提交 1f516fa0 编写于 作者: X xzl

modify format, and modify the layer grad test, op test

上级 81998868
develop 2.0.1-rocm-post Ligoml-patch-1 OliverLPH-patch-1 OliverLPH-patch-2 PaddlePM-patch-1 PaddlePM-patch-2 ZHUI-patch-1 add_default_att add_model_benchmark_ci add_some_yaml_config addfile all_new_design_exec ascendrc ascendrelease cherry_undefined_var compile_windows delete_2.0.1-rocm-post delete_add_default_att delete_all_new_design_exec delete_ascendrc delete_compile_windows delete_delete_addfile delete_disable_iterable_dataset_unittest delete_fix_dataloader_memory_leak delete_fix_imperative_dygraph_error delete_fix_retry_ci delete_fix_undefined_var delete_improve_sccache delete_incubate/lite delete_paddle_tiny_install delete_paralleltest delete_prv-disable-more-cache delete_revert-31068-fix_conv3d_windows delete_revert-31562-mean delete_revert-33630-bug-fix delete_revert-34159-add_npu_bce_logical_dev delete_revert-34910-spinlocks_for_allocator delete_revert-35069-revert-34910-spinlocks_for_allocator delete_revert-36057-dev/read_flags_in_ut dingjiaweiww-patch-1 disable_iterable_dataset_unittest dy2static enable_eager_model_test final_state_gen_python_c final_state_intermediate fix-numpy-issue fix_concat_slice fix_dataloader_memory_leak fix_imperative_dygraph_error fix_npu_ci fix_op_flops fix_retry_ci fix_rnn_docs fix_tensor_type fix_undefined_var fixiscan fixiscan1 fixiscan2 fixiscan3 github/fork/123malin/netifaces github/fork/123malin/tdm_abacus github/fork/AshburnLee/dev_unique github/fork/ForFishes/fix_memory_matmul github/fork/ForFishes/rm_fluid github/fork/LielinJiang/move-2.0-api github/fork/LielinJiang/visual-dl-cb github/fork/LiuChiachi/add-transformer-generate-square-subsequent-mask-api github/fork/LiuChiachi/fix-example-code-for-hapi-Model github/fork/LiuChiachi/remove-input-requirment-in-dygraph-Model github/fork/MrChengmo/fix_ps_profiler github/fork/MrChengmo/update_ps_heter github/fork/PWhiddy/patch-1 github/fork/Shixiaowei02/dev/save_load_upgrade github/fork/TCChenlong/fix_hapi github/fork/TCChenlong/fix_inden github/fork/Thunderbrook/xpu_slice github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_2 github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_3 github/fork/XieYunshen/timeout_20S_ut github/fork/ZeyuChen/remove-nltk github/fork/arlesniak/arlesniak/selective__mkldnn_flags github/fork/baiyfbupt/code_doc_mig github/fork/chalsliu/set_timeout github/fork/chen-zhiyu/develop github/fork/chenwhql/ci/try_to_find_test_buffer_shared_memory_reuse_pass_error github/fork/chenwhql/dygraph/remove_scale_loss_and_apply_collective_grads github/fork/chenwhql/saveload/add_get_inference_program github/fork/chenwhql/saveload/remove_save_load_config github/fork/cryoco/pass-compatibility-trt github/fork/danleifeng/isempty_api2.0 github/fork/frankwhzhang/api_transfer github/fork/hbwx24/error_msg/cuda_kernel_error_msg github/fork/heavengate/cherry_yolo_box github/fork/heavengate/update_yolo_box github/fork/iclementine/rnn_fix github/fork/iducn/testestse github/fork/jczaja/prv-25537-fix github/fork/jeff41404/release/1.8 github/fork/jiweibo/api_2.0 github/fork/jiweibo/fix_lite_resnet50_test github/fork/juncaipeng/fix_doc_1 github/fork/lfchener/sample_code github/fork/littletomatodonkey/fix_reg_doc github/fork/liym27/dy2stat_update_assign_to_rc20 github/fork/luotao1/profiler_ut github/fork/mapingshuo/add_wait github/fork/mapingshuo/doc_2.0 github/fork/mapingshuo/zero-0.5 github/fork/miraiwk/dev github/fork/pangyoki/add-Categorical-class-branch github/fork/pangyoki/add-multinomial-op-branch github/fork/pangyoki/fix-test_distritbution-CI github/fork/qjing666/doublegrad github/fork/qjing666/fix_hdfs_download github/fork/sandyhouse/add_gather_etc github/fork/sandyhouse/add_send_recv_alltoall_etc github/fork/sandyhouse/pipeline_exe_run github/fork/seiriosPlus/feature/large_scale_kv_save_delta github/fork/seiriosPlus/fix/paddle_errors_fix github/fork/seiriosPlus/fix/paddle_op_errors github/fork/shangzhizhou/fix_test_activation_op_random_bug github/fork/smallv0221/yxp0924 github/fork/smallv0221/yxp0925 github/fork/swtkiwi/del-matplotlib github/fork/tianshuo78520a/kunlun_test github/fork/tianshuo78520a/update_dockerfile github/fork/wanghaoshuang/bert_fuse github/fork/wanghaoshuang/label_smooth github/fork/wanghuancoder/develop_CUDASynchronize github/fork/wanghuancoder/develop_Layer_doc github/fork/wanghuancoder/develop_ParameterList_doc github/fork/wanghuancoder/develop_Sequential_doc github/fork/wanghuancoder/develop_bilinear_tensor_product github/fork/wanghuancoder/develop_coverage_build_sh github/fork/wanghuancoder/develop_in_dynamic_mode_doc github/fork/wanghuancoder/develop_unique_name_doc github/fork/wangxicoding/fleet_meta_combine github/fork/wawltor/error_message_fix_5 github/fork/willthefrog/remove_l2_norm github/fork/windstamp/momentum_op github/fork/windstamp/mv_op_5 github/fork/windstamp/normal_api github/fork/wojtuss/wojtuss/fusion_gru_quantization github/fork/wojtuss/wojtuss/quantization-with-shift github/fork/wzzju/fix_err_info github/fork/wzzju/pure_fp16 github/fork/xiemoyuan/op_error_message github/fork/xiemoyuan/optimize_error_message github/fork/yaoxuefeng6/fix_doc github/fork/yaoxuefeng6/mod_dataset_v2 github/fork/yongqiangma/lod github/fork/ysh329/fix-clip-by-norm-error github/fork/ysh329/fix-error-clip-by-value github/fork/yukavio/error_info github/fork/zhangting2020/conv_filter_grad github/fork/zhangting2020/is_compile_with_cuda github/fork/zhangting2020/place_doc github/fork/zhangting2020/program github/fork/zhhsplendid/fix_any github/fork/zhhsplendid/refine_api2 github/fork/zhhsplendid/refine_api2_test github/fork/zhhsplendid/refine_api_test_ptb_lm github/fork/zhhsplendid/refine_api_test_resnet github/fork/zhhsplendid/refine_api_test_simnet github/fork/zhiqiu/dev/refine_initializer github/fork/zhiqiu/dev/remove_inplace_argument github/fork/zlsh80826/nvinfer_plugin_var_len_cuda11 improve_sccache incubate/infrt incubate/lite inplace_addto make_flag_adding_easier master move_embedding_to_phi move_histogram_to_pten move_sgd_to_phi move_slice_to_pten move_temporal_shift_to_phi move_yolo_box_to_phi npu_fix_alloc numel paddle_tiny_install paralleltest preln_ernie prv-disable-more-cache prv-md-even-more prv-onednn-2.5 pten_tensor_refactor release/0.11.0 release/0.12.0 release/0.13.0 release/0.14.0 release/0.15.0 release/1.0.0 release/1.1 release/1.2 release/1.3 release/1.4 release/1.5 release/1.6 release/1.7 release/1.8 release/2.0 release/2.0-alpha release/2.0-beta release/2.0-rc release/2.0-rc1 release/2.1 release/2.2 release/2.3 release/2.3-fc-ernie-fix release/2.4 release/lite-0.1 revert-24981-add_device_attr_for_regulization revert-26856-strategy_example2 revert-27520-disable_pr revert-31068-fix_conv3d_windows revert-31562-mean revert-32290-develop-hardlabel revert-33037-forci revert-33475-fix_cifar_label_dimension revert-33630-bug-fix revert-34159-add_npu_bce_logical_dev revert-34406-add_copy_from_tensor revert-34910-spinlocks_for_allocator revert-35069-revert-34910-spinlocks_for_allocator revert-36057-dev/read_flags_in_ut revert-36201-refine_fast_threaded_ssa_graph_executor revert-36985-add_license revert-37318-refactor_dygraph_to_eager revert-37926-eager_coreops_500 revert-37956-revert-37727-pylayer_support_tuple revert-38100-mingdong revert-38301-allocation_rearrange_pr revert-38703-numpy_bf16_package_reupload revert-38732-remove_useless_header_in_elementwise_mul_grad revert-38959-Reduce_Grad revert-39143-adjust_empty revert-39227-move_trace_op_to_pten revert-39268-dev/remove_concat_fluid_kernel revert-40170-support_partial_grad revert-41056-revert-40727-move_some_activaion_to_phi revert-41065-revert-40993-mv_ele_floordiv_pow revert-41068-revert-40790-phi_new revert-41944-smaller_inference_api_test revert-42149-do-not-reset-default-stream-for-stream-safe-cuda-allocator revert-43155-fix_ut_tempfile revert-43882-revert-41944-smaller_inference_api_test revert-45808-phi/simplify_size_op revert-46827-deform_comment rocm_dev_0217 support_weight_transpose test_benchmark_ci test_feature_precision_test_c test_model_benchmark test_model_benchmark_ci zhiqiu-patch-1 v2.4.0-rc0 v2.3.2 v2.3.1 v2.3.0 v2.3.0-rc0 v2.2.2 v2.2.1 v2.2.0 v2.2.0-rc0 v2.2.0-bak0 v2.1.3 v2.1.2 v2.1.1 v2.1.0 v2.1.0-rc0 v2.0.2 v2.0.1 v2.0.0 v2.0.0-rc1 v2.0.0-rc0 v2.0.0-beta0 v2.0.0-alpha0 v1.8.5 v1.8.4 v1.8.3 v1.8.2 v1.8.1 v1.8.0 v1.7.2 v1.7.1 v1.7.0 v1.6.3 v1.6.2 v1.6.1 v1.6.0 v1.6.0-rc0 v1.5.2 v1.5.1 v1.5.0 v1.4.1 v1.4.0 v1.3.2 v1.3.1 v1.3.0 v1.2.1 v1.2.0 v1.1.0 v1.0.2 v1.0.1 v1.0.0 v1.0.0-rc0 v0.15.0 v0.15.0-rc0 v0.14.0 v0.13.0 v0.12.0 v0.11.1a2 v0.11.1a1 v0.11.0 lite-v0.1
无相关合并请求
......@@ -25,95 +25,89 @@ enum TestType {
kBackwardFilterTest = 2,
};
enum LayerType {
convolutionType = 0,
depthwiseConvolutionType = 1,
};
template <DeviceType DType1, DeviceType DType2>
class ConvolutionTest {
public:
ConvolutionTest(const std::string& conv1,
const std::string& conv2,
LayerType layerType,
TestType type,
bool useGroups = true,
std::string algo = "auto") {
for (size_t batchSize : {1, 32}) {
for (size_t inputSize : {7, 14, 54}) {
for (size_t filterSize : {1, 3, 5}) {
for (size_t inputChannels : {3, 64}) {
for (size_t outputChannels : {3, 64, 128}) {
if (inputChannels > outputChannels) break;
if (layerType == depthwiseConvolutionType &&
outputChannels % inputChannels != 0)
break;
size_t groups = 1;
if (layerType == depthwiseConvolutionType) {
groups = inputChannels;
}
for (size_t stride : {1, 2}) {
for (size_t padding : {0, 1}) {
if (padding >= filterSize) break;
size_t outputSize =
(inputSize - filterSize + 2 * padding + stride) / stride;
VLOG(3) << " batchSize=" << batchSize
<< " inputChannels=" << inputChannels
<< " inputHeight=" << inputSize
<< " inputWidth=" << inputSize
<< " outputChannels=" << outputChannels
<< " filterHeight=" << filterSize
<< " filterWidth=" << filterSize
<< " outputHeight=" << outputSize
<< " outputWidth=" << outputSize
<< " stride=" << stride << " padding=" << padding;
std::vector<size_t> paddings = {padding, padding};
std::vector<size_t> strides = {stride, stride};
Compare2Function<DType1, DType2> test(
conv1,
conv2,
FuncConfig()
.set("paddings", paddings)
.set("strides", strides)
.set("groups", groups)
.set("algo", algo));
TensorShape input{
batchSize, inputChannels, inputSize, inputSize};
TensorShape filter;
if (layerType == depthwiseConvolutionType)
filter = TensorShape({groups,
outputChannels / groups,
(size_t)1,
filterSize,
filterSize});
else
filter = TensorShape({outputChannels,
inputChannels,
filterSize,
filterSize});
TensorShape output{
batchSize, outputChannels, outputSize, outputSize};
if (type == kForwardTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, input));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.run();
} else if (type == kBackwardInputTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, input), ADD_TO);
test.run();
} else if (type == kBackwardFilterTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, input));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.run();
for (size_t groups : {1, 3, 64}) {
if (inputChannels > outputChannels) break;
if (groups != 1 &&
(inputChannels != groups || outputChannels % groups != 0))
continue;
if (!useGroups) groups = 1;
for (size_t stride : {1, 2}) {
for (size_t padding : {0, 1}) {
if (padding >= filterSize) break;
size_t outputSize =
(inputSize - filterSize + 2 * padding + stride) /
stride;
VLOG(3) << " batchSize=" << batchSize
<< " inputChannels=" << inputChannels
<< " inputHeight=" << inputSize
<< " inputWidth=" << inputSize
<< " outputChannels=" << outputChannels
<< " filterHeight=" << filterSize
<< " filterWidth=" << filterSize
<< " outputHeight=" << outputSize
<< " outputWidth=" << outputSize
<< " stride=" << stride << " padding=" << padding;
std::vector<size_t> paddings = {padding, padding};
std::vector<size_t> strides = {stride, stride};
Compare2Function<DType1, DType2> test(
conv1,
conv2,
FuncConfig()
.set("paddings", paddings)
.set("strides", strides)
.set("groups", groups)
.set("algo", algo));
TensorShape input{
batchSize, inputChannels, inputSize, inputSize};
TensorShape filter;
if (groups > 1)
filter = TensorShape({groups,
outputChannels / groups,
inputChannels / groups,
filterSize,
filterSize});
else
filter = TensorShape({outputChannels,
inputChannels,
filterSize,
filterSize});
TensorShape output{
batchSize, outputChannels, outputSize, outputSize};
if (type == kForwardTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, input));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.run();
} else if (type == kBackwardInputTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, input),
ADD_TO);
test.run();
} else if (type == kBackwardFilterTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, input));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.run();
}
}
}
}
......@@ -132,8 +126,8 @@ class ConvolutionTest2 {
public:
ConvolutionTest2(const std::string& conv1,
const std::string& conv2,
LayerType layerType,
TestType type,
bool useGroups = true,
std::string algo = "auto") {
for (size_t batchSize : {16}) {
for (size_t inputHeight : {7, 31}) {
......@@ -142,78 +136,78 @@ public:
for (size_t filterWidth : {3, 7}) {
for (size_t inputChannels : {7}) {
for (size_t outputChannels : {7, 32}) {
if (layerType == depthwiseConvolutionType &&
outputChannels % inputChannels != 0)
break;
size_t groups = 1;
if (layerType == depthwiseConvolutionType) {
groups = inputChannels;
}
size_t stride = 1;
size_t padding = 0;
size_t outputHeight =
(inputHeight - filterHeight + 2 * padding + stride) /
stride;
size_t outputWidth =
(inputWidth - filterWidth + 2 * padding + stride) /
stride;
VLOG(3) << " batchSize=" << batchSize
<< " inputChannels=" << inputChannels
<< " inputHeight=" << inputHeight
<< " inputWidth=" << inputWidth
<< " outputChannels=" << outputChannels
<< " filterHeight=" << filterHeight
<< " filterWidth=" << filterWidth
<< " outputHeight=" << outputHeight
<< " outputWidth=" << outputWidth
<< " stride=" << stride << " padding=" << padding;
std::vector<size_t> paddings = {padding, padding};
std::vector<size_t> strides = {stride, stride};
Compare2Function<DType1, DType2> test(
conv1,
conv2,
FuncConfig()
.set("paddings", paddings)
.set("strides", strides)
.set("groups", groups)
.set("algo", algo));
TensorShape input{
batchSize, inputChannels, inputHeight, inputWidth};
TensorShape filter;
if (layerType == depthwiseConvolutionType)
filter = TensorShape({groups,
outputChannels / groups,
(size_t)1,
filterHeight,
filterWidth});
else
filter = TensorShape({outputChannels,
inputChannels,
filterHeight,
filterWidth});
TensorShape output{
batchSize, outputChannels, outputHeight, outputWidth};
if (type == kForwardTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, input));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.run();
} else if (type == kBackwardInputTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, input), ADD_TO);
test.run();
} else if (type == kBackwardFilterTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, input));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.run();
for (size_t groups : {1, 7}) {
if (!useGroups && groups != 1 &&
(inputChannels != groups ||
outputChannels % groups != 0))
continue;
if (!useGroups) groups = 1;
size_t stride = 1;
size_t padding = 0;
size_t outputHeight =
(inputHeight - filterHeight + 2 * padding + stride) /
stride;
size_t outputWidth =
(inputWidth - filterWidth + 2 * padding + stride) /
stride;
VLOG(3) << " batchSize=" << batchSize
<< " inputChannels=" << inputChannels
<< " inputHeight=" << inputHeight
<< " inputWidth=" << inputWidth
<< " outputChannels=" << outputChannels
<< " filterHeight=" << filterHeight
<< " filterWidth=" << filterWidth
<< " outputHeight=" << outputHeight
<< " outputWidth=" << outputWidth
<< " stride=" << stride << " padding=" << padding;
std::vector<size_t> paddings = {padding, padding};
std::vector<size_t> strides = {stride, stride};
Compare2Function<DType1, DType2> test(
conv1,
conv2,
FuncConfig()
.set("paddings", paddings)
.set("strides", strides)
.set("groups", groups)
.set("algo", algo));
TensorShape input{
batchSize, inputChannels, inputHeight, inputWidth};
TensorShape filter;
if (groups > 1)
filter = TensorShape({groups,
outputChannels / groups,
inputChannels / groups,
filterHeight,
filterWidth});
else
filter = TensorShape({outputChannels,
inputChannels,
filterHeight,
filterWidth});
TensorShape output{
batchSize, outputChannels, outputHeight, outputWidth};
if (type == kForwardTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, input));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.run();
} else if (type == kBackwardInputTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, input),
ADD_TO);
test.run();
} else if (type == kBackwardFilterTest) {
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, output));
test.addInputs(BufferArg(VALUE_TYPE_FLOAT, input));
test.addOutputs(BufferArg(VALUE_TYPE_FLOAT, filter));
test.run();
}
}
}
}
......@@ -225,107 +219,34 @@ public:
}
};
// ======Start Convolution TEST======
TEST(Forward, GEMM) {
ConvolutionTest<DEVICE_TYPE_CPU, DEVICE_TYPE_CPU> test(
"NaiveConv-CPU", "GemmConv-CPU", convolutionType, kForwardTest);
"NaiveConv-CPU", "GemmConv-CPU", kForwardTest, false);
ConvolutionTest2<DEVICE_TYPE_CPU, DEVICE_TYPE_CPU> test2(
"NaiveConv-CPU", "GemmConv-CPU", convolutionType, kForwardTest);
"NaiveConv-CPU", "GemmConv-CPU", kForwardTest, false);
}
#ifndef PADDLE_ONLY_CPU
TEST(Forward, GEMM2) {
ConvolutionTest<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test(
"GemmConv-CPU", "GemmConv-GPU", convolutionType, kForwardTest);
"GemmConv-CPU", "GemmConv-GPU", kForwardTest);
ConvolutionTest2<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test2(
"GemmConv-CPU", "GemmConv-GPU", convolutionType, kForwardTest);
"GemmConv-CPU", "GemmConv-GPU", kForwardTest);
}
TEST(BackwardInput, GEMM) {
ConvolutionTest<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test(
"GemmConvGradInput-CPU",
"GemmConvGradInput-GPU",
convolutionType,
kBackwardInputTest);
"GemmConvGradInput-CPU", "GemmConvGradInput-GPU", kBackwardInputTest);
ConvolutionTest2<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test2(
"GemmConvGradInput-CPU",
"GemmConvGradInput-GPU",
convolutionType,
kBackwardInputTest);
"GemmConvGradInput-CPU", "GemmConvGradInput-GPU", kBackwardInputTest);
}
TEST(BackwardFilter, GEMM) {
ConvolutionTest<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test(
"GemmConvGradFilter-CPU",
"GemmConvGradFilter-GPU",
convolutionType,
kBackwardFilterTest);
ConvolutionTest2<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test2(
"GemmConvGradFilter-CPU",
"GemmConvGradFilter-GPU",
convolutionType,
kBackwardFilterTest);
}
#endif
// ======End Convolution TEST======
// ======Start DepthwiseConvolution TEST======
// TODO(zhaolong) The depthwise convolution cpu test will be added when the cpu
// version of depthwiseConv is implemented.
#ifndef PADDLE_ONLY_CPU
TEST(DepthwiseConvForward, GEMM) {
ConvolutionTest<DEVICE_TYPE_GPU, DEVICE_TYPE_GPU> test(
"GemmConv-GPU",
"DepthwiseConv-GPU",
depthwiseConvolutionType,
kForwardTest);
ConvolutionTest2<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test2(
"GemmConv-GPU",
"DepthwiseConv-GPU",
depthwiseConvolutionType,
kForwardTest);
}
TEST(DepthwiseConvForward, GEMM2) {
ConvolutionTest<DEVICE_TYPE_GPU, DEVICE_TYPE_GPU> test(
"DepthwiseConv-GPU",
"DepthwiseConv-GPU",
depthwiseConvolutionType,
kForwardTest);
ConvolutionTest2<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test2(
"DepthwiseConv-GPU",
"DepthwiseConv-GPU",
depthwiseConvolutionType,
kForwardTest);
}
TEST(DepthwiseConvBackwardInput, GEMM) {
ConvolutionTest<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test(
"DepthwiseConvGradInput-GPU",
"DepthwiseConvGradInput-GPU",
depthwiseConvolutionType,
kBackwardInputTest);
ConvolutionTest2<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test2(
"DepthwiseConvGradInput-GPU",
"DepthwiseConvGradInput-GPU",
depthwiseConvolutionType,
kBackwardInputTest);
}
TEST(DepthwiseConvBackwardFilter, GEMM) {
ConvolutionTest<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test(
"DepthwiseConvGradFilter-GPU",
"DepthwiseConvGradFilter-GPU",
depthwiseConvolutionType,
kBackwardFilterTest);
"GemmConvGradFilter-CPU", "GemmConvGradFilter-GPU", kBackwardFilterTest);
ConvolutionTest2<DEVICE_TYPE_CPU, DEVICE_TYPE_GPU> test2(
"DepthwiseConvGradFilter-GPU",
"DepthwiseConvGradFilter-GPU",
depthwiseConvolutionType,
kBackwardFilterTest);
"GemmConvGradFilter-CPU", "GemmConvGradFilter-GPU", kBackwardFilterTest);
}
#endif
// ======End DepthwiseConvolution TEST======
} // namespace paddle
......@@ -39,21 +39,22 @@ bool ExpandConvLayer::init(const LayerMap &layerMap,
filterShape_.resize(numInputs);
outputShape_.resize(numInputs);
string convType;
string convGradInputType;
string convGradFilterType;
std::string convType;
std::string convGradInputType;
std::string convGradFilterType;
for (int i = 0; i < config_.inputs_size(); i++) {
std::vector<size_t> paddings = {(size_t)paddingY_[i], (size_t)padding_[i]};
std::vector<size_t> strides = {(size_t)strideY_[i], (size_t)stride_[i]};
if (useGpu_ && (size_t)groups_[i] == (size_t)channels_[i] && !isDeconv_) {
convType = "DepthwiseConv" convGradInputType =
"DepthwiseConvGradInput" convGradFilterType =
"DepthwiseConvGradFilter"
convType = "DepthwiseConv";
convGradInputType = "DepthwiseConvGradInput";
convGradFilterType = "DepthwiseConvGradFilter";
} else {
convType = "GemmConv" convGradInputType =
"GemmConvGradInput" convGradFilterType = "GemmConvGradFilter"
convType = "GemmConv";
convGradInputType = "GemmConvGradInput";
convGradFilterType = "GemmConvGradFilter";
}
if (FLAGS_use_nnpack) {
......
......@@ -349,13 +349,13 @@ TEST(Layer, CosSimVecMatLayer) {
void testDepthwiseConvLayer(const string& type, bool useGpu) {
TestConfig config;
config.biasSize = 16;
config.biasSize = 32;
config.layerConfig.set_type(type);
config.layerConfig.set_num_filters(16);
config.layerConfig.set_num_filters(32);
config.layerConfig.set_partial_sum(1);
config.layerConfig.set_shared_biases(true);
config.inputDefs.push_back({INPUT_DATA, "layer_0", 2048, 192 / 2});
config.inputDefs.push_back({INPUT_DATA, "layer_0", 2048, 192});
LayerInputConfig* input = config.layerConfig.add_inputs();
ConvConfig* conv = input->mutable_conv_conf();
conv->set_filter_size(2);
......@@ -388,8 +388,11 @@ void testDepthwiseConvLayer(const string& type, bool useGpu) {
}
TEST(Layer, depthwiseConvLayer) {
// 'depthwise_conv' is a sepecial case of 'exconv' whose
// groups size equals to the input channels size.
testDepthwiseConvLayer("exconv", /* useGpu= */ false);
#ifndef PADDLE_ONLY_CPU
testDepthwiseConvLayer("depthwise_conv", /* useGpu= */ true);
testDepthwiseConvLayer("exconv", /* useGpu= */ true);
#endif
}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部