What value should be included in the --cal_image_dir argument in INT8 mode in yolov4 exporting the Model?
I don’t know what directory to put in the required argument --cal_image_dir when export etlt model to INT8 mode.
And i gave --cal_data_file /export/cal.tensorfile, but nothing was created.
I wonder if the tensorfile is not created originally or if etlt is not created incorrectly.
This is full Log and command
!tlt yolo_v4 export \
-m /workspace/tlt3/210521_darknet19_test/train1_pruned/yolov4_darknet19_epoch_064_pruned1_03.tlt \
-e /workspace/tlt3/210521_darknet19_test/resume_train_darknet19.txt \
-o /workspace/tlt3/210521_darknet19_test/etlt/yolov4_darknet19_epoch_064_pruned1_03_int8.etlt \
-k cnV2NDlmYW9rOHFkdHM4ZnIzcjI2dnA1bGM6YTZkN2YyNzYtYzcxMS00ZmU2LWJmZDgtNGQyMjIyNDE1M2Zh \
--data_type int8 \
--cal_cache_file /workspace/tlt3/210521_darknet19_test/etlt/cal.bin \
--cal_data_file /workspace/tlt3/210521_darknet19_test/etlt/cal.tensorfile \
--cal_image_dir /workspace/tlt3/210427_coco/dataset/train_image
Matplotlib created a temporary config/cache directory at /tmp/matplotlib-90q8p850 because the default path (/.config/matplotlib) is not a writable directory; it is highly recommended to set the MPLCONFIGDIR environment variable to a writable directory, in particular to speed up the import of Matplotlib and to better support multiprocessing.
Using TensorFlow backend.
Using TensorFlow backend.
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
/usr/local/lib/python3.6/dist-packages/keras/engine/saving.py:292: UserWarning: No training configuration found in save file: the model was *not* compiled. Compile it manually.
warnings.warn('No training configuration found in save file: '
NOTE: UFF has been tested with TensorFlow 1.14.0.
WARNING: The version of TensorFlow installed on this system is not guaranteed to work with UFF.
Warning: No conversion function registered for layer: BatchedNMS_TRT yet.
Converting BatchedNMS as custom op: BatchedNMS_TRT
Warning: No conversion function registered for layer: ResizeNearest_TRT yet.
Converting upsample1/ResizeNearestNeighbor as custom op: ResizeNearest_TRT
Warning: No conversion function registered for layer: ResizeNearest_TRT yet.
Converting upsample0/ResizeNearestNeighbor as custom op: ResizeNearest_TRT
Warning: No conversion function registered for layer: BatchTilePlugin_TRT yet.
Converting FirstDimTile_2 as custom op: BatchTilePlugin_TRT
Warning: No conversion function registered for layer: BatchTilePlugin_TRT yet.
Converting FirstDimTile_1 as custom op: BatchTilePlugin_TRT
Warning: No conversion function registered for layer: BatchTilePlugin_TRT yet.
Converting FirstDimTile_0 as custom op: BatchTilePlugin_TRT
DEBUG [/usr/local/lib/python3.6/dist-packages/uff/converters/tensorflow/converter.py:96] Marking ['BatchedNMS'] as outputs
2021-06-02 13:58:01,716 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.