You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
"| `--img_dir` (`-d`) | `str` (required) | Path to your image directory. This can either be a folder of images **or** a dataset folder with a `data.yaml`. |\n",
255
255
"| `--model_path` (`-m`) | `str` (required) | Path to your YOLO ONNX model, created in Step 1. |\n",
256
256
"| `--num_imgs` (`-ni`) | `int` (default: `300`) | Number of images to use for quantization calibration. |\n",
257
-
"| `--disable_quantize` (`-dq`) | `bool` (default: `False`) | Set to `True` to skip quantization entirely, not recommended for performance. |\n",
257
+
"| `--disable_quantize` (`-dq`) | `bool` (default: `False`) | Set to `True` to skip quantization entirely. Not recommended for performance, and should not be used for deployment on PhotonVision, which requires quantization. |\n",
258
258
"| `--rknn_output` (`-o`) | `str` (default: `out.rknn`) | File path where the final RKNN model should be saved. |\n",
259
259
"| `--img_dataset_txt` (`-ds`) | `str` (default: `imgs.txt`) | File path to store the list of images used during quantization. |\n",
260
260
"| `--verbose` (`-vb`) | `bool` (default: `False`) | Enable detailed logging from the RKNN API during conversion. |\n",
261
261
"\n",
262
262
"\n",
263
263
"##### *Notes*\n",
264
264
"\n",
265
-
"1. This script is designed for use with [PhotonVision](https://photonvision.org), and by default sets the target platform for RKNN conversion to `RK3588`, a chipset commonly found in many variants of the Orange Pi 5 series (e.g., Orange Pi 5, 5 Pro, 5 Plus, 5 Max, etc.). You may modify the `TARGET_PLATFORM` value in the `create_onnx.py` script to match your specific hardware or deployment requirements if necessary.\n",
265
+
"1. This script is designed for use with [PhotonVision](https://photonvision.org), and by default sets the target platform for RKNN conversion to `RK3588`, a chipset commonly found in many variants of the Orange Pi 5 series (e.g., Orange Pi 5, 5 Pro, 5 Plus, 5 Max, etc.). You may modify the `DEFAULT_PLATFORM` value in the `create_rknn.py` script to match your specific hardware or deployment requirements if necessary.\n",
266
266
"\n",
267
267
"2. If you followed the Roboflow dataset download instructions from the previous section, the dataset will have been extracted to your **current working directory**. In that case, you can simply set `--img_dir` to \"`.`\" to reference the current directory."
0 commit comments