Hello Everyone,
I am currently working on coverting tensorflow model to TFLite model. I am facing the following issue while converting the model and I coulnt find a solution for this. Anyone faced the same issue and find some solution ?
2024-03-12 11:20:22.181279: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:357] Ignored output_format.
2024-03-12 11:20:22.181335: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:360] Ignored drop_control_dependency.
2024-03-12 11:20:22.182328: I tensorflow/cc/saved_model/reader.cc:43] Reading SavedModel from: ./export/1/
2024-03-12 11:20:22.331948: I tensorflow/cc/saved_model/reader.cc:78] Reading meta graph with tags { serve }
2024-03-12 11:20:22.332007: I tensorflow/cc/saved_model/reader.cc:119] Reading SavedModel debug info (if present) from: ./export/1/
2024-03-12 11:20:22.888341: I tensorflow/cc/saved_model/loader.cc:228] Restoring SavedModel bundle.
2024-03-12 11:20:24.772238: I tensorflow/cc/saved_model/loader.cc:212] Running initialization op on SavedModel bundle at path: ./export/1/
2024-03-12 11:20:25.905722: I tensorflow/cc/saved_model/loader.cc:301] SavedModel load for tags { serve }; Status: success: OK. Took 3723399 microseconds.
2024-03-12 11:20:28.243562: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:237] disabling MLIR crash reproducer, set env var MLIR_CRASH_REPRODUCER_DIRECTORY to enable.
2024-03-12 11:20:32.225859: W tensorflow/compiler/mlir/lite/flatbuffer_export.cc:1892] TFLite interpreter needs to link Flex delegate in order to run the model since it contains the following Select TFop(s):
Flex ops: FlexCombinedNonMaxSuppression, FlexResizeBilinear
Details:
tf.CombinedNonMaxSuppression(tensor<?x49104x1x4xf32>, tensor<?x?x1xf32>, tensor, tensor, tensor, tensor) → (tensor<?x300x4xf32>, tensor<?x300xf32>, tensor<?x300xf32>, tensor<?xi32>) : {clip_boxes = false, device = “”, pad_per_class = false}
tf.ResizeBilinear(tensor<?x?x?x3xui8>, tensor<2xi32>) → (tensor<?x?x?x3xf32>) : {align_corners = false, device = “”, half_pixel_centers = true}
See instructions: Select TensorFlow operators | TensorFlow Lite
Thank you very much in advance.