Compute Library
 20.02.1
CLGenerateProposalsLayer.cpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2019 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"
29 
30 namespace arm_compute
31 {
32 CLGenerateProposalsLayer::CLGenerateProposalsLayer(std::shared_ptr<IMemoryManager> memory_manager)
33  : _memory_group(memory_manager),
34  _permute_deltas_kernel(),
35  _flatten_deltas_kernel(),
36  _permute_scores_kernel(),
37  _flatten_scores_kernel(),
38  _compute_anchors_kernel(),
39  _bounding_box_kernel(),
40  _pad_kernel(),
41  _dequantize_anchors(),
42  _dequantize_deltas(),
43  _quantize_all_proposals(),
44  _cpp_nms(memory_manager),
45  _is_nhwc(false),
46  _is_qasymm8(false),
47  _deltas_permuted(),
48  _deltas_flattened(),
49  _deltas_flattened_f32(),
50  _scores_permuted(),
51  _scores_flattened(),
52  _all_anchors(),
53  _all_anchors_f32(),
54  _all_proposals(),
55  _all_proposals_quantized(),
56  _keeps_nms_unused(),
57  _classes_nms_unused(),
58  _proposals_4_roi_values(),
59  _all_proposals_to_use(nullptr),
60  _num_valid_proposals(nullptr),
61  _scores_out(nullptr)
62 {
63 }
64 
65 void CLGenerateProposalsLayer::configure(const ICLTensor *scores, const ICLTensor *deltas, const ICLTensor *anchors, ICLTensor *proposals, ICLTensor *scores_out, ICLTensor *num_valid_proposals,
67 {
68  ARM_COMPUTE_ERROR_ON_NULLPTR(scores, deltas, anchors, proposals, scores_out, num_valid_proposals);
69  ARM_COMPUTE_ERROR_THROW_ON(CLGenerateProposalsLayer::validate(scores->info(), deltas->info(), anchors->info(), proposals->info(), scores_out->info(), num_valid_proposals->info(), info));
70 
71  _is_nhwc = scores->info()->data_layout() == DataLayout::NHWC;
72  const DataType scores_data_type = scores->info()->data_type();
73  _is_qasymm8 = scores_data_type == DataType::QASYMM8;
74  const int num_anchors = scores->info()->dimension(get_data_layout_dimension_index(scores->info()->data_layout(), DataLayoutDimension::CHANNEL));
75  const int feat_width = scores->info()->dimension(get_data_layout_dimension_index(scores->info()->data_layout(), DataLayoutDimension::WIDTH));
76  const int feat_height = scores->info()->dimension(get_data_layout_dimension_index(scores->info()->data_layout(), DataLayoutDimension::HEIGHT));
77  const int total_num_anchors = num_anchors * feat_width * feat_height;
78  const int pre_nms_topN = info.pre_nms_topN();
79  const int post_nms_topN = info.post_nms_topN();
80  const size_t values_per_roi = info.values_per_roi();
81 
82  const QuantizationInfo scores_qinfo = scores->info()->quantization_info();
83  const DataType rois_data_type = (_is_qasymm8) ? DataType::QASYMM16 : scores_data_type;
84  const QuantizationInfo rois_qinfo = (_is_qasymm8) ? QuantizationInfo(0.125f, 0) : scores->info()->quantization_info();
85 
86  // Compute all the anchors
87  _memory_group.manage(&_all_anchors);
88  _compute_anchors_kernel.configure(anchors, &_all_anchors, ComputeAnchorsInfo(feat_width, feat_height, info.spatial_scale()));
89 
90  const TensorShape flatten_shape_deltas(values_per_roi, total_num_anchors);
91  _deltas_flattened.allocator()->init(TensorInfo(flatten_shape_deltas, 1, scores_data_type, deltas->info()->quantization_info()));
92 
93  // Permute and reshape deltas
94  _memory_group.manage(&_deltas_flattened);
95  if(!_is_nhwc)
96  {
97  _memory_group.manage(&_deltas_permuted);
98  _permute_deltas_kernel.configure(deltas, &_deltas_permuted, PermutationVector{ 2, 0, 1 });
99  _flatten_deltas_kernel.configure(&_deltas_permuted, &_deltas_flattened);
100  _deltas_permuted.allocator()->allocate();
101  }
102  else
103  {
104  _flatten_deltas_kernel.configure(deltas, &_deltas_flattened);
105  }
106 
107  const TensorShape flatten_shape_scores(1, total_num_anchors);
108  _scores_flattened.allocator()->init(TensorInfo(flatten_shape_scores, 1, scores_data_type, scores_qinfo));
109 
110  // Permute and reshape scores
111  _memory_group.manage(&_scores_flattened);
112  if(!_is_nhwc)
113  {
114  _memory_group.manage(&_scores_permuted);
115  _permute_scores_kernel.configure(scores, &_scores_permuted, PermutationVector{ 2, 0, 1 });
116  _flatten_scores_kernel.configure(&_scores_permuted, &_scores_flattened);
117  _scores_permuted.allocator()->allocate();
118  }
119  else
120  {
121  _flatten_scores_kernel.configure(scores, &_scores_flattened);
122  }
123 
124  CLTensor *anchors_to_use = &_all_anchors;
125  CLTensor *deltas_to_use = &_deltas_flattened;
126  if(_is_qasymm8)
127  {
128  _all_anchors_f32.allocator()->init(TensorInfo(_all_anchors.info()->tensor_shape(), 1, DataType::F32));
129  _deltas_flattened_f32.allocator()->init(TensorInfo(_deltas_flattened.info()->tensor_shape(), 1, DataType::F32));
130  _memory_group.manage(&_all_anchors_f32);
131  _memory_group.manage(&_deltas_flattened_f32);
132  // Dequantize anchors to float
133  _dequantize_anchors.configure(&_all_anchors, &_all_anchors_f32);
134  _all_anchors.allocator()->allocate();
135  anchors_to_use = &_all_anchors_f32;
136  // Dequantize deltas to float
137  _dequantize_deltas.configure(&_deltas_flattened, &_deltas_flattened_f32);
138  _deltas_flattened.allocator()->allocate();
139  deltas_to_use = &_deltas_flattened_f32;
140  }
141  // Bounding box transform
142  _memory_group.manage(&_all_proposals);
143  BoundingBoxTransformInfo bbox_info(info.im_width(), info.im_height(), 1.f);
144  _bounding_box_kernel.configure(anchors_to_use, &_all_proposals, deltas_to_use, bbox_info);
145  deltas_to_use->allocator()->allocate();
146  anchors_to_use->allocator()->allocate();
147 
148  _all_proposals_to_use = &_all_proposals;
149  if(_is_qasymm8)
150  {
151  _memory_group.manage(&_all_proposals_quantized);
152  // Requantize all_proposals to QASYMM16 with 0.125 scale and 0 offset
153  _all_proposals_quantized.allocator()->init(TensorInfo(_all_proposals.info()->tensor_shape(), 1, DataType::QASYMM16, QuantizationInfo(0.125f, 0)));
154  _quantize_all_proposals.configure(&_all_proposals, &_all_proposals_quantized);
155  _all_proposals.allocator()->allocate();
156  _all_proposals_to_use = &_all_proposals_quantized;
157  }
158  // The original layer implementation first selects the best pre_nms_topN anchors (thus having a lightweight sort)
159  // that are then transformed by bbox_transform. The boxes generated are then fed into a non-sorting NMS operation.
160  // 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)
161  // and the filtering
162  const int scores_nms_size = std::min<int>(std::min<int>(post_nms_topN, pre_nms_topN), total_num_anchors);
163  const float min_size_scaled = info.min_size() * info.im_scale();
164  _memory_group.manage(&_classes_nms_unused);
165  _memory_group.manage(&_keeps_nms_unused);
166 
167  // Note that NMS needs outputs preinitialized.
168  auto_init_if_empty(*scores_out->info(), TensorShape(scores_nms_size), 1, scores_data_type, scores_qinfo);
169  auto_init_if_empty(*_proposals_4_roi_values.info(), TensorShape(values_per_roi, scores_nms_size), 1, rois_data_type, rois_qinfo);
170  auto_init_if_empty(*num_valid_proposals->info(), TensorShape(1), 1, DataType::U32);
171 
172  // Initialize temporaries (unused) outputs
173  _classes_nms_unused.allocator()->init(TensorInfo(TensorShape(scores_nms_size), 1, scores_data_type, scores_qinfo));
174  _keeps_nms_unused.allocator()->init(*scores_out->info());
175 
176  // Save the output (to map and unmap them at run)
177  _scores_out = scores_out;
178  _num_valid_proposals = num_valid_proposals;
179 
180  _memory_group.manage(&_proposals_4_roi_values);
181  _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,
182  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()));
183  _keeps_nms_unused.allocator()->allocate();
184  _classes_nms_unused.allocator()->allocate();
185  _all_proposals_to_use->allocator()->allocate();
186  _scores_flattened.allocator()->allocate();
187 
188  // Add the first column that represents the batch id. This will be all zeros, as we don't support multiple images
189  _pad_kernel.configure(&_proposals_4_roi_values, proposals, PaddingList{ { 1, 0 } });
190  _proposals_4_roi_values.allocator()->allocate();
191 }
192 
193 Status CLGenerateProposalsLayer::validate(const ITensorInfo *scores, const ITensorInfo *deltas, const ITensorInfo *anchors, const ITensorInfo *proposals, const ITensorInfo *scores_out,
194  const ITensorInfo *num_valid_proposals, const GenerateProposalsInfo &info)
195 {
196  ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(scores, deltas, anchors, proposals, scores_out, num_valid_proposals);
201 
202  const int num_anchors = scores->dimension(get_data_layout_dimension_index(scores->data_layout(), DataLayoutDimension::CHANNEL));
203  const int feat_width = scores->dimension(get_data_layout_dimension_index(scores->data_layout(), DataLayoutDimension::WIDTH));
204  const int feat_height = scores->dimension(get_data_layout_dimension_index(scores->data_layout(), DataLayoutDimension::HEIGHT));
205  const int num_images = scores->dimension(3);
206  const int total_num_anchors = num_anchors * feat_width * feat_height;
207  const int values_per_roi = info.values_per_roi();
208 
209  const bool is_qasymm8 = scores->data_type() == DataType::QASYMM8;
210 
211  ARM_COMPUTE_RETURN_ERROR_ON(num_images > 1);
212 
213  if(is_qasymm8)
214  {
216  const UniformQuantizationInfo anchors_qinfo = anchors->quantization_info().uniform();
217  ARM_COMPUTE_RETURN_ERROR_ON(anchors_qinfo.scale != 0.125f);
218  }
219 
220  TensorInfo all_anchors_info(anchors->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
221  ARM_COMPUTE_RETURN_ON_ERROR(CLComputeAllAnchorsKernel::validate(anchors, &all_anchors_info, ComputeAnchorsInfo(feat_width, feat_height, info.spatial_scale())));
222 
223  TensorInfo deltas_permuted_info = deltas->clone()->set_tensor_shape(TensorShape(values_per_roi * num_anchors, feat_width, feat_height)).set_is_resizable(true);
224  TensorInfo scores_permuted_info = scores->clone()->set_tensor_shape(TensorShape(num_anchors, feat_width, feat_height)).set_is_resizable(true);
225  if(scores->data_layout() == DataLayout::NHWC)
226  {
227  ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(deltas, &deltas_permuted_info);
228  ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(scores, &scores_permuted_info);
229  }
230  else
231  {
232  ARM_COMPUTE_RETURN_ON_ERROR(CLPermuteKernel::validate(deltas, &deltas_permuted_info, PermutationVector{ 2, 0, 1 }));
233  ARM_COMPUTE_RETURN_ON_ERROR(CLPermuteKernel::validate(scores, &scores_permuted_info, PermutationVector{ 2, 0, 1 }));
234  }
235 
236  TensorInfo deltas_flattened_info(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
237  ARM_COMPUTE_RETURN_ON_ERROR(CLReshapeLayerKernel::validate(&deltas_permuted_info, &deltas_flattened_info));
238 
239  TensorInfo scores_flattened_info(scores->clone()->set_tensor_shape(TensorShape(1, total_num_anchors)).set_is_resizable(true));
240  TensorInfo proposals_4_roi_values(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
241 
242  ARM_COMPUTE_RETURN_ON_ERROR(CLReshapeLayerKernel::validate(&scores_permuted_info, &scores_flattened_info));
243 
244  TensorInfo *proposals_4_roi_values_to_use = &proposals_4_roi_values;
245  TensorInfo proposals_4_roi_values_quantized(deltas->clone()->set_tensor_shape(TensorShape(values_per_roi, total_num_anchors)).set_is_resizable(true));
246  proposals_4_roi_values_quantized.set_data_type(DataType::QASYMM16).set_quantization_info(QuantizationInfo(0.125f, 0));
247  if(is_qasymm8)
248  {
249  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));
250  ARM_COMPUTE_RETURN_ON_ERROR(CLDequantizationLayerKernel::validate(&all_anchors_info, &all_anchors_f32_info));
251 
252  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));
253  ARM_COMPUTE_RETURN_ON_ERROR(CLDequantizationLayerKernel::validate(&deltas_flattened_info, &deltas_flattened_f32_info));
254 
255  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));
256  ARM_COMPUTE_RETURN_ON_ERROR(CLBoundingBoxTransformKernel::validate(&all_anchors_f32_info, &proposals_4_roi_values_f32, &deltas_flattened_f32_info,
257  BoundingBoxTransformInfo(info.im_width(), info.im_height(), 1.f)));
258 
259  ARM_COMPUTE_RETURN_ON_ERROR(CLQuantizationLayerKernel::validate(&proposals_4_roi_values_f32, &proposals_4_roi_values_quantized));
260  proposals_4_roi_values_to_use = &proposals_4_roi_values_quantized;
261  }
262  else
263  {
264  ARM_COMPUTE_RETURN_ON_ERROR(CLBoundingBoxTransformKernel::validate(&all_anchors_info, &proposals_4_roi_values, &deltas_flattened_info,
265  BoundingBoxTransformInfo(info.im_width(), info.im_height(), 1.f)));
266  }
267 
268  ARM_COMPUTE_RETURN_ON_ERROR(CLPadLayerKernel::validate(proposals_4_roi_values_to_use, proposals, PaddingList{ { 1, 0 } }));
269 
270  if(num_valid_proposals->total_size() > 0)
271  {
272  ARM_COMPUTE_RETURN_ERROR_ON(num_valid_proposals->num_dimensions() > 1);
273  ARM_COMPUTE_RETURN_ERROR_ON(num_valid_proposals->dimension(0) > 1);
275  }
276 
277  if(proposals->total_size() > 0)
278  {
280  ARM_COMPUTE_RETURN_ERROR_ON(proposals->dimension(0) != size_t(values_per_roi) + 1);
281  ARM_COMPUTE_RETURN_ERROR_ON(proposals->dimension(1) != size_t(total_num_anchors));
282  if(is_qasymm8)
283  {
285  const UniformQuantizationInfo proposals_qinfo = proposals->quantization_info().uniform();
286  ARM_COMPUTE_RETURN_ERROR_ON(proposals_qinfo.scale != 0.125f);
287  ARM_COMPUTE_RETURN_ERROR_ON(proposals_qinfo.offset != 0);
288  }
289  else
290  {
292  }
293  }
294 
295  if(scores_out->total_size() > 0)
296  {
297  ARM_COMPUTE_RETURN_ERROR_ON(scores_out->num_dimensions() > 1);
298  ARM_COMPUTE_RETURN_ERROR_ON(scores_out->dimension(0) != size_t(total_num_anchors));
300  }
301 
302  return Status{};
303 }
304 
305 void CLGenerateProposalsLayer::run_cpp_nms_kernel()
306 {
307  // Map inputs
308  _scores_flattened.map(true);
309  _all_proposals_to_use->map(true);
310 
311  // Map outputs
312  _scores_out->map(CLScheduler::get().queue(), true);
313  _proposals_4_roi_values.map(CLScheduler::get().queue(), true);
314  _num_valid_proposals->map(CLScheduler::get().queue(), true);
315  _keeps_nms_unused.map(true);
316  _classes_nms_unused.map(true);
317 
318  // Run nms
319  _cpp_nms.run();
320 
321  // Unmap outputs
322  _keeps_nms_unused.unmap();
323  _classes_nms_unused.unmap();
324  _scores_out->unmap(CLScheduler::get().queue());
325  _proposals_4_roi_values.unmap(CLScheduler::get().queue());
326  _num_valid_proposals->unmap(CLScheduler::get().queue());
327 
328  // Unmap inputs
329  _scores_flattened.unmap();
330  _all_proposals_to_use->unmap();
331 }
332 
334 {
335  // Acquire all the temporaries
336  MemoryGroupResourceScope scope_mg(_memory_group);
337 
338  // Compute all the anchors
339  CLScheduler::get().enqueue(_compute_anchors_kernel, false);
340 
341  // Transpose and reshape the inputs
342  if(!_is_nhwc)
343  {
344  CLScheduler::get().enqueue(_permute_deltas_kernel, false);
345  CLScheduler::get().enqueue(_permute_scores_kernel, false);
346  }
347  CLScheduler::get().enqueue(_flatten_deltas_kernel, false);
348  CLScheduler::get().enqueue(_flatten_scores_kernel, false);
349 
350  if(_is_qasymm8)
351  {
352  CLScheduler::get().enqueue(_dequantize_anchors, false);
353  CLScheduler::get().enqueue(_dequantize_deltas, false);
354  }
355 
356  // Build the boxes
357  CLScheduler::get().enqueue(_bounding_box_kernel, false);
358 
359  if(_is_qasymm8)
360  {
361  CLScheduler::get().enqueue(_quantize_all_proposals, false);
362  }
363 
364  // Non maxima suppression
365  run_cpp_nms_kernel();
366  // Add dummy batch indexes
367  CLScheduler::get().enqueue(_pad_kernel, true);
368 }
369 } // 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.
void configure(const ICLTensor *anchors, ICLTensor *all_anchors, const ComputeAnchorsInfo &info)
Set the input and output tensors.
Generate Proposals Information class.
Definition: Types.h:1417
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
quantized, symmetric fixed-point 16-bit number
TensorInfo * info() const override
Interface to be implemented by the child class to return the tensor's metadata.
Definition: CLTensor.cpp:41
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:455
static CLScheduler & get()
Access the scheduler singleton.
Definition: CLScheduler.cpp:99
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_LAYOUT(...)
Definition: Validate.h:494
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Definition: Validate.h:545
BoxWithNonMaximaSuppressionLimit Information class.
Definition: Types.h:590
#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.
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Definition: Validate.h:792
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:319
Store the tensor's metadata.
Definition: ITensorInfo.h:40
CLTensorAllocator * allocator()
Return a pointer to the tensor'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
#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.
static Status validate(const ITensorInfo *input, const ITensorInfo *output)
Static function to check if given info will lead to a valid configuration of CLQuantizationLayerKerne...
Copyright (c) 2017-2020 ARM Limited.
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...
Definition: Helpers.inl:202
1 channel, 1 F16 per channel
void map(bool blocking=true)
Enqueue a map operation of the allocated buffer.
Definition: CLTensor.cpp:66
void configure(const ICLTensor *input, ICLTensor *output)
Set the input, output.
void manage(IMemoryManageable *obj) override
Sets a object to be managed by the given memory group.
Definition: MemoryGroup.h:79
void configure(const ICLTensor *boxes, ICLTensor *pred_boxes, const ICLTensor *deltas, const BoundingBoxTransformInfo &info)
Set the input and output tensors.
static Status validate(const ITensorInfo *input, const ITensorInfo *output)
Static function to check if given info will lead to a valid configuration of CLDequantizationLayerKer...
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
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(...)
Definition: Validate.h:443
quantized, asymmetric fixed-point 8-bit number unsigned
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.
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's metadata.
virtual ITensorInfo & set_quantization_info(const QuantizationInfo &quantization_info)=0
Set the quantization settings (scale and offset) of the tensor.
static Status validate(const ITensorInfo *input, const ITensorInfo *output)
Static function to check if given info will lead to a valid configuration of CLReshapeLayerKernel.
Bounding Box Transform information class.
Definition: Types.h:1548
virtual QuantizationInfo quantization_info() const =0
Get the quantization settings (scale and offset) of the tensor.
void configure(const ICLTensor *input, ICLTensor *output, const PaddingList &padding, PixelValue constant_value=PixelValue(), PaddingMode mode=PaddingMode::CONSTANT)
Set the input and output tensor.
void enqueue(ICLKernel &kernel, bool flush=true)
Schedule the execution of the passed kernel if possible.
Num samples, channels, height, width.
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
void configure(const ICLTensor *input, ICLTensor *output)
Set the input and output of the kernel.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
Definition: Validate.h:163
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.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Definition: Validate.h:161
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.
void configure(const ICLTensor *input, ICLTensor *output)
Set the input, output, min and max.
ComputeAnchors information class.
Definition: Types.h:1498
Num samples, height, width, channels.
void configure(const ICLTensor *input, ICLTensor *output, const PermutationVector &perm)
Set the input and output of the kernel.
CLGenerateProposalsLayer(std::shared_ptr< IMemoryManager > memory_manager=nullptr)
Default constructor.
Store the tensor's metadata.
Definition: TensorInfo.h:45
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:327
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_LAYOUT_NOT_IN(t,...)
Definition: Validate.h:746
const TensorShape & tensor_shape() const override
Size for each dimension of the tensor.
Definition: TensorInfo.h:261
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 CLPermuteKernel.
DataType
Available data types.
Definition: Types.h:75
void unmap()
Enqueue an unmap operation of the allocated and mapped buffer.
Definition: CLTensor.cpp:71
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