search

rockchip-linux / rknn-toolkit

BSD 3-Clause "New" or "Revised" License
808 stars 173 forks source link

YOLO V8/V9 TFlite Conversion Error to RKNN #457

Open aayushb-95 opened 3 months ago

aayushb-95 commented 3 months ago

I am trying to convert the TFLite model to RKNN model and I am getting the following error.

W rknn-toolkit version: 1.7.5
W Channels(512) of input node: input_0 > 128, mean/std values will be set to default 0/1.
W Please do pre-processing manually before inference.
--> Config model
--> Loading model
TFLite Model Loaded /home/aayush/yolov9s.tflite
--> Building model
E get error shape: [None, None]
E Catch exception when loading tflite model:  /home/aayush/yolov9s.tflite!
E Traceback (most recent call last):
E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 478, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer
E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 478, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer
E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 478, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer
E   File "rknn/base/RKNNlib/RKNNnetbuilder.py", line 492, in rknn.base.RKNNlib.RKNNnetbuilder.RKNNNetBuilder.build_layer
E   File "rknn/api/rknn_log.py", line 323, in rknn.api.rknn_log.RKNNLog.e
E ValueError: get error shape: [None, None]
E Please feedback the detailed log file <log_feedback_to_the_rknn_toolkit_dev_team.log> to the RKNN Toolkit development team.
E You can also check github issues: https://github.com/rockchip-linux/rknn-toolkit/issues
Traceback (most recent call last):
  File " /home/aayush/yolo_create_rknn.py", line 43, in <module>
    ret = rknn.build(do_quantization=True, dataset='images_512.txt', pre_compile=False, rknn_batch_size=1)
  File "/home/aayush/miniconda3/envs/rknn/lib/python3.8/site-packages/rknn/api/rknn.py", line 272, in build
    inputs = self.rknn_base.net.get_input_layers()
AttributeError: 'NoneType' object has no attribute 'get_input_layers'

Any help on this will be appreciated. Thanks