Compute Library
 21.08
CLGenerateProposalsLayer.cpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2019-2021 Arm Limited.
3  *
4  * SPDX-License-Identifier: MIT
5  *
6  * Permission is hereby granted, free of charge, to any person obtaining a copy
7  * of this software and associated documentation files (the "Software"), to
8  * deal in the Software without restriction, including without limitation the
9  * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
10  * sell copies of the Software, and to permit persons to whom the Software is
11  * furnished to do so, subject to the following conditions:
12  *
13  * The above copyright notice and this permission notice shall be included in all
14  * copies or substantial portions of the Software.
15  *
16  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19  * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20  * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22  * SOFTWARE.
23  */
25 
27 #include "arm_compute/core/Types.h"
34 
35 namespace arm_compute
36 {
37 CLGenerateProposalsLayer::CLGenerateProposalsLayer(std::shared_ptr<IMemoryManager> memory_manager)
38  : _memory_group(memory_manager),
39  _permute_deltas(),
40  _flatten_deltas(),
41  _permute_scores(),
42  _flatten_scores(),
43  _compute_anchors_kernel(std::make_unique<CLComputeAllAnchorsKernel>()),
44  _bounding_box_kernel(std::make_unique<CLBoundingBoxTransformKernel>()),
45  _pad_kernel(std::make_unique<CLPadLayerKernel>()),
46  _dequantize_anchors(std::make_unique<CLDequantizationLayer>()),
47  _dequantize_deltas(std::make_unique<CLDequantizationLayer>()),
48  _quantize_all_proposals(std::make_unique<CLQuantizationLayer>()),
49  _cpp_nms(memory_manager),
50  _is_nhwc(false),
51  _is_qasymm8(false),
52  _deltas_permuted(),
53  _deltas_flattened(),
54  _deltas_flattened_f32(),
55  _scores_permuted(),
56  _scores_flattened(),
57  _all_anchors(),
58  _all_anchors_f32(),
59  _all_proposals(),
60  _all_proposals_quantized(),
61  _keeps_nms_unused(),
62  _classes_nms_unused(),
63  _proposals_4_roi_values(),
64  _all_proposals_to_use(nullptr),
65  _num_valid_proposals(nullptr),
66  _scores_out(nullptr)
67 {
68 }
69 
71 
72 void CLGenerateProposalsLayer::configure(const ICLTensor *scores, const ICLTensor *deltas, const ICLTensor *anchors, ICLTensor *proposals, ICLTensor *scores_out, ICLTensor *num_valid_proposals,
74 {
75  configure(CLKernelLibrary::get().get_compile_context(), scores, deltas, anchors, proposals, scores_out, num_valid_proposals, info);
76 }
77 
78 void CLGenerateProposalsLayer::configure(const CLCompileContext &compile_context, const ICLTensor *scores, const ICLTensor *deltas, const ICLTensor *anchors, ICLTensor *proposals,
79  ICLTensor *scores_out,
80  ICLTensor *num_valid_proposals, const GenerateProposalsInfo &info)
81 {
82  ARM_COMPUTE_ERROR_ON_NULLPTR(scores, deltas, anchors, proposals, scores_out, num_valid_proposals);
83  ARM_COMPUTE_ERROR_THROW_ON(CLGenerateProposalsLayer::validate(scores->info(), deltas->info(), anchors->info(), proposals->info(), scores_out->info(), num_valid_proposals->info(), info));
84 
85  _is_nhwc = scores->info()->data_layout() == DataLayout::NHWC;
86  const DataType scores_data_type = scores->info()->data_type();
87  _is_qasymm8 = scores_data_type == DataType::QASYMM8;
88  const int num_anchors = scores->info()->dimension(get_data_layout_dimension_index(scores->info()->data_layout(), DataLayoutDimension::CHANNEL));
89  const int feat_width = scores->info()->dimension(get_data_layout_dimension_index(scores->info()->data_layout(), DataLayoutDimension::WIDTH));
90  const int feat_height = scores->info()->dimension(get_data_layout_dimension_index(scores->info()->data_layout(), DataLayoutDimension::HEIGHT));
91  const int total_num_anchors = num_anchors * feat_width * feat_height;
92  const int pre_nms_topN = info.pre_nms_topN();
93  const int post_nms_topN = info.post_nms_topN();
94  const size_t values_per_roi = info.values_per_roi();
95 
96  const QuantizationInfo scores_qinfo = scores->info()->quantization_info();
97  const DataType rois_data_type = (_is_qasymm8) ? DataType::QASYMM16 : scores_data_type;
98  const QuantizationInfo rois_qinfo = (_is_qasymm8) ? QuantizationInfo(0.125f, 0) : scores->info()->quantization_info();
99 
100  // Compute all the anchors
101  _memory_group.manage(&_all_anchors);
102  _compute_anchors_kernel->configure(compile_context, anchors, &_all_anchors, ComputeAnchorsInfo(feat_width, feat_height, info.spatial_scale()));
103 
104  const TensorShape flatten_shape_deltas(values_per_roi, total_num_anchors);
105  _deltas_flattened.allocator()->init(TensorInfo(flatten_shape_deltas, 1, scores_data_type, deltas->info()->quantization_info()));
106 
107  // Permute and reshape deltas
108  _memory_group.manage(&_deltas_flattened);
109  if(!_is_nhwc)
110  {
111  _memory_group.manage(&_deltas_permuted);
112  _permute_deltas.configure(compile_context, deltas, &_deltas_permuted, PermutationVector{ 2, 0, 1 });
113  _flatten_deltas.configure(compile_context, &_deltas_permuted, &_deltas_flattened);
114  _deltas_permuted.allocator()->allocate();
115  }
116  else
117  {
118  _flatten_deltas.configure(compile_context, deltas, &_deltas_flattened);
119  }
120 
121  const TensorShape flatten_shape_scores(1, total_num_anchors);
122  _scores_flattened.allocator()->init(TensorInfo(flatten_shape_scores, 1, scores_data_type, scores_qinfo));
123 
124  // Permute and reshape scores
125  _memory_group.manage(&_scores_flattened);
126  if(!_is_nhwc)
127  {
128  _memory_group.manage(&_scores_permuted);
129  _permute_scores.configure(compile_context, scores, &_scores_permuted, PermutationVector{ 2, 0, 1 });
130  _flatten_scores.configure(compile_context, &_scores_permuted, &_scores_flattened);
131  _scores_permuted.allocator()->allocate();
132  }
133  else
134  {
135  _flatten_scores.configure(compile_context, scores, &_scores_flattened);
136  }
137 
138  CLTensor *anchors_to_use = &_all_anchors;
139  CLTensor *deltas_to_use = &_deltas_flattened;
140  if(_is_qasymm8)
141  {
142  _all_anchors_f32.allocator()->init(TensorInfo(_all_anchors.info()->tensor_shape(), 1, DataType::F32));
143  _deltas_flattened_f32.allocator()->init(TensorInfo(_deltas_flattened.info()->tensor_shape(), 1, DataType::F32));
144  _memory_group.manage(&_all_anchors_f32);
145  _memory_group.manage(&_deltas_flattened_f32);
146  // Dequantize anchors to float
147  _dequantize_anchors->configure(compile_context, &_all_anchors, &_all_anchors_f32);
148  _all_anchors.allocator()->allocate();
149  anchors_to_use = &_all_anchors_f32;
150  // Dequantize deltas to float
151  _dequantize_deltas->configure(compile_context, &_deltas_flattened, &_deltas_flattened_f32);
152  _deltas_flattened.allocator()->allocate();
153  deltas_to_use = &_deltas_flattened_f32;
154  }
155  // Bounding box transform
156  _memory_group.manage(&_all_proposals);
157  BoundingBoxTransformInfo bbox_info(info.im_width(), info.im_height(), 1.f);
158  _bounding_box_kernel->configure(compile_context, anchors_to_use, &_all_proposals, deltas_to_use, bbox_info);
159  deltas_to_use->allocator()->allocate();
160  anchors_to_use->allocator()->allocate();
161 
162  _all_proposals_to_use = &_all_proposals;
163  if(_is_qasymm8)
164  {
165  _memory_group.manage(&_all_proposals_quantized);
166  // Requantize all_proposals to QASYMM16 with 0.125 scale and 0 offset
167  _all_proposals_quantized.allocator()->init(TensorInfo(_all_proposals.info()->tensor_shape(), 1, DataType::QASYMM16, QuantizationInfo(0.125f, 0)));
168  _quantize_all_proposals->configure(compile_context, &_all_proposals, &_all_proposals_quantized);
169  _all_proposals.allocator()->allocate();
170  _all_proposals_to_use = &_all_proposals_quantized;
171  }
172  // The original layer implementation first selects the best pre_nms_topN anchors (thus having a lightweight sort)
173  // that are then transformed by bbox_transform. The boxes generated are then fed into a non-sorting NMS operation.
174  // Since we are reusing the NMS layer and we don't implement any CL/sort, we let NMS do the sorting (of all the input)
175  // and the filtering
176  const int scores_nms_size = std::min<int>(std::min<int>(post_nms_topN, pre_nms_topN), total_num_anchors);
177  const float min_size_scaled = info.min_size() * info.im_scale();
178  _memory_group.manage(&_classes_nms_unused);
179  _memory_group.manage(&_keeps_nms_unused);
180 
181  // Note that NMS needs outputs preinitialized.
182  auto_init_if_empty(*scores_out->info(), TensorShape(scores_nms_size), 1, scores_data_type, scores_qinfo);
183  auto_init_if_empty(*_proposals_4_roi_values.info(), TensorShape(values_per_roi, scores_nms_size), 1, rois_data_type, rois_qinfo);
184  auto_init_if_empty(*num_valid_proposals->info(), TensorShape(1), 1, DataType::U32);
185 
186  // Initialize temporaries (unused) outputs
187  _classes_nms_unused.allocator()->init(TensorInfo(TensorShape(scores_nms_size), 1, scores_data_type, scores_qinfo));
188  _keeps_nms_unused.allocator()->init(*scores_out->info());
189 
190  // Save the output (to map and unmap them at run)
191  _scores_out = scores_out;
192  _num_valid_proposals = num_valid_proposals;
193 
194  _memory_group.manage(&_proposals_4_roi_values);
195  _cpp_nms.configure(&_scores_flattened, _all_proposals_to_use, nullptr, scores_out, &_proposals_4_roi_values, &_classes_nms_unused, nullptr, &_keeps_nms_unused, num_valid_proposals,
196  BoxNMSLimitInfo(0.0f, info.nms_thres(), scores_nms_size, false, NMSType::LINEAR, 0.5f, 0.001f, true, min_size_scaled, info.im_width(), info.im_height()));
197  _keeps_nms_unused.allocator()->allocate();
198  _classes_nms_unused.allocator()->allocate();
199  _all_proposals_to_use->allocator()->allocate();
200  _scores_flattened.allocator()->allocate();
201 
202  // Add the first column that represents the batch id. This will be all zeros, as we don't support multiple images
203  _pad_kernel->configure(compile_context, &_proposals_4_roi_values, proposals, PaddingList{ { 1, 0 } });
204  _proposals_4_roi_values.allocator()->allocate();
205 }
206 
207 Status CLGenerateProposalsLayer::validate(const ITensorInfo *scores, const ITensorInfo *deltas, const ITensorInfo *anchors, const ITensorInfo *proposals, const ITensorInfo *scores_out,
208  const ITensorInfo *num_valid_proposals, const GenerateProposalsInfo &info)
209 {
210  ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(scores, deltas, anchors, proposals, scores_out, num_valid_proposals);
215 
216  const int num_anchors = scores->dimension(get_data_layout_dimension_index(scores->data_layout(), DataLayoutDimension::CHANNEL));
217  const int feat_width = scores->dimension(get_data_layout_dimension_index(scores->data_layout(), DataLayoutDimension::WIDTH));
218  const int feat_height = scores->dimension(get_data_layout_dimension_index(scores->data_layout(), DataLayoutDimension::HEIGHT));
219  const int num_images = scores->dimension(3);
220  const int total_num_anchors = num_anchors * feat_width * feat_height;
221  const int values_per_roi = info.values_per_roi();
222 
223  const bool is_qasymm8 = scores->data_type() == DataType::QASYMM8;
224 
225  ARM_COMPUTE_RETURN_ERROR_ON(num_images > 1);
226 
227  if(is_qasymm8)
228  {
230  const UniformQuantizationInfo anchors_qinfo = anchors->quantization_info().uniform();
231  ARM_COMPUTE_RETURN_ERROR_ON(anchors_qinfo.scale != 0.125f);
232  }
233 
234  TensorInfo all_anchors_info(anchors->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
235  ARM_COMPUTE_RETURN_ON_ERROR(CLComputeAllAnchorsKernel::validate(anchors, &all_anchors_info, ComputeAnchorsInfo(feat_width, feat_height, info.spatial_scale())));
236 
237  TensorInfo deltas_permuted_info = deltas->clone()->set_tensor_shape(TensorShape(values_per_roi * num_anchors, feat_width, feat_height)).set_is_resizable(true);
238  TensorInfo scores_permuted_info = scores->clone()->set_tensor_shape(TensorShape(num_anchors, feat_width, feat_height)).set_is_resizable(true);
239  if(scores->data_layout() == DataLayout::NHWC)
240  {
241  ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(deltas, &deltas_permuted_info);
242  ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(scores, &scores_permuted_info);
243  }
244  else
245  {
246  ARM_COMPUTE_RETURN_ON_ERROR(CLPermute::validate(deltas, &deltas_permuted_info, PermutationVector{ 2, 0, 1 }));
247  ARM_COMPUTE_RETURN_ON_ERROR(CLPermute::validate(scores, &scores_permuted_info, PermutationVector{ 2, 0, 1 }));
248  }
249 
250  TensorInfo deltas_flattened_info(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
251  ARM_COMPUTE_RETURN_ON_ERROR(CLReshapeLayer::validate(&deltas_permuted_info, &deltas_flattened_info));
252 
253  TensorInfo scores_flattened_info(scores->clone()->set_tensor_shape(TensorShape(1, total_num_anchors)).set_is_resizable(true));
254  TensorInfo proposals_4_roi_values(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
255 
256  ARM_COMPUTE_RETURN_ON_ERROR(CLReshapeLayer::validate(&scores_permuted_info, &scores_flattened_info));
257 
258  TensorInfo *proposals_4_roi_values_to_use = &proposals_4_roi_values;
259  TensorInfo proposals_4_roi_values_quantized(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
260  proposals_4_roi_values_quantized.set_data_type(DataType::QASYMM16).set_quantization_info(QuantizationInfo(0.125f, 0));
261  if(is_qasymm8)
262  {
263  TensorInfo all_anchors_f32_info(anchors->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true).set_data_type(DataType::F32));
264  ARM_COMPUTE_RETURN_ON_ERROR(CLDequantizationLayer::validate(&all_anchors_info, &all_anchors_f32_info));
265 
266  TensorInfo deltas_flattened_f32_info(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true).set_data_type(DataType::F32));
267  ARM_COMPUTE_RETURN_ON_ERROR(CLDequantizationLayer::validate(&deltas_flattened_info, &deltas_flattened_f32_info));
268 
269  TensorInfo proposals_4_roi_values_f32(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true).set_data_type(DataType::F32));
270  ARM_COMPUTE_RETURN_ON_ERROR(CLBoundingBoxTransformKernel::validate(&all_anchors_f32_info, &proposals_4_roi_values_f32, &deltas_flattened_f32_info,
271  BoundingBoxTransformInfo(info.im_width(), info.im_height(), 1.f)));
272 
273  ARM_COMPUTE_RETURN_ON_ERROR(CLQuantizationLayer::validate(&proposals_4_roi_values_f32, &proposals_4_roi_values_quantized));
274  proposals_4_roi_values_to_use = &proposals_4_roi_values_quantized;
275  }
276  else
277  {
278  ARM_COMPUTE_RETURN_ON_ERROR(CLBoundingBoxTransformKernel::validate(&all_anchors_info, &proposals_4_roi_values, &deltas_flattened_info,
279  BoundingBoxTransformInfo(info.im_width(), info.im_height(), 1.f)));
280  }
281 
282  ARM_COMPUTE_RETURN_ON_ERROR(CLPadLayerKernel::validate(proposals_4_roi_values_to_use, proposals, PaddingList{ { 1, 0 } }));
283 
284  if(num_valid_proposals->total_size() > 0)
285  {
286  ARM_COMPUTE_RETURN_ERROR_ON(num_valid_proposals->num_dimensions() > 1);
287  ARM_COMPUTE_RETURN_ERROR_ON(num_valid_proposals->dimension(0) > 1);
289  }
290 
291  if(proposals->total_size() > 0)
292  {
294  ARM_COMPUTE_RETURN_ERROR_ON(proposals->dimension(0) != size_t(values_per_roi) + 1);
295  ARM_COMPUTE_RETURN_ERROR_ON(proposals->dimension(1) != size_t(total_num_anchors));
296  if(is_qasymm8)
297  {
299  const UniformQuantizationInfo proposals_qinfo = proposals->quantization_info().uniform();
300  ARM_COMPUTE_RETURN_ERROR_ON(proposals_qinfo.scale != 0.125f);
301  ARM_COMPUTE_RETURN_ERROR_ON(proposals_qinfo.offset != 0);
302  }
303  else
304  {
306  }
307  }
308 
309  if(scores_out->total_size() > 0)
310  {
311  ARM_COMPUTE_RETURN_ERROR_ON(scores_out->num_dimensions() > 1);
312  ARM_COMPUTE_RETURN_ERROR_ON(scores_out->dimension(0) != size_t(total_num_anchors));
314  }
315 
316  return Status{};
317 }
318 
319 void CLGenerateProposalsLayer::run_cpp_nms_kernel()
320 {
321  // Map inputs
322  _scores_flattened.map(true);
323  _all_proposals_to_use->map(true);
324 
325  // Map outputs
326  _scores_out->map(CLScheduler::get().queue(), true);
327  _proposals_4_roi_values.map(CLScheduler::get().queue(), true);
328  _num_valid_proposals->map(CLScheduler::get().queue(), true);
329  _keeps_nms_unused.map(true);
330  _classes_nms_unused.map(true);
331 
332  // Run nms
333  _cpp_nms.run();
334 
335  // Unmap outputs
336  _keeps_nms_unused.unmap();
337  _classes_nms_unused.unmap();
338  _scores_out->unmap(CLScheduler::get().queue());
339  _proposals_4_roi_values.unmap(CLScheduler::get().queue());
340  _num_valid_proposals->unmap(CLScheduler::get().queue());
341 
342  // Unmap inputs
343  _scores_flattened.unmap();
344  _all_proposals_to_use->unmap();
345 }
346 
348 {
349  // Acquire all the temporaries
350  MemoryGroupResourceScope scope_mg(_memory_group);
351 
352  // Compute all the anchors
353  CLScheduler::get().enqueue(*_compute_anchors_kernel, false);
354 
355  // Transpose and reshape the inputs
356  if(!_is_nhwc)
357  {
358  _permute_deltas.run();
359  _permute_scores.run();
360  }
361  _flatten_deltas.run();
362  _flatten_scores.run();
363 
364  if(_is_qasymm8)
365  {
366  _dequantize_anchors->run();
367  _dequantize_deltas->run();
368  }
369 
370  // Build the boxes
371  CLScheduler::get().enqueue(*_bounding_box_kernel, false);
372 
373  if(_is_qasymm8)
374  {
375  _quantize_all_proposals->run();
376  }
377 
378  // Non maxima suppression
379  run_cpp_nms_kernel();
380  // Add dummy batch indexes
381  CLScheduler::get().enqueue(*_pad_kernel, true);
382 }
383 } // namespace arm_compute
void configure(const ICLTensor *scores, const ICLTensor *deltas, const ICLTensor *anchors, ICLTensor *proposals, ICLTensor *scores_out, ICLTensor *num_valid_proposals, const GenerateProposalsInfo &info)
Set the input and output tensors.
virtual size_t num_dimensions() const =0
The number of dimensions of the tensor (rank)
static Status validate(const ITensorInfo *input, const ITensorInfo *output, const PaddingList &padding, PixelValue constant_value=PixelValue(), PaddingMode mode=PaddingMode::CONSTANT)
Static function to check if given info will lead to a valid configuration of CLPadLayerKernel.
static Status validate(const ITensorInfo *input, const ITensorInfo *output)
Static function to check if given info will lead to a valid configuration of CLReshapeLayer.
static Status validate(const ITensorInfo *input, const ITensorInfo *output)
Static function to check if given info will lead to a valid configuration of CLDequantizationLayer.
Generate Proposals Information class.
Definition: Types.h:1277
void map(cl::CommandQueue &q, bool blocking=true)
Enqueue a map operation of the allocated buffer on the given queue.
Definition: ICLTensor.cpp:35
Shape of a tensor.
Definition: TensorShape.h:39
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_LAYOUT_NOT_IN(t,...)
Definition: Validate.h:742
quantized, symmetric fixed-point 16-bit number
TensorInfo * info() const override
Interface to be implemented by the child class to return the tensor&#39;s metadata.
Definition: CLTensor.cpp:41
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_LAYOUT(...)
Definition: Validate.h:490
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
std::vector< PaddingInfo > PaddingList
List of padding information.
Definition: Types.h:431
static CLScheduler & get()
Access the scheduler singleton.
BoxWithNonMaximaSuppressionLimit Information class.
Definition: Types.h:551
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
Definition: Error.h:204
virtual DataType data_type() const =0
Data type used for each element of the tensor.
void run() override
Run the kernels contained in the function.
void run() override
Run the kernels contained in the function.
1 channel, 1 F32 per channel
ITensorInfo & set_data_type(DataType data_type) override
Set the data type to the specified value.
Definition: TensorInfo.cpp:286
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
Store the tensor&#39;s metadata.
Definition: ITensorInfo.h:40
CLTensorAllocator * allocator()
Return a pointer to the tensor&#39;s allocator.
Definition: CLTensor.cpp:61
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Definition: Error.h:455
Quantization info when assuming per layer quantization.
quantized, asymmetric fixed-point 16-bit number
Status class.
Definition: Error.h:52
Basic function to run opencl::ClDequantize that dequantizes an input tensor.
#define ARM_COMPUTE_RETURN_ERROR_ON(cond)
If the condition is true, an error is returned.
Definition: Error.h:296
void init(const TensorInfo &input, size_t alignment=0)
Initialize a tensor based on the passed TensorInfo.
Copyright (c) 2017-2021 Arm Limited.
void run() override
Run the kernels contained in the function.
Definition: CLPermute.cpp:70
1 channel, 1 F16 per channel
void run() override
Run the kernels contained in the function.
void map(bool blocking=true)
Enqueue a map operation of the allocated buffer.
Definition: CLTensor.cpp:66
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
Definition: Validate.h:159
void manage(IMemoryManageable *obj) override
Sets a object to be managed by the given memory group.
Definition: MemoryGroup.h:79
Quantization information.
static Status validate(const ITensorInfo *anchors, const ITensorInfo *all_anchors, const ComputeAnchorsInfo &info)
Static function to check if given info will lead to a valid configuration of CLComputeAllAnchorsKerne...
1 channel, 1 U32 per channel
quantized, asymmetric fixed-point 8-bit number unsigned
Interface for the PadLayer function.
void unmap(cl::CommandQueue &q)
Enqueue an unmap operation of the allocated and mapped buffer on the given queue. ...
Definition: ICLTensor.cpp:40
UniformQuantizationInfo uniform() const
Return per layer quantization info.
bool auto_init_if_empty(ITensorInfo &info, const TensorShape &shape, int num_channels, DataType data_type, QuantizationInfo quantization_info=QuantizationInfo())
Auto initialize the tensor info (shape, number of channels and data type) if the current assignment i...
virtual std::unique_ptr< T > clone() const =0
Provide a clone of the current object of class T.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor&#39;s metadata.
virtual ITensorInfo & set_quantization_info(const QuantizationInfo &quantization_info)=0
Set the quantization settings (scale and offset) of the tensor.
Bounding Box Transform information class.
Definition: Types.h:1408
virtual QuantizationInfo quantization_info() const =0
Get the quantization settings (scale and offset) of the tensor.
Interface for the bounding box kernel.
void enqueue(ICLKernel &kernel, bool flush=true)
Schedule the execution of the passed kernel if possible.
Num samples, channels, height, width.
CLCompileContext class.
static Status validate(const ITensorInfo *boxes, const ITensorInfo *pred_boxes, const ITensorInfo *deltas, const BoundingBoxTransformInfo &info)
Static function to check if given info will lead to a valid configuration of CLBoundingBoxTransform.
Strides of an item in bytes.
Definition: Strides.h:37
static Status validate(const ITensorInfo *scores, const ITensorInfo *deltas, const ITensorInfo *anchors, const ITensorInfo *proposals, const ITensorInfo *scores_out, const ITensorInfo *num_valid_proposals, const GenerateProposalsInfo &info)
Static function to check if given info will lead to a valid configuration of CLGenerateProposalsLayer...
void allocate() override
Allocate size specified by TensorInfo of OpenCL memory.
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
Memory group resources scope handling class.
Definition: IMemoryGroup.h:82
Interface for OpenCL tensor.
Definition: ICLTensor.h:42
virtual size_t total_size() const =0
Returns the total size of the tensor in bytes.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(...)
Definition: Validate.h:439
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:541
ComputeAnchors information class.
Definition: Types.h:1358
Num samples, height, width, channels.
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Definition: Validate.h:788
CLGenerateProposalsLayer(std::shared_ptr< IMemoryManager > memory_manager=nullptr)
Default constructor.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:157
Store the tensor&#39;s metadata.
Definition: TensorInfo.h:43
void configure(const ICLTensor *input, ICLTensor *output, const PermutationVector &perm)
Set the input and output tensors.
Definition: CLPermute.cpp:49
void configure(const ICLTensor *input, ICLTensor *output)
Initialise the kernel&#39;s inputs and outputs.
static Status validate(const ITensorInfo *input, const ITensorInfo *output, const PermutationVector &perm)
Static function to check if given info will lead to a valid configuration of CLPermute.
Definition: CLPermute.cpp:65
size_t get_data_layout_dimension_index(const DataLayout data_layout, const DataLayoutDimension data_layout_dimension)
Get the index of the given dimension.
Definition: Helpers.inl:193
Basic function to simulate a quantization layer.
const TensorShape & tensor_shape() const override
Size for each dimension of the tensor.
Definition: TensorInfo.h:234
DataType
Available data types.
Definition: Types.h:77
Interface for Compute All Anchors kernel.
void unmap()
Enqueue an unmap operation of the allocated and mapped buffer.
Definition: CLTensor.cpp:71
static Status validate(const ITensorInfo *input, const ITensorInfo *output)
Static function to check if given info will lead to a valid configuration of CLQuantizationLayer.
~CLGenerateProposalsLayer()
Default destructor.
virtual DataLayout data_layout() const =0
Get the data layout of the tensor.
void configure(const ITensor *scores_in, const ITensor *boxes_in, const ITensor *batch_splits_in, ITensor *scores_out, ITensor *boxes_out, ITensor *classes, ITensor *batch_splits_out=nullptr, ITensor *keeps=nullptr, ITensor *keeps_size=nullptr, const BoxNMSLimitInfo info=BoxNMSLimitInfo())
Configure the BoxWithNonMaximaSuppressionLimit CPP kernel.
Basic implementation of the OpenCL tensor interface.
Definition: CLTensor.h:41