Hi,
I have the following example. How to rewrite the code - so I can use the model Predict for the given input? There is no example in the docs...
#include "yggdrasil_decision_forests/dataset/data_spec.h"
#include "yggdrasil_decision_forests/dataset/data_spec.pb.h"
#include "yggdrasil_decision_forests/dataset/data_spec_inference.h"
#include "yggdrasil_decision_forests/dataset/vertical_dataset_io.h"
#include "yggdrasil_decision_forests/learner/learner_library.h"
#include "yggdrasil_decision_forests/metric/metric.h"
#include "yggdrasil_decision_forests/metric/report.h"
#include "yggdrasil_decision_forests/model/model_library.h"
#include "yggdrasil_decision_forests/utils/filesystem.h"
#include "yggdrasil_decision_forests/utils/logging.h"
#include "yggdrasil_decision_forests/serving/decision_forest/decision_forest.h"
#include <chrono>
namespace ygg = yggdrasil_decision_forests;
int main(int argc, char** argv) {
// Enable the logging. Optional in most cases.
InitLogging(argv[0], &argc, &argv, true);
// Import the model.
LOG(INFO) << "Import the model";
const std::string model_path = "/tmp/my_saved_model/1/assets";
std::unique_ptr<ygg::model::AbstractModel> model;
QCHECK_OK(ygg::model::LoadModel(model_path, &model));
// Show information about the model.
// Like :show_model, but without the list of compatible engines.
std::string model_description;
model->AppendDescriptionAndStatistics(/*full_definition=*/false,
&model_description);
LOG(INFO) << "Model:\n" << model_description;
auto start = std::chrono::high_resolution_clock::now();
// Compile the model for fast inference.
const std::unique_ptr<ygg::serving::FastEngine> serving_engine =
model->BuildFastEngine().value();
const auto& features = serving_engine->features();
// Handle to two features.
const auto age_feature = features.GetNumericalFeatureId("age").value();
const auto sex_feature =
features.GetCategoricalFeatureId("sex").value();
// Allocate a batch of 1 examples.
std::unique_ptr<ygg::serving::AbstractExampleSet> examples =
serving_engine->AllocateExamples(1);
// Set all the values as missing. This is only necessary if you don't set all
// the feature values manually e.g. SetNumerical.
//examples->FillMissing(features);
// Set the value of "age" and "eduction" for the first example.
examples->SetNumerical(/*example_idx=*/0, age_feature, 50.f, features);
examples->SetCategorical(/*example_idx=*/0, sex_feature, "Male",
features);
// Run the predictions on the first two examples.
std::vector<float> batch_of_predictions;
serving_engine->Predict(*examples, 1, &batch_of_predictions);
auto stop = high_resolution_clock::now();
auto duration = std::chrono::duration_cast<milliseconds>(stop - start);
// To get the value of duration use the count()
// member function on the duration object
LOG(INFO) << duration.count();
LOG(INFO) << "Predictions:";
for (const float prediction : batch_of_predictions) {
LOG(INFO) << "\t" << prediction;
}
return 0;
}
Output:
[INFO beginner4.cc:31] Import the model
[INFO beginner4.cc:41] Model:
Type: "RANDOM_FOREST"
Task: CLASSIFICATION
Label: "__LABEL"
Input Features (2):
age
sex
No weights
Variable Importance: MEAN_MIN_DEPTH:
1. "__LABEL" 8.480250 ################
2. "sex" 1.313142 ##
3. "age" 0.000000
Variable Importance: NUM_AS_ROOT:
1. "age" 300.000000
Variable Importance: NUM_NODES:
1. "age" 34255.000000 ################
2. "sex" 1584.000000
Variable Importance: SUM_SCORE:
1. "age" 516361.208020 ################
2. "sex" 148174.885377
Winner take all: true
Out-of-bag evaluation: accuracy:0.756613 logloss:5.68258
Number of trees: 300
Total number of nodes: 71978
Number of nodes by tree:
Count: 300 Average: 239.927 StdDev: 4.94044
Min: 223 Max: 251 Ignored: 0
----------------------------------------------
[ 223, 224) 1 0.33% 0.33%
[ 224, 225) 0 0.00% 0.33%
[ 225, 227) 1 0.33% 0.67%
[ 227, 228) 3 1.00% 1.67% #
[ 228, 230) 3 1.00% 2.67% #
[ 230, 231) 0 0.00% 2.67%
[ 231, 233) 9 3.00% 5.67% ##
[ 233, 234) 17 5.67% 11.33% ###
[ 234, 236) 33 11.00% 22.33% ######
[ 236, 237) 0 0.00% 22.33%
[ 237, 238) 28 9.33% 31.67% #####
[ 238, 240) 51 17.00% 48.67% ##########
[ 240, 241) 0 0.00% 48.67%
[ 241, 243) 46 15.33% 64.00% #########
[ 243, 244) 47 15.67% 79.67% #########
[ 244, 246) 34 11.33% 91.00% #######
[ 246, 247) 0 0.00% 91.00%
[ 247, 249) 13 4.33% 95.33% ###
[ 249, 250) 10 3.33% 98.67% ##
[ 250, 251] 4 1.33% 100.00% #
Depth by leafs:
Count: 36139 Average: 8.48037 StdDev: 2.34049
Min: 3 Max: 15 Ignored: 0
----------------------------------------------
[ 3, 4) 70 0.19% 0.19%
[ 4, 5) 662 1.83% 2.03% #
[ 5, 6) 3633 10.05% 12.08% ######
[ 6, 7) 3980 11.01% 23.09% #######
[ 7, 8) 4520 12.51% 35.60% ########
[ 8, 9) 5143 14.23% 49.83% #########
[ 9, 10) 5817 16.10% 65.93% ##########
[ 10, 11) 5152 14.26% 80.18% #########
[ 11, 12) 3519 9.74% 89.92% ######
[ 12, 13) 2003 5.54% 95.46% ###
[ 13, 14) 975 2.70% 98.16% ##
[ 14, 15) 483 1.34% 99.50% #
[ 15, 15] 182 0.50% 100.00%
Number of training obs by leaf:
Count: 36139 Average: 190.182 StdDev: 179.903
Min: 5 Max: 2370 Ignored: 0
----------------------------------------------
[ 5, 123) 14849 41.09% 41.09% ##########
[ 123, 241) 10680 29.55% 70.64% #######
[ 241, 359) 3917 10.84% 81.48% ###
[ 359, 478) 6234 17.25% 98.73% ####
[ 478, 596) 137 0.38% 99.11%
[ 596, 714) 7 0.02% 99.13%
[ 714, 833) 17 0.05% 99.18%
[ 833, 951) 19 0.05% 99.23%
[ 951, 1069) 6 0.02% 99.24%
[ 1069, 1188) 135 0.37% 99.62%
[ 1188, 1306) 33 0.09% 99.71%
[ 1306, 1424) 0 0.00% 99.71%
[ 1424, 1542) 0 0.00% 99.71%
[ 1542, 1661) 8 0.02% 99.73%
[ 1661, 1779) 53 0.15% 99.88%
[ 1779, 1897) 6 0.02% 99.89%
[ 1897, 2016) 0 0.00% 99.89%
[ 2016, 2134) 2 0.01% 99.90%
[ 2134, 2252) 28 0.08% 99.98%
[ 2252, 2370] 8 0.02% 100.00%
Attribute in nodes:
34255 : age [NUMERICAL]
1584 : sex [CATEGORICAL]
Attribute in nodes with depth <= 0:
300 : age [NUMERICAL]
Attribute in nodes with depth <= 1:
600 : age [NUMERICAL]
300 : sex [CATEGORICAL]
Attribute in nodes with depth <= 2:
1721 : age [NUMERICAL]
379 : sex [CATEGORICAL]
Attribute in nodes with depth <= 3:
3328 : age [NUMERICAL]
1102 : sex [CATEGORICAL]
Attribute in nodes with depth <= 5:
11208 : age [NUMERICAL]
1583 : sex [CATEGORICAL]
Condition type in nodes:
34255 : HigherCondition
1584 : ContainsBitmapCondition
Condition type in nodes with depth <= 0:
300 : HigherCondition
Condition type in nodes with depth <= 1:
600 : HigherCondition
300 : ContainsBitmapCondition
Condition type in nodes with depth <= 2:
1721 : HigherCondition
379 : ContainsBitmapCondition
Condition type in nodes with depth <= 3:
3328 : HigherCondition
1102 : ContainsBitmapCondition
Condition type in nodes with depth <= 5:
11208 : HigherCondition
1583 : ContainsBitmapCondition
Node format: BLOB_SEQUENCE
Training OOB:
trees: 1, Out-of-bag evaluation: accuracy:0.750237 logloss:9.00239
trees: 13, Out-of-bag evaluation: accuracy:0.754722 logloss:7.09704
trees: 23, Out-of-bag evaluation: accuracy:0.753863 logloss:6.3117
trees: 33, Out-of-bag evaluation: accuracy:0.75395 logloss:6.19856
trees: 43, Out-of-bag evaluation: accuracy:0.754299 logloss:6.0429
trees: 53, Out-of-bag evaluation: accuracy:0.753165 logloss:5.9747
trees: 63, Out-of-bag evaluation: accuracy:0.754867 logloss:5.96594
trees: 73, Out-of-bag evaluation: accuracy:0.75443 logloss:5.92934
trees: 83, Out-of-bag evaluation: accuracy:0.754954 logloss:5.92356
trees: 93, Out-of-bag evaluation: accuracy:0.756307 logloss:5.89293
trees: 103, Out-of-bag evaluation: accuracy:0.756569 logloss:5.89233
trees: 113, Out-of-bag evaluation: accuracy:0.755696 logloss:5.81216
trees: 123, Out-of-bag evaluation: accuracy:0.755653 logloss:5.81
trees: 133, Out-of-bag evaluation: accuracy:0.755347 logloss:5.80588
trees: 143, Out-of-bag evaluation: accuracy:0.755914 logloss:5.77847
trees: 153, Out-of-bag evaluation: accuracy:0.755783 logloss:5.77828
trees: 163, Out-of-bag evaluation: accuracy:0.755522 logloss:5.74301
trees: 173, Out-of-bag evaluation: accuracy:0.756264 logloss:5.73794
trees: 183, Out-of-bag evaluation: accuracy:0.756176 logloss:5.7384
trees: 193, Out-of-bag evaluation: accuracy:0.756831 logloss:5.73852
trees: 203, Out-of-bag evaluation: accuracy:0.756613 logloss:5.73565
trees: 213, Out-of-bag evaluation: accuracy:0.757268 logloss:5.73545
trees: 223, Out-of-bag evaluation: accuracy:0.757486 logloss:5.7286
trees: 233, Out-of-bag evaluation: accuracy:0.757093 logloss:5.72556
trees: 243, Out-of-bag evaluation: accuracy:0.757093 logloss:5.7087
trees: 253, Out-of-bag evaluation: accuracy:0.757224 logloss:5.70704
trees: 263, Out-of-bag evaluation: accuracy:0.757006 logloss:5.69758
trees: 273, Out-of-bag evaluation: accuracy:0.756831 logloss:5.69816
trees: 283, Out-of-bag evaluation: accuracy:0.756526 logloss:5.69813
trees: 293, Out-of-bag evaluation: accuracy:0.756526 logloss:5.68217
trees: 300, Out-of-bag evaluation: accuracy:0.756613 logloss:5.68258
[INFO decision_forest.cc:639] Model loaded with 300 root(s), 71978 node(s), and 2 input feature(s).
[INFO abstract_model.cc:1158] Engine "RandomForestOptPred" built
[INFO beginner4.cc:79] 18
[INFO beginner4.cc:81] Predictions:
[INFO beginner4.cc:83] 0.649999
Lets say I want to continuously read the inference input data from stdin - I only need to load model and initialized serving_engine once?
every time stdin has new data to run a prediction I just need to run the following code? does anything change when I change to a http inference - anything to consider regarding thread safety - I cant share the model and serving_engine across multiple threads?
Is there anything I should change when I dont need batching? I still need to use std::unique_ptr<ygg::serving::AbstractExampleSet> examples = serving_engine->AllocateExamples(1)?
// Handle to two features.
const auto age_feature = features.GetNumericalFeatureId("age").value();
const auto sex_feature =
features.GetCategoricalFeatureId("sex").value();
// Allocate a batch of 1 examples.
std::unique_ptr<ygg::serving::AbstractExampleSet> examples =
serving_engine->AllocateExamples(1);
// Set all the values as missing. This is only necessary if you don't set all
// the feature values manually e.g. SetNumerical.
//examples->FillMissing(features);
// Set the value of "age" and "eduction" for the first example.
examples->SetNumerical(/*example_idx=*/0, age_feature, 50.f, features);
examples->SetCategorical(/*example_idx=*/0, sex_feature, "Male",
features);
// Run the predictions on the first two examples.
std::vector<float> batch_of_predictions;
serving_engine->Predict(*examples, 1, &batch_of_predictions);
auto stop = high_resolution_clock::now();
auto duration = std::chrono::duration_cast<milliseconds>(stop - start);
// To get the value of duration use the count()
// member function on the duration object
LOG(INFO) << duration.count();
LOG(INFO) << "Predictions:";
for (const float prediction : batch_of_predictions) {
LOG(INFO) << "\t" << prediction;
}
I also tried to use the c-api here, but always get as Result Tensor: 1.0? any idea why?
// gcc -I/usr/local/include -L/usr/local/lib main.c -ltensorflow -o main
#include <stdio.h>
#include <tensorflow/c/c_api.h>
void NoOpDeallocator(void* data, size_t a, void* b) {}
int main() {
TF_Graph *Graph = TF_NewGraph();
TF_Status *Status = TF_NewStatus();
TF_SessionOptions *SessionOpts = TF_NewSessionOptions();
TF_Buffer *RunOpts = NULL;
TF_Library *library;
library = TF_LoadLibrary("/usr/local/lib/python3.10/dist-packages/tensorflow_decision_forests/tensorflow/ops/inference/inference.so",
Status);
const char *saved_model_dir = "/tmp/my_saved_model/1/";
const char *tags = "serve";
int ntags = 1;
TF_Session *Session = TF_LoadSessionFromSavedModel(
SessionOpts, RunOpts, saved_model_dir, &tags, ntags, Graph, NULL, Status);
printf("status: %s\n", TF_Message(Status));
if(TF_GetCode(Status) == TF_OK) {
printf("loaded\n");
}else{
printf("not loaded\n");
}
/* Get Input Tensor */
int NumInputs = 2;
TF_Output* Input = malloc(sizeof(TF_Output) * NumInputs);
TF_Output t0 = {TF_GraphOperationByName(Graph, "serving_default_age"), 0};
if(t0.oper == NULL)
printf("ERROR: Failed TF_GraphOperationByName serving_default_input_1\n");
else
printf("TF_GraphOperationByName serving_default_input_1 is OK\n");
TF_Output t1 = {TF_GraphOperationByName(Graph, "serving_default_sex"), 0};
if(t1.oper == NULL)
printf("ERROR: Failed TF_GraphOperationByName serving_default_input_2\n");
else
printf("TF_GraphOperationByName serving_default_input_2 is OK\n");
Input[0] = t0;
Input[1] = t1;
// Get Output tensor
int NumOutputs = 1;
TF_Output* Output = malloc(sizeof(TF_Output) * NumOutputs);
TF_Output tout = {TF_GraphOperationByName(Graph, "StatefulPartitionedCall_1"), 0};
if(tout.oper == NULL)
printf("ERROR: Failed TF_GraphOperationByName StatefulPartitionedCall\n");
else
printf("TF_GraphOperationByName StatefulPartitionedCall is OK\n");
Output[0] = tout;
/* Allocate data for inputs and outputs */
TF_Tensor** InputValues = (TF_Tensor**)malloc(sizeof(TF_Tensor*)*NumInputs);
TF_Tensor** OutputValues = (TF_Tensor**)malloc(sizeof(TF_Tensor*)*NumOutputs);
int ndims = 1;
int64_t dims[] = {1};
int64_t data[] = {50};
int ndata = sizeof(int64_t);
TF_Tensor* int_tensor0 = TF_NewTensor(TF_INT64, dims, ndims, data, ndata, &NoOpDeallocator, 0);
if (int_tensor0 != NULL)
printf("TF_NewTensor is OK\n");
else
printf("ERROR: Failed TF_NewTensor\n");
const char test_string[] = "Male";
TF_TString tstr[1];
TF_TString_Init(&tstr[0]);
TF_TString_Copy(&tstr[0], test_string, sizeof(test_string)-1);
TF_Tensor* int_tensor1 = TF_NewTensor(TF_STRING, NULL, 0, &tstr[0], sizeof(tstr), &NoOpDeallocator, 0);
if (int_tensor1 != NULL)
printf("TF_NewTensor is OK\n");
else
printf("ERROR: Failed TF_NewTensor\n");
InputValues[0] = int_tensor0;
InputValues[1] = int_tensor1;
// Run the Session
TF_SessionRun(Session,
NULL, // Run options.
Input, InputValues, NumInputs, // Input tensors name, input tensor values, number of inputs.
Output, OutputValues, NumOutputs, // Output tensors name, output tensor values, number of outputs.
NULL, 0, // Target operations, number of targets.
NULL,
Status); // Output status.
if(TF_GetCode(Status) == TF_OK)
printf("Session is OK\n");
else
printf("%s",TF_Message(Status));
// Free memory
TF_DeleteGraph(Graph);
TF_DeleteSession(Session, Status);
TF_DeleteSessionOptions(SessionOpts);
TF_DeleteStatus(Status);
/* Get Output Result */
void* buff = TF_TensorData(OutputValues[0]);
float* offsets = (float*)buff;
printf("Result Tensor :\n");
printf("%f\n",offsets[0]);
return 0;
}
Output:
# gcc -I/usr/local/include -L/usr/local/lib main.c -ltensorflow -o main; ./main
2022-06-16 21:05:24.070748: I tensorflow/cc/saved_model/reader.cc:43] Reading SavedModel from: /tmp/my_saved_model/1/
2022-06-16 21:05:24.072148: I tensorflow/cc/saved_model/reader.cc:81] Reading meta graph with tags { serve }
2022-06-16 21:05:24.072208: I tensorflow/cc/saved_model/reader.cc:122] Reading SavedModel debug info (if present) from: /tmp/my_saved_model/1/
2022-06-16 21:05:24.072280: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-06-16 21:05:24.085806: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:354] MLIR V1 optimization pass is not enabled
2022-06-16 21:05:24.086985: I tensorflow/cc/saved_model/loader.cc:228] Restoring SavedModel bundle.
2022-06-16 21:05:24.116570: I tensorflow/cc/saved_model/loader.cc:212] Running initialization op on SavedModel bundle at path: /tmp/my_saved_model/1/
[INFO kernel.cc:1176] Loading model from path /tmp/my_saved_model/1/assets/ with prefix cf8326335a66430a
[INFO decision_forest.cc:639] Model loaded with 300 root(s), 71978 node(s), and 2 input feature(s).
[INFO abstract_model.cc:1246] Engine "RandomForestOptPred" built
[INFO kernel.cc:1022] Use fast generic engine
2022-06-16 21:05:24.373058: I tensorflow/cc/saved_model/loader.cc:301] SavedModel load for tags { serve }; Status: success: OK. Took 302321 microseconds.
status:
loaded
TF_GraphOperationByName serving_default_input_1 is OK
TF_GraphOperationByName serving_default_input_2 is OK
TF_GraphOperationByName StatefulPartitionedCall is OK
TF_NewTensor is OK
TF_NewTensor is OK
Session is OK
Result Tensor :
1.000000
337 Dec 27, 2022
122 Nov 17, 2022
602 Jan 5, 2023
49 Dec 15, 2022
1.5k Dec 29, 2022
23.6k Dec 30, 2022
11.6k Dec 31, 2022
413 Dec 17, 2022
269 Jan 2, 2023
2.8k Dec 29, 2022
2.2k Jan 4, 2023
10 Oct 15, 2022
5.7k Jan 4, 2023
128 Nov 18, 2022
648 Dec 16, 2022
6 Sep 29, 2022
6.6k Jan 8, 2023
651 Dec 29, 2022