim(layout, 4)] height_out_ = height_in_ + node.pad_beg + node.pad_end width_out_ = width_in_ + node.pad_beg + node.pad_end if node.shrink_factor != 1 and node.zoom_factor == 1: shrink_factor = node.shrink_factor if shrink_factor < 1: log.error('Shrink factor should be positive in node {}'.format(node.id)) return None height_out_ = (height_out_ - 1) / shrink_factor + 1 width_out_ = (width_out_ - 1) / shrink_factor + 1 elif node.shrink_factor == 1 and node.zoom_factor != 1: zoom_factor = node.zoom_factor if zoom_factor < 1: log.error('Zoom factor should be positive in node {}'.format(node.id)) return None node['debug_message'] = 'Interp layer shape inference function may be wrong, please, try to update ' \ 'layer shape inference function in the file (openvino/tools/mo/ops/interp.op at the ' \ 'line {}).'.format(inspect.currentframe().f_lineno) + refer_to_faq_msg(100) # Reshape methods can be different in some cases # Commented out section represents reshape that used in deeplab-caffe # Uncomment the following lines, if your model was trained with deeplab-caffe # or have the same reshape method # height_out_ = height_out_ + (height_out_ - 1) * (zoom_factor - 1) # width_out_ = width_out_ + (width_out_ - 1) * (zoom_factor - 1) # Comment out the following lines if you use the reshape method from previous section height_out_ = height_out_ * zoom_factor width_out_ = width_out_ * zoom_factor elif node.width != 0 and node.height != 0: height_out_ = node.height width_out_ = node.width elif node.shrink_factor != 1 and node.zoom_factor != 1: shrink_factor = node.shrink_factor zoom_factor = node.zoom_factor if shrink_factor < 1: log.error('Shrink factor should be positive in node {}'.format(node.id)) return None if zoom_factor < 1: log.error('Zoom factor should be positive in node {}'.format(node.id)) return None height_out_ = (height_out_ - 1) / shrink_factor + 1 width_out_ = (width_out_ - 1) / shrink_factor + 1 height_out_ = height_out_ + (height_out_ - 1) * (zoom_factor - 1) width_out_ = width_out_ + (width_out_ - 1) * (zoom_factor - 1) outn.shape = shape_for_layout(layout, batch=num_, features=channels_, height=height_out_, width=width_out_)
def test_get_features_dim_NCDHW(self): self.assertEqual(get_features_dim('NCHW', 5), 1)
def test_get_features_dim_NDHWC(self): self.assertEqual(get_features_dim('NHWC', 5), 4)