Cloud Inference Application - Graphs & Enhancements #115

hansely · 2019-05-11T00:12:41Z

No description provided.

apps/cloud_inference/client_app/annInferenceApp.pro

kiritigowda · 2019-05-11T00:14:48Z

apps/cloud_inference/client_app/inference_receiver.cpp

@@ -72,7 +72,6 @@ void inference_receiver::run()
    //    - when results are received add the results to imageIndex, imageLabel, imageSummary queues

    progress->images_sent = 0;
-    progress->images_received = 0;


kiritigowda · 2019-05-11T00:14:56Z

apps/cloud_inference/client_app/inference_receiver.cpp

@@ -86,7 +85,6 @@ void inference_receiver::run()
                break;
            if(cmd.magic != INFCOM_MAGIC) {
                progress->errorCode = -1;
-                progress->message.sprintf("ERROR: got invalid magic 0x%08x", cmd.magic);


kiritigowda · 2019-05-11T00:15:03Z

apps/cloud_inference/client_app/inference_receiver.cpp

@@ -113,7 +111,6 @@ void inference_receiver::run()
                connection->sendCmd(reply);
            }
            else if(cmd.command == INFCOM_CMD_SEND_IMAGES) {
-                progress->message = "";


kiritigowda · 2019-05-11T00:15:16Z

apps/cloud_inference/client_app/inference_receiver.cpp

}
+

kiritigowda · 2019-05-11T00:16:03Z

apps/cloud_inference/client_app/inference_viewer.cpp

+                (y < (state->graphButtonRect.y() + state->graphButtonRect.height())))
+        {
+            showChartResults();
+            //TBD Function


kiritigowda · 2019-05-11T00:16:45Z

apps/cloud_inference/client_app/inference_viewer.cpp

@@ -1011,7 +1048,7 @@ void inference_viewer::paintEvent(QPaintEvent *)
            imageRows = imageCount / numCols;
            imageCols = imageCount % numCols;
        }
-        // get received image/rate
+


keep comment

kiritigowda · 2019-05-11T00:19:56Z

apps/cloud_inference/client_app/perf_graph.ui

  <property name="windowTitle">
-   <string>Performance</string>
+   <string>AMD MIVisionX Performance</string>


AMD MIVisionX Inference - for 4 windows

kiritigowda · 2019-05-11T00:23:17Z

apps/cloud_inference/client_app/inference_receiver.cpp

@@ -244,6 +241,7 @@ void inference_receiver::run()
    if(progress->errorCode) {
        qDebug("inference_receiver::run() terminated: errorCode=%d", progress->errorCode);
    }
+    printf("hi1\n");


debug print

…nto H/perf_chart

kiritigowda · 2019-05-11T00:40:10Z

apps/cloud_inference/client_app/inference_receiver.cpp

@@ -225,7 +225,6 @@ void inference_receiver::run()
            }
            else {
                progress->errorCode = -1;
-                progress->message.sprintf("ERROR: got invalid command 0x%08x", cmd.command);


* nnir_to_openvx print (ROCm#103) * Ubuntu 18.04 warnings fix (ROCm#104) * Support for ONNX V1.3 (ROCm#101) ONNX 1.3 support for ResNet50 * adding grouped convolution and updating readme (ROCm#105) * Update README.md * Update convolution_layer.cpp * Loom Sample & Readme Updates (ROCm#106) * Loom Readme updates * Loom Samples Added * Samples Readme Updates * ROCm Version Updated * Readme updates (ROCm#107) * loom logo added * logo updates for loom * Samples readme updates * Main readme updates * WinML Readme updates * OpenVX Readme updates * loom readme updates * Apps readme updates * updates (ROCm#108) * Extensions readme updates * main readme update * loom readme updates * loom link updates * updates to loom * updates * Set up script updates * YoloV2 Fix (ROCm#109) * cloud inference updates (ROCm#111) * client app images added * Readme for Cloud Application * Cloud Inference Fix (ROCm#112) * Server Rename fix * Readme Link Fix * Client Readme updates * Server usage help added * Model Compiler Path Set * Model Compiler Scripts updated * Default Model Compiler Path Added * Server Readme fix * Cloud Inference readme fix * Server/Client bug fix * Cloud Inference Fix (ROCm#113) * Cloud Inference - Server Help (ROCm#114) * Cloud Inference Application - Graphs & Enhancements (ROCm#115) * graph added/polished * Update annInferenceApp.pro * Update inference_receiver.h * Update inference_viewer.cpp * Update inference_viewer.cpp * Update perf_graph.ui * Update inference_receiver.cpp * Title update * Update inference_receiver.cpp * onnx_to_nnir help text fix (ROCm#118) * bug fix * bug fix * bug fix * Update perf_chart.cpp * bug fix

* initial support for resize mirror normalize u8 variant * Add codes for Lanczos interpolation Add separable resampling support for lanczos Add generic kernel implementation Test suite changes Add support for different data types * Minor fix and changes * Minor changes * Minor fix - F16 PKD3 resize store * Minor fix Move the intermediate buffer allocation inside * update the store function used for pln3 case in rmn * added rmn support for all cases of u8 variant * added tensor avx2 support for RMN i8 variant * added tensor avx2 support for RMN F32, F16 variants * added RMN case to performance test suite * Add ci * Add ci * added base code for rmn hip PLN case * Changes for bicubic interpolation * added support for all input image types for RMN HIP kernel * removed usage of permute in store function to handle mirror case in RMN HOST functions * added RMN case in HIP performance test suites * code cleanup * Code clean up * Fix bilinear resize HOST * Fix padding issue resize bilinear * minor change in HIP PKD3 test suite * Fix padding issue with resize bilinear * changed from float4() to (float4) minor code cleanup * Minor changes * Code clean up * Code clean up - Variable name changes * Fix issue with resize bilinear PLN inputs * Replace RPPRANGECHECK with max and min * Add comments * Code clean up * made changes based on the latest resize codes * added fix for u8 to resolve low intensity values for first column in case of mirror * added condition check to do normalization for mean ! = 0 and stdDev != 1 added support to calculate src locations based on the roi values * added fix for low intensity values for RMN i8,f16,f32 variants * removed conditon check to break from the avx loop * minor changes * code cleanup * fixed the issue with rmn hip outputs made changes to accept 3 mean and 3 stddev values for normalization * minor changes * added 3 mean and 3 stddev support for RMN U8 HOST * added 3 mean and 3 stddev support for RMN I8,F16,F32 HOST * added helper function to convert pkd3 data to pln3 data in hip changed RMN PKD hip kernel to convert pkd values to pln values for normalization * experimental changes * minor changes * added fix to set non roi pixels as zero * added fix to set non-ROI pixels as 0 for RMN HIP * code cleanup * updated test cases for RMN performance tests * fixed bug in filling non ROI pixels as 0 for RMN HIP * minor code cleanup * minor change * added compute_rmn_24_host function * added u8 to f32 support for RMN HIP kernel * added macros for constants used in bilinear interpolation in rpp_cpu_common.hpp * fixed the incorrect mean and stddev issue values happening with hipMemcpy() for RMN HIP * added u8 to f32/f16 support for RMN Tensor HOST * made changes for mean and stddev values for pln1 case * reverted back incorrect changes happened with merge * updated description for resize mirror normalize * minor chnages to RMN HIP kernel * minor code cleanup * minor changes in test suite for resize mirror normalize * minor changes * Remove ci * Remove codacy warnings Co-authored-by: sampath1117 <sampath.rachumallu@multicorewareinc.com> Co-authored-by: fiona-gladwin <fionagladwin@multicorewareinc.com>

* remove jpegint.h dependancy * added libjpeg as dependancy for partial decoding * remove competitor ref from Readme

hansely123 added 2 commits May 10, 2019 17:11

graph added/polished

90493db

Merge remote-tracking branch 'upstream/master' into H/perf_chart

b58b423

kiritigowda reviewed May 11, 2019

View reviewed changes

apps/cloud_inference/client_app/annInferenceApp.pro Outdated Show resolved Hide resolved

kiritigowda reviewed May 11, 2019

View reviewed changes

Update annInferenceApp.pro

e46c07f

kiritigowda reviewed May 11, 2019

View reviewed changes

hansely123 added 4 commits May 10, 2019 17:23

Update inference_receiver.h

02ee285

Update inference_viewer.cpp

1bef788

Update inference_viewer.cpp

1432a40

Update perf_graph.ui

b2c375a

kiritigowda assigned hansely May 11, 2019

kiritigowda added bugfix Bug fixes to existing features enhancement New feature or request labels May 11, 2019

kiritigowda changed the title ~~H/perf chart~~ Cloud Inference Application - Graphs & Enhancements May 11, 2019

hansely123 added 3 commits May 10, 2019 17:36

Update inference_receiver.cpp

e1edaf6

Title update

2af563a

Merge branch 'H/perf_chart' of https://github.com/hansely/MIVisionX i…

04445e9

…nto H/perf_chart

kiritigowda reviewed May 11, 2019

View reviewed changes

Update inference_receiver.cpp

2accbdf

kiritigowda approved these changes May 11, 2019

View reviewed changes

kiritigowda merged commit 825064b into ROCm:master May 11, 2019

hansely deleted the H/perf_chart branch May 11, 2019 00:57

fiona-gladwin pushed a commit to fiona-gladwin/MIVisionX that referenced this pull request Jun 6, 2024

remove jpegint.h dependency from rocAL (ROCm#115)

78fae9a

* remove jpegint.h dependancy * added libjpeg as dependancy for partial decoding * remove competitor ref from Readme

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Cloud Inference Application - Graphs & Enhancements #115

Cloud Inference Application - Graphs & Enhancements #115

hansely commented May 11, 2019

kiritigowda May 11, 2019

kiritigowda May 11, 2019

kiritigowda May 11, 2019

kiritigowda May 11, 2019

kiritigowda May 11, 2019

kiritigowda May 11, 2019

kiritigowda May 11, 2019

kiritigowda May 11, 2019

kiritigowda May 11, 2019

Cloud Inference Application - Graphs & Enhancements #115

Cloud Inference Application - Graphs & Enhancements #115

Conversation

hansely commented May 11, 2019

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment