I have cloned the tao_tensorflow1_backend github repo and has been training YoloV3 model in the docker container tao_tf1.
I tried converting my Kitti labels to TFRecords and tried executing the model once again and I am getting the below shown error. Please help me with the same
{“date”: “5/31/2024”, “time”: “10:18:1”, “status”: “STARTED”, “verbosity”: “INFO”, “message”: “Starting Yolo_V3 Training job”}
{“date”: “5/31/2024”, “time”: “10:18:4”, “status”: “FAILURE”, “verbosity”: “INFO”, “message”: “in converted code:\n\n /workspace/tao-tf1/third_party/keras/tensorflow_backend.py:365 _map_func_set_random_wrapper *\n return map_func(*args, **kwargs)\n /workspace/tao-tf1/nvidia_tao_tf1/cv/yolo_v3/data_loader/yolo_v3_data_loader.py:196 call *\n labels = self._extract_bbox_labels(example)\n /workspace/tao-tf1/nvidia_tao_tf1/cv/yolo_v3/data_loader/yolo_v3_data_loader.py:285 _extract_bbox_labels *\n sparse_coordinates = \\n /workspace/tao-tf1/nvidia_tao_tf1/blocks/multi_source_loader/types/tensor_transforms.py:171 sparsify_dense_coordinates *\n regular_sparse_tensor = values_and_count_to_sparse_tensor(\n /workspace/tao-tf1/nvidia_tao_tf1/core/processors/processors.py:328 values_and_count_to_sparse_tensor *\n op = load_custom_tf_op("op_values_and_count_to_sparse_tensor.so")\n /workspace/tao-tf1/nvidia_tao_tf1/core/processors/processors.py:201 load_custom_tf_op\n return tf.load_op_library(abs_path)\n /usr/local/lib/python3.8/dist-packages/tensorflow_core/python/framework/load_library.py:61 load_op_library\n lib_handle = py_tf.TF_LoadLibrary(library_filename)\n\n NotFoundError: /workspace/tao-tf1/nvidia_tao_tf1/core/processors/…/lib/op_values_and_count_to_sparse_tensor.so: cannot open shared object file: No such file or directory\n”}
