Discussions

first, the data frame that presented in the example is not with the correct columns img_filename vs filename or bbox_x vs col_x and more.

when loading the dataset using fd.run(annotations=coco_annotations, overwrite=True) there is a RunTimeError

{
"name": "RuntimeError",
"message": "Fastdup execution failed",
"stack": "---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
Cell In[8], line 3
1 fd = fastdup.create(work_dir="/home/ohad/dataManager/",
2 input_dir="images/train2017/")
----> 3 fd.run(annotations=coco_annotations, overwrite=True)

File ~/miniconda3/envs/dm_test_3_10/lib/python3.10/site-packages/fastdup/engine.py:157, in Fastdup.run(self, input_dir, annotations, embeddings, subset, data_type, overwrite, model_path, distance, nearest_neighbors_k, threshold, outlier_percentile, num_threads, num_images, verbose, license, high_accuracy, cc_threshold, kwargs)
154 fastdup_func_params['model_path'] = model_path
155 fastdup_func_params.update(kwargs)
--> 157 return super().run(annotations=annotations, input_dir=input_dir, subset=subset, data_type=data_type,
158 overwrite=overwrite, embeddings=embeddings, fastdup_func_params)

File ~/miniconda3/envs/dm_test_3_10/lib/python3.10/site-packages/fastdup/sentry.py:144, in v1_sentry_handler..inner_function(*args, kwargs)
142 else:
143 fastdup_capture_exception(f"V1:{func.name}", ex)
--> 144 raise ex
146 except Exception as ex:
147 fastdup_capture_exception(f"V1:{func.name**}", ex)

File ~/miniconda3/envs/dm_test_3_10/lib/python3.10/site-packages/fastdup/sentry.py:135, in v1_sentry_handler..inner_function(_args, kwargs)
133 try:
134 start_time = time.time()
--> 135 ret = func(_args, kwargs)
136 fastdup_performance_capture(f"V1:{func.name}", start_time)
137 return ret

File ~/miniconda3/envs/dm_test_3_10/lib/python3.10/site-packages/fastdup/fastdup_controller.py:593, in FastdupController.run(self, input_dir, annotations, subset, embeddings, data_type, overwrite, print_summary, print_vl_datasets_ref, fastdup_kwargs)
591 # run fastdup - create embeddings
592 if fastdup.run(self._set_fastdup_input(), work_dir=str(self._work_dir), fastdup_kwargs) != 0:
--> 593 raise RuntimeError('Fastdup execution failed')
595 #fastdup_convert_to_relpath(self._work_dir, self._filename_prefix)
596
597 # post process - map fastdup-id to image (for bbox this is done in self._set_fastdup_input)
598 if self._dtype == FD.IMG or self._run_mode == FD.MODE_CROP:

RuntimeError: Fastdup execution failed"
}