aiwintermuteai/transfer_learning_sipeed

Image Recognition With Sipeed MaiX and Arduino IDE/Micropython

transfer_learning_sipeed's Issues

'ProgbarLogger' object has no attribute 'log_values'

I'm trying to follow the instructables tutorial (on windows). Running test.py worked fine, but trying to running "python mbnet_keras.py" ends in

dense_3 (Dense)              (None, 2)                 102
=================================================================
Total params: 1,915,028
Trainable params: 82,052
Non-trainable params: 1,832,976
_________________________________________________________________
Epoch 1/10
Traceback (most recent call last):
  File "mbnet_keras.py", line 60, in <module>
    model.fit_generator(generator=train_generator,steps_per_epoch=step_size_train,epochs=10)
  File "C:\Users\Nitek\.conda\envs\ml\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Nitek\.conda\envs\ml\lib\site-packages\keras\engine\training.py", line 1418, in fit_generator
    initial_epoch=initial_epoch)
  File "C:\Users\Nitek\.conda\envs\ml\lib\site-packages\keras\engine\training_generator.py", line 251, in fit_generator
    callbacks.on_epoch_end(epoch, epoch_logs)
  File "C:\Users\Nitek\.conda\envs\ml\lib\site-packages\keras\callbacks.py", line 79, in on_epoch_end
    callback.on_epoch_end(epoch, logs)
  File "C:\Users\Nitek\.conda\envs\ml\lib\site-packages\keras\callbacks.py", line 338, in on_epoch_end
    self.progbar.update(self.seen, self.log_values)
AttributeError: 'ProgbarLogger' object has no attribute 'log_values'

Any hints?

AttributeError: module 'tensorflow.python.keras.backend' has no attribute 'get_graph'

Hi, thank you for the great tutorial.
Upon running the test.py it fails with the AttributeError.
I am new to python, so this might be a simple thing to fix?

Using TensorFlow backend.
/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:523: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:524: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:532: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
Traceback (most recent call last):
  File "test.py", line 1, in <module>
    import keras
  File "/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/keras/__init__.py", line 3, in <module>
    from . import utils
  File "/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/keras/utils/__init__.py", line 6, in <module>
    from . import conv_utils
  File "/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/keras/utils/conv_utils.py", line 9, in <module>
    from .. import backend as K
  File "/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/keras/backend/__init__.py", line 1, in <module>
    from .load_backend import epsilon
  File "/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/keras/backend/load_backend.py", line 90, in <module>
    from .tensorflow_backend import *
  File "/Users/cv/opt/miniconda3/envs/ml/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 54, in <module>
    get_graph = tf_keras_backend.get_graph
AttributeError: module 'tensorflow.python.keras.backend' has no attribute 'get_graph'

Fatal: Layer PAD is not supported

Follow the tutorial Image Recogntion With Sipeed MaiX and Arduino IDE/Micropython ,
that error occur:

$ ./tflite2kmodel.sh xo_model.tflite
uasge: ./tflite2kmodel.sh xxx.tflite
Fatal: Layer PAD is not supported

Pip install axelerate error.

No matching distribution found for tensorflow 2.3.0 I have the latest version .