English

Common Algorithm Model Samples

Sample Location

The common algorithmic model samples are located at 02_preq_examples/, 03_classification/, 04_detection/ and 07_segmentation/ folders in the horizon_model_convert_sample path.

Prepare Datasets

Dataset Download Address

The dataset can be downloaded from the following address.

Dataset	Address
ImageNet	https://www.image-net.org/download.php
COCO	https://cocodataset.org/
VOC	http://host.robots.ox.ac.uk/pascal/VOC/ (need to download both versions 2007 and 2012)
Cityscapes	https://github.com/mcordts/cityscapesScripts
CIFAR-10	http://www.cs.toronto.edu/~kriz/cifar.html

Dataset Reference Structure

To facilitate your subsequent steps, after the dataset has been downloaded, you need to process the evaluation dataset according to the structure suggested by Horizon below.

Dataset	Description
ImageNet Dataset	We recommend that you unzip the downloaded dataset into the following structure. Please contact Horizon if you encounter any problems during data preparation. imagenet/ ├── calibration_data │ ├── ILSVRC2012_val_00000001.JPEG │ ├── ... │ └── ILSVRC2012_val_00000100.JPEG ├── ILSVRC2017_val.txt ├── val │ ├── ILSVRC2012_val_00000001.JPEG │ ├── ... │ └── ILSVRC2012_val_00050000.JPEG └── val.txt
COCO Dataset	We recommend that you unzip the downloaded dataset into the following structure. Please contact Horizon if you encounter any problems during data preparation. coco/ ├── calibration_data │ ├── COCO_val2014_000000181007.jpg │ ├── ... │ └── COCO_val2014_000000181739.jpg └── coco_val2017 ├── annotations │ ├── instances_train2017.json │ └── instances_val2017.json └── images ├── 000000000139.jpg ├── 000000000285.jpg ├── ... ├── 000000581615.jpg └── 000000581781.jpg
VOC Dataset	Attention Please note that the VOC2012 directory currently stores two datasets, VOC2007 and VOC2012, so please follow the directory structure below for the evaluation dataset. Please contact Horizon if you encounter any problems during data preparation. VOCdevkit/ └── VOC2012 ├── Annotations │ ├── 2007_000027.xml │ ├── ... │ └── 2012_004331.xml ├── ImageSets │ ├── Action │ │ ├── jumping_train.txt │ │ ├── jumping_trainval.txt │ │ ├── jumping_val.txt │ │ ├── ... │ │ ├── val.txt │ │ ├── walking_train.txt │ │ ├── walking_trainval.txt │ │ └── walking_val.txt │ ├── Layout │ │ ├── train.txt │ │ ├── trainval.txt │ │ └── val.txt │ ├── Main │ │ ├── aeroplane_train.txt │ │ ├── aeroplane_trainval.txt │ │ ├── aeroplane_val.txt │ │ ├── ... │ │ ├── train.txt │ │ ├── train_val.txt │ │ ├── trainval.txt │ │ ├── tvmonitor_train.txt │ │ ├── tvmonitor_trainval.txt │ │ ├── tvmonitor_val.txt │ │ └── val.txt │ └── Segmentation │ ├── train.txt │ ├── trainval.txt │ └── val.txt ├── JPEGImages │ ├── 2007_000027.jpg │ ├── ... │ └── 2012_004331.jpg ├── SegmentationClass │ ├── 2007_000032.png │ ├── ... │ └── 2011_003271.png ├── SegmentationObject │ ├── 2007_000032.png │ ├── ... │ └── 2011_003271.png └── train.txt
Citys capes Dataset	We recommend that you unzip the downloaded dataset into the following structure. Please contact Horizon if you encounter any problems during data preparation. cityscapes/ ├── cityscapes_calibration_data │ ├── aachen_000000_000019_leftImg8bit.png │ ├── ... │ └── aachen_000099_000019_leftImg8bit.png ├── gtFine │ ├── test │ │ ├── berlin │ │ ├── ... │ │ └── munich │ ├── train │ │ ├── aachen │ │ ├── ... │ │ └── zurich │ └── val │ ├── frankfurt │ ├── lindau │ └── munster ├── leftImg8bit │ ├── test │ │ ├── berlin │ │ ├── ... │ │ └── munich │ ├── train │ │ ├── aachen │ │ ├── ... │ │ └── munich │ └── val │ ├── frankfurt │ ├── lindau │ └── munster ├── license.txt └── README
CIF AR-10 Dataset	We recommend that you unzip the downloaded dataset into the following structure. Please contact Horizon if you encounter any problems during data preparation. cifar-10/ ├── batches.meta ├── cifar10_val.txt ├── data_batch_1 ├── data_batch_2 ├── data_batch_3 ├── data_batch_4 ├── data_batch_5 ├── readme.html └── test_batch

Prepare Models

When using the model conversion sample package, please prepare the corresponding floating-point model first.

Note

If you need to do this process in the sample folder, you need to execute the 00_init.sh script in the folder first to get the corresponding original model and dataset.

Sources and modifications (if any) of the original models, please refer to below subsections.

MobileNetv1

model source: https://github.com/shicai/MobileNet-Caffe
md5sum code:

md5sum File
3fd6889ec48bda46451d67274144e2a8 mobilenet.caffemodel
8922f90f629d428fecf866e798ac7c08 mobilenet_deploy.prototxt

md5sum	File
3fd6889ec48bda46451d67274144e2a8	mobilenet.caffemodel
8922f90f629d428fecf866e798ac7c08	mobilenet_deploy.prototxt

MobileNetv2

model source: https://github.com/shicai/MobileNet-Caffe
md5sum code:

md5sum File
54aab8425ea068d472e8e4015f22360c mobilenet_v2.caffemodel
13101ee86ab6d217d5fd6ed46f7a4faa mobilenet_v2_deploy.prototxt

md5sum	File
54aab8425ea068d472e8e4015f22360c	mobilenet_v2.caffemodel
13101ee86ab6d217d5fd6ed46f7a4faa	mobilenet_v2_deploy.prototxt

ResNet50

model source: https://pytorch.org/vision/main/models/generated/torchvision.models.resnet50.html
md5sum code:

md5sum File
ebaeb70c972d1a3e6eb06c0e1541eeb4 resnet50.onnx

md5sum	File
ebaeb70c972d1a3e6eb06c0e1541eeb4	resnet50.onnx

GoogleNet

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/GoogleNet
md5sum code:

md5sum File
f107ae6806ea1016afbc718210b7a617 googlenet.onnx

md5sum	File
f107ae6806ea1016afbc718210b7a617	googlenet.onnx

EfficientNet_Lite0/1/2/3/4

Attention

To quickly start running samples and avoid the risks caused by third party tools, we strongly recommend using the off-the-shelf ONNX model in the model_zoo/mapper/ directory in Horizon model release package. If you are interested in reproducing the model conversion process of tflite2onnx, you can still try using the below 3rd-party tool, however, we do not guarantee the quality and success of the conversion.

model source: obtain the TAR package from https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite

md5sum of the converted ONNX models in Horizon model_zoo:

md5sum	File
001a329bd367fbec22b415c7a33d7bdb	efficientnet_lite0_fp32.onnx
1205e95aea66650c71292bde236d55a9	efficientnet_lite1_fp32.onnx
474741c15494b79a89fe51d89e0c43c7	efficientnet_lite2_fp32.onnx
550455b41848d333f8359279c89a6bae	efficientnet_lite3_fp32.onnx
bde7fe57eadb4a30ef76f68da622dcd5	efficientnet_lite4_fp32.onnx

Download and get .tflite from the TAR package, and then convert it to an ONNX model using the tflite2onnx tool (https://pypi.org/project/tflite2onnx/).

Note that model layouts may vary by tflite2onnx version. If the input layout of the converted ONNX model is NHWC, when building, the configure input_layout_train of the EfficientNet_Lite0/1/2/3/4 should be NHWC.

Vargconvnet

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/VargConvNet
md5sum code:

md5sum File
e21b8db17916f9046253bbe0bb8de3ef vargconvnet.onnx

md5sum	File
e21b8db17916f9046253bbe0bb8de3ef	vargconvnet.onnx

Efficientnasnet_m

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/EfficientnasNet
md5sum code:

md5sum File
fc36c052c6f034c0b64a6197b91b0c62 efficientnasnet-m.onnx

md5sum	File
fc36c052c6f034c0b64a6197b91b0c62	efficientnasnet-m.onnx

Efficientnasnet_s

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/EfficientnasNet
md5sum code:

md5sum File
e2744bd748f4265f4488676835a6ca24 efficientnasnet-s.onnx

md5sum	File
e2744bd748f4265f4488676835a6ca24	efficientnasnet-s.onnx

ResNet18

model source: https://pytorch.org/vision/main/models/generated/torchvision.models.resnet18.html
md5sum code:

md5sum File
62de4ff68317c65ab4bb6a451e719e6d resnet18.onnx

md5sum	File
62de4ff68317c65ab4bb6a451e719e6d	resnet18.onnx

YOLOv2_Darknet19

Attention

To quickly start running samples and avoid the risks caused by third party tools, we strongly recommend using the off-the-shelf Caffe model in the model_zoo/mapper/ directory in Horizon model release package. If you are interested in reproducing the model conversion process of darknet2caffe, you can still try using the below 3rd-party tool, however, we do not guarantee the quality and success of the conversion.
To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

To get YOLOv2_Darknet19, first download the .cfg and .weight files of YOLOv2 608x608 from YOLO's official website (https://pjreddie.com/darknet/yolo/) and convert it to a Caffe model using the darknet2caffe conversion tool (https://github.com/xingyanan/darknet2caffe).

Note

As this conversion tool is a simplified version, you should modify the .prototxt file generated by this tool before the conversion, change the 'Reshape' layer to 'Passthrough' layer, and then add an NCHW2NHWC Permute operation to the output node.

For details about the parameters of the modified Passthrough layer, refer to the yolov2.prototxt sample.

2.md5sum code:

md5sum	File
7aa7a6764401cebf58e73e72fcbd2a45	yolov2.caffemodel
72e9a51c1e284e4b66e69f72ca9214c8	yolov2_transposed.prototxt

YOLOv3_Darknet53

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

YOLOv3_Darknet53 model:

URL: https://github.com/ChenYingpeng/caffe-yolov3/ .

The caffemodel file can be downloaded from the Baidu Cloud URL provided in the README.md file in GitHub, in which you should add an NCHW2NHWC Permute operation to the output node.

md5sum code:

md5sum File
935af6e1530af5c0017b3674adce95e9 yolov3_transposed.prototxt
9a0f09c850656913ec27a6da06d9f9cc yolov3.caffemodel

md5sum	File
935af6e1530af5c0017b3674adce95e9	yolov3_transposed.prototxt
9a0f09c850656913ec27a6da06d9f9cc	yolov3.caffemodel

YOLOv5x

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

YOLOv5x model: Download the corresponding pt file from https://github.com/ultralytics/yolov5/releases/tag/v2.0

Important

When cloning the source code, be sure to use [v2.0] tags, otherwise the conversion may fail.

md5sum code:

md5sum File
2e296b5e31bf1e1b6b8ea4bf36153ea5 yolov5l.pt
16150e35f707a2f07e7528b89c032308 yolov5m.pt
42c681cf466c549ff5ecfe86bcc491a0 yolov5s.pt
069a6baa2a741dec8a2d44a9083b6d6e yolov5x.pt

md5sum	File
2e296b5e31bf1e1b6b8ea4bf36153ea5	yolov5l.pt
16150e35f707a2f07e7528b89c032308	yolov5m.pt
42c681cf466c549ff5ecfe86bcc491a0	yolov5s.pt
069a6baa2a741dec8a2d44a9083b6d6e	yolov5x.pt

To better adapt to post-processing code, before exporting the ONNX model, we modified the code at Github as follows (for more code details see: https://github.com/ultralytics/yolov5/blob/v2.0/models/yolo.py):

def forward(self, x):
    # x = x.copy()  # for profiling
    z = []  # inference output
    self.training |= self.export
    for i in range(self.nl):
        x[i] = self.m[i](x[i])  # conv
        bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
        #  x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
        x[i] = x[i].permute(0, 2, 3, 1).contiguous()

Note

Remove the reshape from 4D to 5D at the end of each output branch (i.e., not splitting the channel from 255 to 3x85), then convert the layout from NHWC to NCHW before dumping.

The bottom left image displays the visualization of a certain output node before modifying the model, while the bottom right image displays the visualization of the corresponding output node after the modification.

After download, perform the pt to ONNX file conversion using the script https://github.com/ultralytics/yolov5/blob/v2.0/models/export.py .

Attention

When using the export.py script:

Because Horizon algorithm toolchain only supports ONNX opset [10] ~ [19], please modify the opset_version parameter in the torch.onnx.export as per the version you use.
Change the default input name parameter in the torch.onnx.export from 'image' into 'data' to keep it consistent with that of in the YOLOv5s sample in the model conversion sample package.
Change the default data input size in the parser.add_argument from 640x640 to 672x672 as in the YOLOv5x sample in the model conversion sample package.

SSD_MobileNetv1

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

SSD_MobileNetv1 model: Obtain the Caffe model from URL: https://github.com/chuanqi305/MobileNet-SSD
md5sum code:

md5sum File
bbcb3b6a0afe1ec89e1288096b5b8c66 mobilenet_iter_73000.caffemodel
3c230e4415195a50c6248be80c49882d MobileNetSSD_deploy.prototxt

md5sum	File
bbcb3b6a0afe1ec89e1288096b5b8c66	mobilenet_iter_73000.caffemodel
3c230e4415195a50c6248be80c49882d	MobileNetSSD_deploy.prototxt

Efficientdetd0

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/EfficientDet
md5sum code:

md5sum File
ec4129c4b300cd04f1e8f71e0fe54ca5 efficientdet_nhwc.onnx

md5sum	File
ec4129c4b300cd04f1e8f71e0fe54ca5	efficientdet_nhwc.onnx

CenterNet_Resnet101

Attention

To achieve optimal on-board performance:

We put the maxpool and sigmoid nodes into the model and specify them to be compiled as BPU nodes for reducing the amount of computation during post-processing.
We modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/Centernet
md5sum code:

md5sum File
db195ff784792f475e573c5126401d2a centernet_resnet101_coco_modify.onnx

md5sum	File
db195ff784792f475e573c5126401d2a	centernet_resnet101_coco_modify.onnx

Fcos_efficientnetb0

Attention

This model is a trained model using the PTQ method.
To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/blob/master/Fcos_Efficientnetb0
md5sum code:

md5sum File
9f9a1fe8508e2bd068e70146eb559b4f fcos_efficientnetb0.onnx

md5sum	File
9f9a1fe8508e2bd068e70146eb559b4f	fcos_efficientnetb0.onnx

Yolov4

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/YoloV4
md5sum code:

md5sum File
aaa3c3e5e4c4c1d4830b6501b1720e4d yolov4_efficientnetb0.onnx

md5sum	File
aaa3c3e5e4c4c1d4830b6501b1720e4d	yolov4_efficientnetb0.onnx

YOLOv3_VargDarknet

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

YOLOv3_VargDarknet model

URL: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/Yolov3_VargDarknet . The model file can be downloaded from the Baidu Cloud URL provided in the README.md file in GitHub.

md5sum code:

md5sum File
fd4e46bc7c9798b51778d3aa09c5053a yolov3_vargdarknet53.onnx

md5sum	File
fd4e46bc7c9798b51778d3aa09c5053a	yolov3_vargdarknet53.onnx

Fcos_resnet50

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/Fcos_Resnet50
md5sum code:

md5sum File
0218942777615fac2f54cefdac4fbfa7 fcos_resnet50.onnx

md5sum	File
0218942777615fac2f54cefdac4fbfa7	fcos_resnet50.onnx

Fcos_resnext101

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/Fcos_Resnext101
md5sum code:

md5sum File
4b80efd22448021721ac5a860909c59f fcos_resnext101.onnx

md5sum	File
4b80efd22448021721ac5a860909c59f	fcos_resnext101.onnx

Unet_mobilenet

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Dequantize node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/MobilenetUnet
md5sum code:

md5sum File
21c6c645ebca92befbebc8c39d385c1e tf_unet_trained.onnx

md5sum	File
21c6c645ebca92befbebc8c39d385c1e	tf_unet_trained.onnx

DeeplabV3plus_efficientnetb0

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Reshape and Cast node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus
md5sum code:

md5sum File
cf3a683f31b4b0ebe090647729f869d9 deeplabv3plus_efficientnetb0.onnx

md5sum	File
cf3a683f31b4b0ebe090647729f869d9	deeplabv3plus_efficientnetb0.onnx

Fastscnn_efficientnetb0

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Reshape and Cast node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/FastSCNN
md5sum code:

md5sum File
c1ace8f08a9c7b9c91509fa68327d0c8 fastscnn_efficientnetb0.onnx

md5sum	File
c1ace8f08a9c7b9c91509fa68327d0c8	fastscnn_efficientnetb0.onnx

Deeplabv3plus_dilation1248

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Transpose node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus
md5sum code:

md5sum File
ad002e572cbb49e1e99d893aac69f3e3 deeplabv3_cityscapes_dila1248_permute.onnx

md5sum	File
ad002e572cbb49e1e99d893aac69f3e3	deeplabv3_cityscapes_dila1248_permute.onnx

Deeplabv3plus_efficientnetm1

Attention

To achieve optimal on-board performance, we modified the remove_node_type parameter in the YAML file used for hbm model compilation and removed the Reshape, Cast, and Transpose node from the hbm model.

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus
md5sum code:

md5sum File
0a1dfd01e173c68630d9e8dc1a6036fe deeplabv3plus_efficientnetm1.onnx

md5sum	File
0a1dfd01e173c68630d9e8dc1a6036fe	deeplabv3plus_efficientnetm1.onnx

Deeplabv3plus_efficientnetm2

Attention

model source: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus
md5sum code:

md5sum File
c11a2673c4b3cf6e5d7bf1a051925d38 deeplabv3plus_efficientnetm2.onnx

md5sum	File
c11a2673c4b3cf6e5d7bf1a051925d38	deeplabv3plus_efficientnetm2.onnx

Demo Of Algorithm Model Samples

Taking the GoogleNet model as an example, This section illustrates the steps of floating-point to fixed-point model conversion by using the scripts in 03_classification/04_googlenet/.

Docker Container Prep

First complete the docker installation and configuration and enter the docker container accoridng to Docker Container Deployment .

Obtain The Original Model And Calibration Dataset

Execute 00_init.sh in the 03_classification/04_googlenet/ folder to obtain the model and calibration dataset needed for the current sample.

# 1. Enter the folder the demo script resides
cd samples/ai_toolchain/horizon_model_convert_sample/03_classification/04_googlenet/
# 2. Execute the script to obtain the original model and calibration dataset
sh 00_init.sh

Check If the Model is Executable

1.Run the script as follows:

# Execute model checking
sh 01_check.sh

2.Output the model inspection result:

Use the hb_compile tool to check whether the model can be supported by Horizon ASIC.

Prepare Calibration Dataset

Run the 02_preprocess.sh script in the same directory, as follows:

# Convert the images in 01_common/data/imagenet/calibration_data
# to: ./calibration_data_rgb_f32
sh 02_preprocess.sh

Note

We extracted 100 images from the ImageNet dataset and use them as a calibration dataset. Before calibration, we pre-processed the data and convert short size resize/crop size/NHWC to NCHW/to rgb.
The hb_compile tool will load data from the converted binary data, the format of the pre-processed binary data file is npy, the dtype is unit8.

Building Heterogeneous Models

Run the 03_build.sh script in the same directory, as follows:

sh 03_build.sh

Note

The above script uses the hb_compile tool to convert the model. The most important thing to focus on is the conversion configuration file, refer to Model Quantized Compilation section.

The output of the above script is as follows:

ls model_output | cat
googlenet_224x224_nv12.hbm
googlenet_224x224_nv12_calibrated_model.onnx
googlenet_224x224_nv12_ptq_model.onnx
googlenet_224x224_nv12_optimized_float_model.onnx
googlenet_224x224_nv12_original_float_model.onnx
googlenet_224x224_nv12_quantized_model.bc
googlenet_224x224_nv12.html
googlenet_224x224_nv12.json 
googlenet_224x224_nv12_quant_info.json 
googlenet_224x224_nv12_advice.json
googlenet_224x224_nv12_node_info.csv

Note

For now you ONLY need to focus on the googlenet_224x224_nv12.hbm file.

Single Image Inference

Run the 04_inference.sh script to inference a single image, as follows:

sh 04_inference.sh

Note

As image pre-processing, model data post-processing are required in the image inference, we offered a Python sample script, please refer to sh 04_inference.sh.
This script is to perform the inference against a single image and verify whether the inference result meets the expectations. If you want to perform accuracy evaluation, refer to the script 05_evaluate.sh.

Accuracy Evaluation

Run the 05_evaluate.sh script to evaluate the accuracy, as follows:

export PARALLEL_PROCESS_NUM=${parallel_process_num}
sh 05_evaluate.sh

Note

As image pre-processing, model data post-processing are required in accuracy evaluation, awe offered a Python sample script, please refer to sh 05_evaluate.sh.
To accelerate the evaluation, you can adjust the number of concurrent processes by using the -p option; meanwhile, pay attention to the memory usage. When the value of the -p option is set to 0 or left unfilled, the fixed-point models in the CPU environment will be processed by 10 processes, while other scenarios using 1 process.

FAQ

Why is the reproduced accuracy slightly different from the indicators in the documentation?

There are two possible reasons:

There may be minor differences in calculation methods when in different server environments, which can cause small data fluctuations in the accuracy of the compiled fixed-point ONNX models in different server environments when compared with the documentation.
The user side uses different versions of third-party libraries such as OpenCV and NumPy, which may produce different results after pre-processing, and this may also lead to slight data fluctuations in reproduced accuracy when compared with the documentation.

No need to worry much about this situation, the records provided in the documentation is only for reference, and it is ok that your reproduced accuracy is slightly different from those in documents.

Why is the fixed-point model accuracy not aligned with the on-board accuracy of the hbm file in the ai_benchmark example?

In the standard delivery, when adding the example, we have already aligned the fixed-point model accuracy with the hbm on-board accuracy in the ai_benchmark example.

If you find any unaligned accuracy, we recommend you first checking the model input for consistency.

When executing the fixed-point model evaluation script, you use the dataset of image type, while for the hbm model used on board, you use the binary dataset converted by the hb_eval_preprocess tool.

Based on this, if the dataset you used on-board is not generated by using the above methods, we recommend that you first use our data preprocessing tool (i.e., hb_eval_preprocess) to regenerate the dataset needed for on-board running on the same server that you run the fixed-point model accuracy and rerun the on-board accuracy to ensure the model inputs are consistent.

Attention

Make sure to use the same environment to generate the dataset by using the hb_eval_preprocess tool and to run the fixed-point model accuracy.

On This Page

The hb_compile Tool

QAT

Model Export

Horizon Operator

Vision Algorithm

Sample

VP API Introduction

Data Structure

Function Interface

Model Inference API Introduction

Data Type and Data Structure

API Interface

Model Inference Tool Introduction

High Performance Algorithm

HPL API Introduction

Data Structure

Functional Interface

Data Structure

Functional Interface

FRAMEWORK

TUTORIALS

EXAMPLES

API REFERENCE

#Common Algorithm Model Samples

#Sample Location

#Prepare Datasets

#Dataset Download Address

#Dataset Reference Structure

#Prepare Models

#MobileNetv1

#MobileNetv2

#ResNet50

#GoogleNet

#EfficientNet_Lite0/1/2/3/4

#Vargconvnet

#Efficientnasnet_m

#Efficientnasnet_s

#ResNet18

#YOLOv2_Darknet19

#YOLOv3_Darknet53

#YOLOv5x

#SSD_MobileNetv1

#Efficientdetd0

#CenterNet_Resnet101

#Fcos_efficientnetb0

#Yolov4

#YOLOv3_VargDarknet

#Fcos_resnet50

#Fcos_resnext101

#Unet_mobilenet

#DeeplabV3plus_efficientnetb0

#Fastscnn_efficientnetb0

#Deeplabv3plus_dilation1248

#Deeplabv3plus_efficientnetm1

#Deeplabv3plus_efficientnetm2

#Demo Of Algorithm Model Samples

#Docker Container Prep

#Obtain The Original Model And Calibration Dataset

#Check If the Model is Executable

#Prepare Calibration Dataset

#Building Heterogeneous Models

#Single Image Inference

#Accuracy Evaluation

#FAQ

#Why is the reproduced accuracy slightly different from the indicators in the documentation?

#Why is the fixed-point model accuracy not aligned with the on-board accuracy of the hbm file in the ai_benchmark example?

Common Algorithm Model Samples

Sample Location

Prepare Datasets

Dataset Download Address

Dataset Reference Structure

Prepare Models

MobileNetv1

MobileNetv2

ResNet50

GoogleNet

EfficientNet_Lite0/1/2/3/4

Vargconvnet

Efficientnasnet_m

Efficientnasnet_s

ResNet18

YOLOv2_Darknet19

YOLOv3_Darknet53

YOLOv5x

SSD_MobileNetv1

Efficientdetd0

CenterNet_Resnet101

Fcos_efficientnetb0

Yolov4

YOLOv3_VargDarknet

Fcos_resnet50

Fcos_resnext101

Unet_mobilenet

DeeplabV3plus_efficientnetb0

Fastscnn_efficientnetb0

Deeplabv3plus_dilation1248

Deeplabv3plus_efficientnetm1

Deeplabv3plus_efficientnetm2

Demo Of Algorithm Model Samples

Docker Container Prep

Obtain The Original Model And Calibration Dataset

Check If the Model is Executable

Prepare Calibration Dataset

Building Heterogeneous Models

Single Image Inference

Accuracy Evaluation

FAQ

Why is the reproduced accuracy slightly different from the indicators in the documentation?

Why is the fixed-point model accuracy not aligned with the on-board accuracy of the hbm file in the ai_benchmark example?