Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Exception: Not support layer LOGISTIC #77

Open
panjea opened this issue Jul 2, 2024 · 0 comments
Open

Exception: Not support layer LOGISTIC #77

panjea opened this issue Jul 2, 2024 · 0 comments

Comments

@panjea
Copy link

panjea commented Jul 2, 2024

getting this error from my model:

NEW KERAS MODEL:
<keras.src.layers.core.dense.Dense object at 0x7f36dca9e550>
input: (None, 10)
output: (None, 20)
<keras.src.layers.core.dense.Dense object at 0x7f36d8435e10>
input: (None, 20)
output: (None, 3)
ai_reset: <keras.src.engine.sequential.Sequential object at 0x7f36dc623fd0>
ai reset OK
Model: "sequential"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 dense (Dense)               (None, 20)                220       
                                                                 
 dense_1 (Dense)             (None, 3)                 63        
                                                                 
=================================================================
Total params: 283 (1.11 KB)
Trainable params: 283 (1.11 KB)
Non-trainable params: 0 (0.00 Byte)

error from calling: tflite2tmdl.py

INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
FULLY_CONNECTED
{'asymmetric_quantize_inputs': False, 'fused_activation_function': 1, 'keep_num_dims': False, 'weights_format': 0}
    input: dense_input
    output: dense/MatMul;dense/Relu;dense/BiasAdd
    weight: dense/MatMul
    bias: dense/bias
FULLY_CONNECTED
{'asymmetric_quantize_inputs': False, 'fused_activation_function': 0, 'keep_num_dims': False, 'weights_format': 0}
    input: dense/MatMul;dense/Relu;dense/BiasAdd
    output: dense_1/MatMul;dense_1/BiasAdd
    weight: dense_1/MatMul
    bias: dense_1/bias
LOGISTIC
None
OUTPUT!
    input: dense_1/MatMul;dense_1/BiasAdd
    output: dense_1/Sigmoid
Traceback (most recent call last):
  File "/home/rap/gir/./TinyMaix/tools/tflite2tmdl.py", line 619, in <module>
    tflite2tmdl(tflite_name, tmdl_name, mdl_type, out_deq, in_dims, out_dims, endian)
  File "/home/rap/gir/./TinyMaix/tools/tflite2tmdl.py", line 580, in tflite2tmdl
    layers = read_tflite(tflite_name, log_func=log_func)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/rap/gir/TinyMaix/tools/tflite_reader.py", line 273, in read_tflite
    raise Exception("Not support layer %s"%layer_name)
Exception: Not support layer LOGISTIC
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant