mivisionx-inference-analyzer

MIVisionX Python Inference Analyzer uses pre-trained ONNX/NNEF/Caffe models to analyze inference results and summarize individual image results

MIVisionX Python Inference Analyzer

MIVisionX Inference Analyzer Application uses pre-trained ONNX/NNEF/Caffe models to analyze inference results and summarize images.

Pre-trained models in ONNX, NNEF, & Caffe formats are supported by MIVisionX. The app first converts the pre-trained models to AMD Neural Net Intermediate Representation (NNIR), once the model has been translated into AMD NNIR (AMD’s internal open format), the Optimizer goes through the NNIR and applies various optimizations which would allow the model to be deployed on to target hardware most efficiently. Finally, AMD NNIR is converted into OpenVX C code, which is compiled and wrapped with a python API to run on any targeted hardware.

MIVisionX Inference Analyzer - Processing Images

MIVisionX Inference Analyzer - Processing Images Complete

MIVisionX Inference Analyzer - Results

Analyzer Index

MIVisionX Model Compiler & Optimizer
Prerequisites
- Docker for MIVisionX Inference Analyzer
Usage
- Usage help
Supported Pre-Trained Model Formats
Samples

Prerequisites

Ubuntu 16.04/18.04 or CentOS 7.5/7.6
ROCm supported hardware
- AMD Radeon GPU or AMD APU required
Latest ROCm
Build & Install MIVisionX

Use MIVisionX Docker

MIVisionX provides developers with docker images for Ubuntu 16.04, Ubuntu 18.04, CentOS 7.5, & CentOS 7.6. Using docker images developers can quickly prototype and build applications without having to be locked into a single system setup or lose valuable time figuring out the dependencies of the underlying software.

Docker with display option

Check docker prerequisites

Start docker with display

% sudo docker pull mivisionx/ubuntu-16.04:latest
% xhost +local:root
% sudo docker run -it --device=/dev/kfd --device=/dev/dri --cap-add=SYS_RAWIO --device=/dev/mem --group-add video --network host --env DISPLAY=unix$DISPLAY --privileged --volume $XAUTH:/root/.Xauthority --volume /tmp/.X11-unix/:/tmp/.X11-unix mivisionx/ubuntu-16.04:latest

Test display with MIVisionX sample

% export PATH=$PATH:/opt/rocm/mivisionx/bin
% export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/rocm/mivisionx/lib
% runvx /opt/rocm/mivisionx/samples/gdf/canny.gdf

Run Samples

Usage

Command Line Interface (CLI)

usage: python mivisionx_inference_analyzer.py 	[-h/--help] 
                             	       		--model_format MODEL_FORMAT 
                                       		--model_name MODEL_NAME 
                                       		--model MODEL 
                                       		--model_input_dims MODEL_INPUT_DIMS 
                                       		--model_output_dims MODEL_OUTPUT_DIMS 
                                       		--label LABEL 
                                       		--output_dir OUTPUT_DIR 
                                       		--image_dir IMAGE_DIR
                                       		[--image_val IMAGE_VAL] 
                                       		[--hierarchy HIERARCHY]
                                       		[--add ADD] 
                                       		[--multiply MULTIPLY]
				       		[--fp16 FP16]
						[--resize_option RESIZE_OPTION]
						[--display_option DISPLAY_OPTION]
                                       		[--replace REPLACE] 
                                       		[--verbose VERBOSE]

Usage help

  -h, --help            show this help message and exit
  --model_format        pre-trained model format, options:caffe/onnx/nnef [required]
  --model_name          model name                                        [required]
  --model               pre_trained model file/folder                     [required]
  --model_input_dims    c,h,w - channel,height,width                      [required]
  --model_output_dims   c,h,w - channel,height,width                      [required]
  --label               labels text file                                  [required]
  --output_dir          output dir to store ADAT results                  [required]
  --image_dir           image directory for analysis                      [required]
  --image_val           image list with ground truth                      [optional]
  --hierarchy           AMD proprietary hierarchical file                 [optional]
  --add                 input preprocessing factor      [optional - default:[0,0,0]]
  --multiply            input preprocessing factor      [optional - default:[1,1,1]]
  --fp16                quantize model to FP16 		     [optional - default:no]
  --resize_option       image resize interpolation [optional - default:0 range[0-5]]
  --display_option      application display option [optional - default:1 range[0-2]]
  --replace             replace/overwrite model              [optional - default:no]
  --verbose             verbose                              [optional - default:no]

Input Image Resize Interpolation Options

0: INTER_LINEAR 	- Default CV Resize Interpolation
1: INTER_NEAREST 	– a nearest-neighbor interpolation
2: INTER_LINEAR 	– a bilinear interpolation (used by default)
3: INTER_AREA 		– a resampling using pixel area relation. 
			  It may be a preferred method for image decimation, 
			  as it gives moire’-free results. But when the image is zoomed, 
			  it is similar to the INTER_NEAREST method.
4: INTER_CUBIC 		– a bicubic interpolation over 4×4 pixel neighborhood
5: INTER_LANCZOS4 	– a Lanczos interpolation over 8×8 pixel neighborhood

Display Option

OFF 	- Application Display Turn Off
MIN 	– Display Progress Window
ALL 	– Display Input Image, Image Results, & Progress Window

Graphical User Interface (GUI)

usage: python mivisionx_inference_analyzer.py

Supported Pre-Trained Model Formats

Caffe
NNEF
ONNX

Samples

Sample 1 - Using Pre-Trained ONNX Model

Run SqueezeNet on sample images

Step 1: Clone MIVisionX Inference Analyzer Project
```
  % cd && mkdir sample-1 && cd sample-1
  % git clone https://github.com/kiritigowda/MIVisionX-inference-analyzer.git
```
Note:
- MIVisionX needs to be pre-installed
- MIVisionX Model Compiler & Optimizer scripts are at /opt/rocm/mivisionx/model_compiler/python/
- ONNX model conversion requires ONNX install using pip install onnx
Step 2: Download pre-trained SqueezeNet ONNX model from ONNX Model Zoo - SqueezeNet Model
```
  % wget https://s3.amazonaws.com/download.onnx/models/opset_8/squeezenet.tar.gz
  % tar -xvf squeezenet.tar.gz
```
Note: pre-trained model - squeezenet/model.onnx

Step 3: Use the command below to run the inference analyzer

View inference analyzer usage

  % cd ~/sample-1/MIVisionX-inference-analyzer/
  % python mivisionx_inference_analyzer.py -h

Run SqueezeNet Inference Analyzer

  % python mivisionx_inference_analyzer.py --model_format onnx --model_name SqueezeNet --model ~/sample-1/squeezenet/model.onnx --model_input_dims 3,224,224 --model_output_dims 1000,1,1 --label ./sample/labels.txt --output_dir ~/sample-1/ --image_dir ./sample/AMD-tinyDataSet --image_val ./sample/AMD-tinyDataSet-val.txt --hierarchy ./sample/hierarchy.csv --replace yes

Sample 2 - Using Pre-Trained Caffe Model

Run VGG 16 on sample images

Step 1: Clone MIVisionX Inference Analyzer Project
```
  % cd && mkdir sample-2 && cd sample-2
  % git clone https://github.com/kiritigowda/MIVisionX-inference-analyzer.git
```
Note:
- MIVisionX needs to be pre-installed
- MIVisionX Model Compiler & Optimizer scripts are at /opt/rocm/mivisionx/model_compiler/python/

Step 2: Download pre-trained VGG 16 caffe model - VGG_ILSVRC_16_layers.caffemodel

  % wget http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel

Step 3: Use the command below to run the inference analyzer

View inference analyzer usage

  % cd ~/sample-2/MIVisionX-inference-analyzer/
  % python mivisionx_inference_analyzer.py -h

Run VGGNet-16 Inference Analyzer

  % python mivisionx_inference_analyzer.py --model_format caffe --model_name VggNet-16-Caffe --model ~/sample-2/VGG_ILSVRC_16_layers.caffemodel --model_input_dims 3,224,224 --model_output_dims 1000,1,1 --label ./sample/labels.txt --output_dir ~/sample-2/ --image_dir ./sample/AMD-tinyDataSet --image_val ./sample/AMD-tinyDataSet-val.txt --hierarchy ./sample/hierarchy.csv --replace yes

Sample 3 - Using Pre-Trained NNEF Model

Run VGG 16 on sample images

Step 1: Clone MIVisionX Inference Analyzer Project
```
  % cd && mkdir sample-3 && cd sample-3
  % git clone https://github.com/kiritigowda/MIVisionX-inference-analyzer.git
```
Note:
- MIVisionX needs to be pre-installed
- MIVisionX Model Compiler & Optimizer scripts are at /opt/rocm/mivisionx/model_compiler/python/
- NNEF model conversion requires NNEF python parser installed

Step 2: Download pre-trained VGG 16 NNEF model

  % mkdir ~/sample-3/vgg16
  % cd ~/sample-3/vgg16
  % wget https://sfo2.digitaloceanspaces.com/nnef-public/vgg16.onnx.nnef.tgz
  % tar -xvf vgg16.onnx.nnef.tgz

Step 3: Use the command below to run the inference analyzer

View inference analyzer usage

  % cd ~/sample-3/MIVisionX-inference-analyzer/
  % python mivisionx_inference_analyzer.py -h

Run VGGNet-16 Inference Analyzer

  % python mivisionx_inference_analyzer.py --model_format nnef --model_name VggNet-16-NNEF --model ~/sample-3/vgg16/ --model_input_dims 3,224,224 --model_output_dims 1000,1,1 --label ./sample/labels.txt --output_dir ~/sample-3/ --image_dir ./sample/AMD-tinyDataSet --image_val ./sample/AMD-tinyDataSet-val.txt --hierarchy ./sample/hierarchy.csv --replace yes

Preprocessing the model: Use the –add/–multiply option to preprocess the input images

  % python mivisionx_inference_analyzer.py --model_format nnef --model_name VggNet-16-NNEF --model ~/sample-3/vgg16/ --model_input_dims 3,224,224 --model_output_dims 1000,1,1 --label ./sample/labels.txt --output_dir ~/sample-3/ --image_dir ./sample/AMD-tinyDataSet --image_val ./sample/AMD-tinyDataSet-val.txt --hierarchy ./sample/hierarchy.csv --replace yes --add [-2.1179,-2.0357,-1.8044] --multiply [0.0171,0.0175,0.0174]