Example run and img2raw usage for a ResNet-50 model¶

For ONNX models:

$ python3 /opt/qti-aic/scripts/qaic-model-configurator/model_configurator.py resnet50.onnx onnx -iter 5000 -precision Int8 -list-configs -batchsize 1 -cores 2,7-12 -mos 2 -ols 2 -instance 2,7 -input-list-file inputs_res.txt

For an ONNX model with single device partitioning:

$ python3 /opt/qti-aic/scripts/qaic-model-configurator/model_configurator.py SsdResnet18_1MP.onnx onnx -iter 5000 -list-configs -batchsize 1 -cores 6 -mos 1,2,4,8 -ols 2,4 -instance 1 -input-list-file list.txt -width 224 -height 224 -reuse-single-file -enable-single-device-partitioning

To generate raw files from jpg/png images for different batch sizes, the img2raw Python script can be used. This script is imported by the model_configurator to generate raw files for different batch sizes from a provided image directory.

img2raw.py [-h] [-batchsize BATCH_SIZE] -image-dir IMAGE_DIR
                [-image-type {jpg,png}] -height IMGHEIGHT -width IMGWIDTH
                [-no-nhwc-conversion] [-no-normalize] [-fp32-to-int8]
                [-bgr-to-rgb] [-num-raw-files RAW_FILES_CNT]
                [-reuse-single-file] [-output OUTPUT]

                -h, --help show this help message and exit
                -batchsize BATCH_SIZE   Output batch size, default 1
                -image-dir IMAGE_DIR Input image directory
                -image-type {jpg,png} jpg (default) or png
                -height IMGHEIGHT output image height
                -width IMGWIDTH output image width
                -no-nhwc-conversion Disable conversion from NHWC to NCHW
                -no-normalize Disable Normalization
                -fp32-to-int8 Convert input from Fp32 to int8
                -bgr-to-rgb Convert from BGR to RGB
                -num-raw-files RAW_FILES_CNT  Number of raw files to generate default 1 (multiple of batchsize)
                -reuse-single-file If set will reuse same image for multiple batches
                -output OUTPUT Output Directory

Example img2raw.py

(Picks up four images from JPEGImages_dir, does scaling with provided width and height, NHWC>NCHW, normalization, and merges the buffers into a single raw image.)

$ python3 /opt/qti-aic/scripts/qaic-model-configurator/img2raw.py -image-dir JPEGImages_dir -height 124 -width 124 -batchsize 4

ls batch_size_4
    file-list.txt img_0.raw

The img2raw options are:

• -batchsize: Output batch size, default 1.

• -image-dir IMAGE_DIR: Input image directory. There could be any number of files in the image-dir (should be more than the batch size * num-raw-files).

• -image-type Type: Type of images in the image-dir (png/jpg).

• -height IMGHEIGHT, -width IMGWIDTH: Output image dimensions. Input images are scaled to these dimensions.

• -no-nhwc-conversion: Input images are expected in NHWC format and converted to NCHW. Add this flag to disable this conversion.

• -no-normalize: Disable normalization of images.

• -fp32-to-int8: Convert the output images in int8 format. (Disabled by default.)

• -bgr-to-rgb: Convert input images from BGR to RGB format. (Disabled by default.)

• -num-raw-files: How many raw files to generate (Default 1). Example: If -batchsize=8 and if 16 images are present in the directory, two raw files will be created. The image-dir should have at least batch size * num-raw-files files.

• -reuse-single-file: If set, will reuse the same image for generating multibatch raw files. Only a single image from the image-dir will be used.

• -output: Output directory where the files will be created. A text file is also created in the same directory with the names of the raw files generated.

• -letterbox-resize: Resize image as per letterbox logic.

• -normalize-255: Normalization by dividing image by 255.

• -iter: Number of iterations (iter) for which input file should be generated.