itlab-vision / dl-benchmark

Deep Learning Inference benchmark. Supports OpenVINO™ toolkit, TensorFlow, TensorFlow Lite, ONNX Runtime, OpenCV DNN, MXNet, PyTorch, Apache TVM, ncnn, PaddlePaddle, etc.
http://hpc-education.unn.ru/dli
Apache License 2.0
27 stars 37 forks source link

TFLite converter effecientnet-b0 error #511

Open FenixFly opened 8 months ago

FenixFly commented 8 months ago

Пытаюсь конвертировать TF модель efficientnet-b0 из OpenModelZoo. tflite_converter.py выдает ошибку с неподдерживаемым слоем __inference_swish_f32_730.

Пробовал с разными tensorflow, последний раз с tensorflow==2.12.0 и tensorflow-addons==0.19 tensorflow-estimator==2.12.0 tensorflow-probability==0.19

Строка конвертации:

python tflite_converter.py --model-path /home/vasiliev/_dev/itlab/public/efficientnet-b0/efficientnet-b0/saved_model --input-names sub --input-shapes [1,224,224,3] --source-framework tf --output-names logits

Вывод скрипта с ошибкой (часть, полный вывод по ссылке: https://gist.github.com/FenixFly/3c523abc679934a7df6b67ad006c7ad6 ):

[ INFO ] Loading TF model
[ INFO ] Loading saved model from /home/vasiliev/_dev/itlab/public/efficientnet-b0/efficientnet-b0/saved_model
2024-03-10 12:27:35.194661: I tensorflow/compiler/xla/stream_executor/cuda/cuda_gpu_executor.cc:996] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2024-03-10 12:27:35.194910: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1956] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
INFO:tensorflow:Saver not created because there are no variables in the graph to restore
[ INFO ] Saver not created because there are no variables in the graph to restore
[ INFO ] Setting input shapes to ([1, 224, 224, 3],)
[ INFO ] Converting to tflite
[ WARNING ] Please consider providing the trackable_obj argument in the from_concrete_functions. Providing without the trackable_obj argument is deprecated and it will use the deprecated conversion path.
2024-03-10 12:27:35.778469: I tensorflow/compiler/xla/stream_executor/cuda/cuda_gpu_executor.cc:996] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2024-03-10 12:27:35.778594: I tensorflow/core/grappler/devices.cc:66] Number of eligible GPUs (core count >= 8, compute capability >= 0.0): 1
loc(fused["__inference_swish_f32_73:", callsite("efficientnet-b0/model/blocks_4/se/swish_f32"("/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py":985:0) at callsite("/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py":836:0 at callsite("/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py":12:0 at callsite("/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py":142:0 at callsite("/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py":164:0 at "/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py":176:0)))))]): error: 'tf.LegacyCall' op is neither a custom op nor a flex op
loc(fused["__inference_swish_f32_73:", callsite("efficientnet-b0/model/head/swish_f32"("/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py":985:0) at callsite("/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py":836:0 at callsite("/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py":12:0 at callsite("/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py":142:0 at callsite("/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py":164:0 at "/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py":176:0)))))]): error: 'tf.LegacyCall' op is neither a custom op nor a flex op
2024-03-10 12:27:36.605790: W tensorflow/compiler/mlir/lite/flatbuffer_export.cc:2051] TFLite interpreter needs to link Flex delegate in order to run the model since it contains the following Select TFop(s):
Flex ops: FlexConv2D, FlexDepthwiseConv2dNative
Details:
    tf.Conv2D(tensor<*xf32>, tensor<1x1x10x240xf32>) -> (tensor<?x?x?x240xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x1152x192xf32>) -> (tensor<?x?x?x192xf32>) : {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x1152x320xf32>) -> (tensor<?x?x?x320xf32>) : {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x1152x48xf32>) -> (tensor<?x?x?x48xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x144x24xf32>) -> (tensor<?x?x?x24xf32>) : {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x144x40xf32>) -> (tensor<?x?x?x40xf32>) : {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x144x6xf32>) -> (tensor<?x?x?x6xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x20x480xf32>) -> (tensor<?x?x?x480xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x240x10xf32>) -> (tensor<?x?x?x10xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x240x40xf32>) -> (tensor<?x?x?x40xf32>) : {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x240x80xf32>) -> (tensor<?x?x?x80xf32>) : {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x28x672xf32>) -> (tensor<?x?x?x672xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x32x16xf32>) -> (tensor<?x?x?x16xf32>) : {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x32x8xf32>) -> (tensor<?x?x?x8xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x480x112xf32>) -> (tensor<?x?x?x112xf32>) : {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x480x20xf32>) -> (tensor<?x?x?x20xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x480x80xf32>) -> (tensor<?x?x?x80xf32>) : {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.Conv2D(tensor<*xf32>, tensor<1x1x48x1152xf32>) -> (tensor<?x?x?x1152xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true}
    tf.DepthwiseConv2dNative(tensor<*xf32>, tensor<3x3x96x1xf32>) -> (tensor<?x?x?x96xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 2, 2, 1]}
    tf.DepthwiseConv2dNative(tensor<*xf32>, tensor<5x5x1152x1xf32>) -> (tensor<?x?x?x1152xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1]}
    tf.DepthwiseConv2dNative(tensor<*xf32>, tensor<5x5x144x1xf32>) -> (tensor<?x?x?x144xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 2, 2, 1]}
    tf.DepthwiseConv2dNative(tensor<*xf32>, tensor<5x5x240x1xf32>) -> (tensor<?x?x?x240xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1]}
    tf.DepthwiseConv2dNative(tensor<*xf32>, tensor<5x5x480x1xf32>) -> (tensor<?x?x?x480xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1]}
    tf.DepthwiseConv2dNative(tensor<*xf32>, tensor<5x5x672x1xf32>) -> (tensor<?x?x?x672xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1]}
    tf.DepthwiseConv2dNative(tensor<*xf32>, tensor<5x5x672x1xf32>) -> (tensor<?x?x?x672xf32>) : {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 2, 2, 1]}
See instructions: https://www.tensorflow.org/lite/guide/ops_select
error: failed while converting: 'main': 
Some ops in the model are custom ops, See instructions to implement custom ops: https://www.tensorflow.org/lite/guide/ops_custom 
Custom ops: __inference_swish_f32_730
Details:
    tf.LegacyCall(tensor<1x112x112x32xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x10xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x1152xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x1280xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x144xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x20xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x240xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x28xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x32xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x480xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x48xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x4xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x672xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x6xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x8xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x96xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}

Traceback (most recent call last):
  File "/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py", line 176, in <module>
    main()
  File "/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py", line 172, in main
    convert_to_tflite(model, output_file)
  File "/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py", line 85, in convert_to_tflite
    tflite_model = converter.convert()
  File "/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/lite/python/lite.py", line 1897, in convert
    return super(TFLiteConverterV2, self).convert()
  File "/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/lite/python/lite.py", line 962, in wrapper
    return self._convert_and_export_metrics(convert_func, *args, **kwargs)
  File "/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/lite/python/lite.py", line 940, in _convert_and_export_metrics
    result = convert_func(self, *args, **kwargs)
  File "/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/lite/python/lite.py", line 1546, in convert
    return super(TFLiteFrozenGraphConverterV2,
  File "/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/lite/python/lite.py", line 1166, in convert
    result = _convert_graphdef(
  File "/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/lite/python/convert_phase.py", line 212, in wrapper
    raise converter_error from None  # Re-throws the exception.
  File "/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/lite/python/convert_phase.py", line 205, in wrapper
    return func(*args, **kwargs)
  File "/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/lite/python/convert.py", line 817, in convert_graphdef
    data = convert(
  File "/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/lite/python/convert.py", line 322, in convert
    raise converter_error
tensorflow.lite.python.convert_phase.ConverterError: /home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: error: 'tf.LegacyCall' op is neither a custom op nor a flex op
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:836:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:12:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tensorflow_common.py:142:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:164:0: note: called from
/home/vasiliev/_dev/itlab/dl-benchmark-vasilev/src/model_converters/tf2tflite/tflite_converter.py:176:0: note: called from
/home/vasiliev/miniconda3/envs/vino/lib/python3.9/site-packages/tensorflow/python/saved_model/load.py:985:0: note: Error code: ERROR_NEEDS_CUSTOM_OPS
<unknown>:0: error: failed while converting: 'main': 
Some ops in the model are custom ops, See instructions to implement custom ops: https://www.tensorflow.org/lite/guide/ops_custom 
Custom ops: __inference_swish_f32_730
Details:
    tf.LegacyCall(tensor<1x112x112x32xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x10xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x1152xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x1280xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x144xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x20xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x240xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x28xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x32xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x480xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x48xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x4xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x672xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x6xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x8xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
    tf.LegacyCall(tensor<?x?x?x96xf32>) -> (tensor<*xf32>) : {_disable_call_shape_inference = true, device = "", tfg.legacy_call = @__inference_swish_f32_730}
FenixFly commented 8 months ago

@n-berezina-nn Наталья, не могли бы вы помочь разобраться почему модель efficientnet-b0 из OpenModelZoo не конвертируется в формат tflite?

valentina-kustikova commented 7 months ago

@n-berezina-nn, @FenixFly, сконвертировала модель с использованием следующего скрипта:

import tensorflow as tf

converter = tf.lite.TFLiteConverter.from_saved_model('./efficientnet-b0/saved_model/')
converter.target_spec.supported_ops = [
  tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS
]
converter.allow_custom_ops=True
tflite_model = converter.convert()

with open('model.tflite', 'wb') as f:
  f.write(tflite_model)

Запускаю вывод средствами вот такой командной строки:

python3 ./inference_tensorflowlite.py -m ./efficientnet-b0/model.tflite -i ./data/ -b 1 -t classification --output_names logits -l ./labels/image_net_synset.txt --input_names sub[1,224,224,3]

Получаю следующий вывод:

2024-03-20 22:07:52.309100: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-03-20 22:07:52.309335: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
2024-03-20 22:07:52.311233: I external/local_tsl/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.
2024-03-20 22:07:52.334658: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-03-20 22:07:52.738092: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
[ INFO ] Loading network files:
         /home/itmm/Documents/kustikova_v/public/efficientnet-b0/efficientnet-b0/model.tflite
INFO: Created TensorFlow Lite delegate for select TF ops.
INFO: TfLiteFlexDelegate delegate: 64 nodes delegated out of 270 nodes with 64 partitions.

2024-03-20 22:07:52.998300: E tensorflow/core/framework/node_def_util.cc:676] NodeDef mentions attribute use_inter_op_parallelism which is not in the op definition: Op<name=DepthwiseConv2dNative; signature=input:T, filter:T -> output:T; attr=T:type,allowed=[DT_HALF, DT_BFLOAT16, DT_FLOAT, DT_DOUBLE]; attr=strides:list(int); attr=padding:string,allowed=["SAME", "VALID", "EXPLICIT"]; attr=explicit_paddings:list(int),default=[]; attr=data_format:string,default="NHWC",allowed=["NHWC", "NCHW"]; attr=dilations:list(int),default=[1, 1, 1, 1]> This may be expected if your graph generating binary is newer  than this binary. Unknown attributes will be ignored. NodeDef: {{node DepthwiseConv2dNative}}
[ INFO ] Shape for input layer sub:0: 1x224x224x3
[ INFO ] Preparing input data: ['/home/itmm/Documents/kustikova_v/data/']
[ INFO ] Starting inference (1 iterations)
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
[ ERROR ] Traceback (most recent call last):
  File "/home/itmm/Documents/kustikova_v/upstream/dl-benchmark/src/inference/./inference_tensorflowlite.py", line 286, in main
    result, inference_time = inference_tflite(interpreter, args.number_iter, io.get_slice_input, args.time)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/itmm/Documents/kustikova_v/upstream/dl-benchmark/src/inference/./inference_tensorflowlite.py", line 191, in inference_tflite
    interpreter.allocate_tensors()
  File "/home/itmm/miniconda/envs/tflite_converter_env/lib/python3.11/site-packages/tensorflow/lite/python/interpreter.py", line 531, in allocate_tensors
    return self._interpreter.AllocateTensors()
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Encountered unresolved custom op: swish_f320.
See instructions: https://www.tensorflow.org/lite/guide/ops_custom Node number 2 (swish_f320) failed to prepare.Encountered unresolved custom op: swish_f320.
See instructions: https://www.tensorflow.org/lite/guide/ops_custom Node number 2 (swish_f320) failed to prepare.

Если все правильно понимаю, то это означает, что конвертер посчитал, что оператор swich_f320 относится к числу кастомных, и реализация должна быть передана через делегат при запуске инференса, но стандартные делегаты не содержат его реализации.

valentina-kustikova commented 7 months ago

@FenixFly, @n-berezina-nn, сравнила через netron модель из OMZ в формате saved_model, которую мы хотим сконвертировать, и присланную модель в формате tflite. В модели OMZ есть явный слой swish_f32 (схема ниже), в присланной модели таких преобразований вообще нет. Это означает, что либо для конвертации использована другая модель, либо эту модель как-то преобразовывали перед тем, как сконвертировать.

image