Compute Library
 21.11
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 #include "src/common/utils/Log.h"
36 
37 namespace arm_compute
38 {
39 CLGenerateProposalsLayer::CLGenerateProposalsLayer(std::shared_ptr<IMemoryManager> memory_manager)
40  : _memory_group(memory_manager),
41  _permute_deltas(),
42  _flatten_deltas(),
43  _permute_scores(),
44  _flatten_scores(),
45  _compute_anchors_kernel(std::make_unique<CLComputeAllAnchorsKernel>()),
46  _bounding_box_kernel(std::make_unique<CLBoundingBoxTransformKernel>()),
47  _pad_kernel(std::make_unique<CLPadLayerKernel>()),
48  _dequantize_anchors(std::make_unique<CLDequantizationLayer>()),
49  _dequantize_deltas(std::make_unique<CLDequantizationLayer>()),
50  _quantize_all_proposals(std::make_unique<CLQuantizationLayer>()),
51  _cpp_nms(memory_manager),
52  _is_nhwc(false),
53  _is_qasymm8(false),
54  _deltas_permuted(),
55  _deltas_flattened(),
56  _deltas_flattened_f32(),
57  _scores_permuted(),
58  _scores_flattened(),
59  _all_anchors(),
60  _all_anchors_f32(),
61  _all_proposals(),
62  _all_proposals_quantized(),
63  _keeps_nms_unused(),
64  _classes_nms_unused(),
65  _proposals_4_roi_values(),
66  _all_proposals_to_use(nullptr),
67  _num_valid_proposals(nullptr),
68  _scores_out(nullptr)
69 {
70 }
71 
73 
74 void CLGenerateProposalsLayer::configure(const ICLTensor *scores, const ICLTensor *deltas, const ICLTensor *anchors, ICLTensor *proposals, ICLTensor *scores_out, ICLTensor *num_valid_proposals,
76 {
77  configure(CLKernelLibrary::get().get_compile_context(), scores, deltas, anchors, proposals, scores_out, num_valid_proposals, info);
78 }
79 
80 void CLGenerateProposalsLayer::configure(const CLCompileContext &compile_context, const ICLTensor *scores, const ICLTensor *deltas, const ICLTensor *anchors, ICLTensor *proposals,
81  ICLTensor *scores_out,
82  ICLTensor *num_valid_proposals, const GenerateProposalsInfo &info)
83 {
84  ARM_COMPUTE_ERROR_ON_NULLPTR(scores, deltas, anchors, proposals, scores_out, num_valid_proposals);
85  ARM_COMPUTE_ERROR_THROW_ON(CLGenerateProposalsLayer::validate(scores->info(), deltas->info(), anchors->info(), proposals->info(), scores_out->info(), num_valid_proposals->info(), info));
86  ARM_COMPUTE_LOG_PARAMS(scores, deltas, anchors, proposals, scores_out, num_valid_proposals, info);
87 
88  _is_nhwc = scores->info()->data_layout() == DataLayout::NHWC;
89  const DataType scores_data_type = scores->info()->data_type();
90  _is_qasymm8 = scores_data_type == DataType::QASYMM8;
91  const int num_anchors = scores->info()->dimension(get_data_layout_dimension_index(scores->info()->data_layout(), DataLayoutDimension::CHANNEL));
92  const int feat_width = scores->info()->dimension(get_data_layout_dimension_index(scores->info()->data_layout(), DataLayoutDimension::WIDTH));
93  const int feat_height = scores->info()->dimension(get_data_layout_dimension_index(scores->info()->data_layout(), DataLayoutDimension::HEIGHT));
94  const int total_num_anchors = num_anchors * feat_width * feat_height;
95  const int pre_nms_topN = info.pre_nms_topN();
96  const int post_nms_topN = info.post_nms_topN();
97  const size_t values_per_roi = info.values_per_roi();
98 
99  const QuantizationInfo scores_qinfo = scores->info()->quantization_info();
100  const DataType rois_data_type = (_is_qasymm8) ? DataType::QASYMM16 : scores_data_type;
101  const QuantizationInfo rois_qinfo = (_is_qasymm8) ? QuantizationInfo(0.125f, 0) : scores->info()->quantization_info();
102 
103  // Compute all the anchors
104  _memory_group.manage(&_all_anchors);
105  _compute_anchors_kernel->configure(compile_context, anchors, &_all_anchors, ComputeAnchorsInfo(feat_width, feat_height, info.spatial_scale()));
106 
107  const TensorShape flatten_shape_deltas(values_per_roi, total_num_anchors);
108  _deltas_flattened.allocator()->init(TensorInfo(flatten_shape_deltas, 1, scores_data_type, deltas->info()->quantization_info()));
109 
110  // Permute and reshape deltas
111  _memory_group.manage(&_deltas_flattened);
112  if(!_is_nhwc)
113  {
114  _memory_group.manage(&_deltas_permuted);
115  _permute_deltas.configure(compile_context, deltas, &_deltas_permuted, PermutationVector{ 2, 0, 1 });
116  _flatten_deltas.configure(compile_context, &_deltas_permuted, &_deltas_flattened);
117  _deltas_permuted.allocator()->allocate();
118  }
119  else
120  {
121  _flatten_deltas.configure(compile_context, deltas, &_deltas_flattened);
122  }
123 
124  const TensorShape flatten_shape_scores(1, total_num_anchors);
125  _scores_flattened.allocator()->init(TensorInfo(flatten_shape_scores, 1, scores_data_type, scores_qinfo));
126 
127  // Permute and reshape scores
128  _memory_group.manage(&_scores_flattened);
129  if(!_is_nhwc)
130  {
131  _memory_group.manage(&_scores_permuted);
132  _permute_scores.configure(compile_context, scores, &_scores_permuted, PermutationVector{ 2, 0, 1 });
133  _flatten_scores.configure(compile_context, &_scores_permuted, &_scores_flattened);
134  _scores_permuted.allocator()->allocate();
135  }
136  else
137  {
138  _flatten_scores.configure(compile_context, scores, &_scores_flattened);
139  }
140 
141  CLTensor *anchors_to_use = &_all_anchors;
142  CLTensor *deltas_to_use = &_deltas_flattened;
143  if(_is_qasymm8)
144  {
145  _all_anchors_f32.allocator()->init(TensorInfo(_all_anchors.info()->tensor_shape(), 1, DataType::F32));
146  _deltas_flattened_f32.allocator()->init(TensorInfo(_deltas_flattened.info()->tensor_shape(), 1, DataType::F32));
147  _memory_group.manage(&_all_anchors_f32);
148  _memory_group.manage(&_deltas_flattened_f32);
149  // Dequantize anchors to float
150  _dequantize_anchors->configure(compile_context, &_all_anchors, &_all_anchors_f32);
151  _all_anchors.allocator()->allocate();
152  anchors_to_use = &_all_anchors_f32;
153  // Dequantize deltas to float
154  _dequantize_deltas->configure(compile_context, &_deltas_flattened, &_deltas_flattened_f32);
155  _deltas_flattened.allocator()->allocate();
156  deltas_to_use = &_deltas_flattened_f32;
157  }
158  // Bounding box transform
159  _memory_group.manage(&_all_proposals);
160  BoundingBoxTransformInfo bbox_info(info.im_width(), info.im_height(), 1.f);
161  _bounding_box_kernel->configure(compile_context, anchors_to_use, &_all_proposals, deltas_to_use, bbox_info);
162  deltas_to_use->allocator()->allocate();
163  anchors_to_use->allocator()->allocate();
164 
165  _all_proposals_to_use = &_all_proposals;
166  if(_is_qasymm8)
167  {
168  _memory_group.manage(&_all_proposals_quantized);
169  // Requantize all_proposals to QASYMM16 with 0.125 scale and 0 offset
170  _all_proposals_quantized.allocator()->init(TensorInfo(_all_proposals.info()->tensor_shape(), 1, DataType::QASYMM16, QuantizationInfo(0.125f, 0)));
171  _quantize_all_proposals->configure(compile_context, &_all_proposals, &_all_proposals_quantized);
172  _all_proposals.allocator()->allocate();
173  _all_proposals_to_use = &_all_proposals_quantized;
174  }
175  // The original layer implementation first selects the best pre_nms_topN anchors (thus having a lightweight sort)
176  // that are then transformed by bbox_transform. The boxes generated are then fed into a non-sorting NMS operation.
177  // 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)
178  // and the filtering
179  const int scores_nms_size = std::min<int>(std::min<int>(post_nms_topN, pre_nms_topN), total_num_anchors);
180  const float min_size_scaled = info.min_size() * info.im_scale();
181  _memory_group.manage(&_classes_nms_unused);
182  _memory_group.manage(&_keeps_nms_unused);
183 
184  // Note that NMS needs outputs preinitialized.
185  auto_init_if_empty(*scores_out->info(), TensorShape(scores_nms_size), 1, scores_data_type, scores_qinfo);
186  auto_init_if_empty(*_proposals_4_roi_values.info(), TensorShape(values_per_roi, scores_nms_size), 1, rois_data_type, rois_qinfo);
187  auto_init_if_empty(*num_valid_proposals->info(), TensorShape(1), 1, DataType::U32);
188 
189  // Initialize temporaries (unused) outputs
190  _classes_nms_unused.allocator()->init(TensorInfo(TensorShape(scores_nms_size), 1, scores_data_type, scores_qinfo));
191  _keeps_nms_unused.allocator()->init(*scores_out->info());
192 
193  // Save the output (to map and unmap them at run)
194  _scores_out = scores_out;
195  _num_valid_proposals = num_valid_proposals;
196 
197  _memory_group.manage(&_proposals_4_roi_values);
198  _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,
199  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()));
200  _keeps_nms_unused.allocator()->allocate();
201  _classes_nms_unused.allocator()->allocate();
202  _all_proposals_to_use->allocator()->allocate();
203  _scores_flattened.allocator()->allocate();
204 
205  // Add the first column that represents the batch id. This will be all zeros, as we don't support multiple images
206  _pad_kernel->configure(compile_context, &_proposals_4_roi_values, proposals, PaddingList{ { 1, 0 } });
207  _proposals_4_roi_values.allocator()->allocate();
208 }
209 
210 Status CLGenerateProposalsLayer::validate(const ITensorInfo *scores, const ITensorInfo *deltas, const ITensorInfo *anchors, const ITensorInfo *proposals, const ITensorInfo *scores_out,
211  const ITensorInfo *num_valid_proposals, const GenerateProposalsInfo &info)
212 {
213  ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(scores, deltas, anchors, proposals, scores_out, num_valid_proposals);
218 
219  const int num_anchors = scores->dimension(get_data_layout_dimension_index(scores->data_layout(), DataLayoutDimension::CHANNEL));
220  const int feat_width = scores->dimension(get_data_layout_dimension_index(scores->data_layout(), DataLayoutDimension::WIDTH));
221  const int feat_height = scores->dimension(get_data_layout_dimension_index(scores->data_layout(), DataLayoutDimension::HEIGHT));
222  const int num_images = scores->dimension(3);
223  const int total_num_anchors = num_anchors * feat_width * feat_height;
224  const int values_per_roi = info.values_per_roi();
225 
226  const bool is_qasymm8 = scores->data_type() == DataType::QASYMM8;
227 
228  ARM_COMPUTE_RETURN_ERROR_ON(num_images > 1);
229 
230  if(is_qasymm8)
231  {
233  const UniformQuantizationInfo anchors_qinfo = anchors->quantization_info().uniform();
234  ARM_COMPUTE_RETURN_ERROR_ON(anchors_qinfo.scale != 0.125f);
235  }
236 
237  TensorInfo all_anchors_info(anchors->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
238  ARM_COMPUTE_RETURN_ON_ERROR(CLComputeAllAnchorsKernel::validate(anchors, &all_anchors_info, ComputeAnchorsInfo(feat_width, feat_height, info.spatial_scale())));
239 
240  TensorInfo deltas_permuted_info = deltas->clone()->set_tensor_shape(TensorShape(values_per_roi * num_anchors, feat_width, feat_height)).set_is_resizable(true);
241  TensorInfo scores_permuted_info = scores->clone()->set_tensor_shape(TensorShape(num_anchors, feat_width, feat_height)).set_is_resizable(true);
242  if(scores->data_layout() == DataLayout::NHWC)
243  {
244  ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(deltas, &deltas_permuted_info);
245  ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(scores, &scores_permuted_info);
246  }
247  else
248  {
249  ARM_COMPUTE_RETURN_ON_ERROR(CLPermute::validate(deltas, &deltas_permuted_info, PermutationVector{ 2, 0, 1 }));
250  ARM_COMPUTE_RETURN_ON_ERROR(CLPermute::validate(scores, &scores_permuted_info, PermutationVector{ 2, 0, 1 }));
251  }
252 
253  TensorInfo deltas_flattened_info(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
254  ARM_COMPUTE_RETURN_ON_ERROR(CLReshapeLayer::validate(&deltas_permuted_info, &deltas_flattened_info));
255 
256  TensorInfo scores_flattened_info(scores->clone()->set_tensor_shape(TensorShape(1, total_num_anchors)).set_is_resizable(true));
257  TensorInfo proposals_4_roi_values(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
258 
259  ARM_COMPUTE_RETURN_ON_ERROR(CLReshapeLayer::validate(&scores_permuted_info, &scores_flattened_info));
260 
261  TensorInfo *proposals_4_roi_values_to_use = &proposals_4_roi_values;
262  TensorInfo proposals_4_roi_values_quantized(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
263  proposals_4_roi_values_quantized.set_data_type(DataType::QASYMM16).set_quantization_info(QuantizationInfo(0.125f, 0));
264  if(is_qasymm8)
265  {
266  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));
267  ARM_COMPUTE_RETURN_ON_ERROR(CLDequantizationLayer::validate(&all_anchors_info, &all_anchors_f32_info));
268 
269  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));
270  ARM_COMPUTE_RETURN_ON_ERROR(CLDequantizationLayer::validate(&deltas_flattened_info, &deltas_flattened_f32_info));
271 
272  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));
273  ARM_COMPUTE_RETURN_ON_ERROR(CLBoundingBoxTransformKernel::validate(&all_anchors_f32_info, &proposals_4_roi_values_f32, &deltas_flattened_f32_info,
274  BoundingBoxTransformInfo(info.im_width(), info.im_height(), 1.f)));
275 
276  ARM_COMPUTE_RETURN_ON_ERROR(CLQuantizationLayer::validate(&proposals_4_roi_values_f32, &proposals_4_roi_values_quantized));
277  proposals_4_roi_values_to_use = &proposals_4_roi_values_quantized;
278  }
279  else
280  {
281  ARM_COMPUTE_RETURN_ON_ERROR(CLBoundingBoxTransformKernel::validate(&all_anchors_info, &proposals_4_roi_values, &deltas_flattened_info,
282  BoundingBoxTransformInfo(info.im_width(), info.im_height(), 1.f)));
283  }
284 
285  ARM_COMPUTE_RETURN_ON_ERROR(CLPadLayerKernel::validate(proposals_4_roi_values_to_use, proposals, PaddingList{ { 1, 0 } }));
286 
287  if(num_valid_proposals->total_size() > 0)
288  {
289  ARM_COMPUTE_RETURN_ERROR_ON(num_valid_proposals->num_dimensions() > 1);
290  ARM_COMPUTE_RETURN_ERROR_ON(num_valid_proposals->dimension(0) > 1);
292  }
293 
294  if(proposals->total_size() > 0)
295  {
297  ARM_COMPUTE_RETURN_ERROR_ON(proposals->dimension(0) != size_t(values_per_roi) + 1);
298  ARM_COMPUTE_RETURN_ERROR_ON(proposals->dimension(1) != size_t(total_num_anchors));
299  if(is_qasymm8)
300  {
302  const UniformQuantizationInfo proposals_qinfo = proposals->quantization_info().uniform();
303  ARM_COMPUTE_RETURN_ERROR_ON(proposals_qinfo.scale != 0.125f);
304  ARM_COMPUTE_RETURN_ERROR_ON(proposals_qinfo.offset != 0);
305  }
306  else
307  {
309  }
310  }
311 
312  if(scores_out->total_size() > 0)
313  {
314  ARM_COMPUTE_RETURN_ERROR_ON(scores_out->num_dimensions() > 1);
315  ARM_COMPUTE_RETURN_ERROR_ON(scores_out->dimension(0) != size_t(total_num_anchors));
317  }
318 
319  return Status{};
320 }
321 
322 void CLGenerateProposalsLayer::run_cpp_nms_kernel()
323 {
324  // Map inputs
325  _scores_flattened.map(true);
326  _all_proposals_to_use->map(true);
327 
328  // Map outputs
329  _scores_out->map(CLScheduler::get().queue(), true);
330  _proposals_4_roi_values.map(CLScheduler::get().queue(), true);
331  _num_valid_proposals->map(CLScheduler::get().queue(), true);
332  _keeps_nms_unused.map(true);
333  _classes_nms_unused.map(true);
334 
335  // Run nms
336  _cpp_nms.run();
337 
338  // Unmap outputs
339  _keeps_nms_unused.unmap();
340  _classes_nms_unused.unmap();
341  _scores_out->unmap(CLScheduler::get().queue());
342  _proposals_4_roi_values.unmap(CLScheduler::get().queue());
343  _num_valid_proposals->unmap(CLScheduler::get().queue());
344 
345  // Unmap inputs
346  _scores_flattened.unmap();
347  _all_proposals_to_use->unmap();
348 }
349 
351 {
352  // Acquire all the temporaries
353  MemoryGroupResourceScope scope_mg(_memory_group);
354 
355  // Compute all the anchors
356  CLScheduler::get().enqueue(*_compute_anchors_kernel, false);
357 
358  // Transpose and reshape the inputs
359  if(!_is_nhwc)
360  {
361  _permute_deltas.run();
362  _permute_scores.run();
363  }
364  _flatten_deltas.run();
365  _flatten_scores.run();
366 
367  if(_is_qasymm8)
368  {
369  _dequantize_anchors->run();
370  _dequantize_deltas->run();
371  }
372 
373  // Build the boxes
374  CLScheduler::get().enqueue(*_bounding_box_kernel, false);
375 
376  if(_is_qasymm8)
377  {
378  _quantize_all_proposals->run();
379  }
380 
381  // Non maxima suppression
382  run_cpp_nms_kernel();
383  // Add dummy batch indexes
384  CLScheduler::get().enqueue(*_pad_kernel, true);
385 }
386 } // 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:1311
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:440
static CLScheduler & get()
Access the scheduler singleton.
BoxWithNonMaximaSuppressionLimit Information class.
Definition: Types.h:560
#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:287
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:73
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:1442
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
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
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:541
ComputeAnchors information class.
Definition: Types.h:1392
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_LOG_PARAMS(...)
#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:51
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:68
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:79
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