1# The ImageTensorGenerator 2 3The `ImageTensorGenerator` is a program for pre-processing a .jpg image before generating a .raw tensor file from it. 4 5Build option: 6To build ModelAccuracyTool, pass the following options to Cmake: 7* -DBUILD_ACCURACY_TOOL=1 8 9|Cmd:||| 10| ---|---|---| 11| -h | --help | Display help messages | 12| -f | --model-format | Format of the intended model file that uses the images.Different formats have different image normalization styles.Accepted values (tflite) | 13| -i | --infile | Input image file to generate tensor from | 14| -o | --outfile | Output raw tensor file path | 15| -z | --output-type | The data type of the output tensors.If unset, defaults to "float" for all defined inputs. Accepted values (float, int or qasymm8) 16| | --new-width |Resize image to new width. Keep original width if unspecified | 17| | --new-height | Resize image to new height. Keep original height if unspecified | 18| -l | --layout | Output data layout, "NHWC" or "NCHW". Default value: NHWC | 19 20Example usage: <br> 21<code>./ImageTensorGenerator -i /path/to/image/dog.jpg -o /output/path/dog.raw --new-width 224 --new-height 224</code>
