oswaldoludwig / human-action-recognition-with-keras Goto Github PK

When i run the code i get the following warnings. Which leads to an error at the end.

Using TensorFlow backend.
/home/farshid/PycharmProjects/HumanActionRecognition/Main.py:67: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), name="conv1_1", activation="relu")`
  model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_1'))
/home/farshid/PycharmProjects/HumanActionRecognition/Main.py:69: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), name="conv1_2", activation="relu")`
  model.add(Convolution2D(64, 3, 3, activation='relu', name='conv1_2'))
/home/farshid/PycharmProjects/HumanActionRecognition/Main.py:73: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(128, (3, 3), name="conv2_1", activation="relu")`
  model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_1'))
/home/farshid/PycharmProjects/HumanActionRecognition/Main.py:75: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(128, (3, 3), name="conv2_2", activation="relu")`
  model.add(Convolution2D(128, 3, 3, activation='relu', name='conv2_2'))
Traceback (most recent call last):
  File "/home/farshid/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line 671, in _call_cpp_shape_fn_impl
    input_tensors_as_shapes, status)
  File "/home/farshid/anaconda3/lib/python3.5/contextlib.py", line 66, in __exit__
    next(self.gen)
  File "/home/farshid/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].

hello, interested in your code .But can your provide pre-trained models and inference script?
thank you very much~

这篇论文从哪里可以下载啊

Hi,
I noticed that in row 36 the pre-trained model whole_model.h5 is used. I can't find it in your depository. Anyone ones where to find it? Thanks.

Hi,I run 'python3 HumanActionRecognition.py', then get this, have you ever happened?

Using TensorFlow backend.
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line 670, in _call_cpp_shape_fn_impl
status)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/contextlib.py", line 66, in exit
next(self.gen)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 469, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'MaxPool_1' (op: 'MaxPool') with input shapes: [?,1,112,128].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "HumanActionRecognition.py", line 75, in
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/keras/models.py", line 332, in add
output_tensor = layer(self.outputs[0])
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/keras/engine/topology.py", line 572, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/keras/engine/topology.py", line 635, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/keras/engine/topology.py", line 166, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/keras/layers/pooling.py", line 160, in call
dim_ordering=self.dim_ordering)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/keras/layers/pooling.py", line 210, in _pooling_function
pool_mode='max')
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2866, in pool2d
x = tf.nn.max_pool(x, pool_size, strides, padding=padding)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/ops/nn_ops.py", line 1793, in max_pool
name=name)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 1598, in _max_pool
data_format=data_format, name=name)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 763, in apply_op
op_def=op_def)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2397, in create_op
set_shapes_for_outputs(ret)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1757, in set_shapes_for_outputs
shapes = shape_func(op)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1707, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn
debug_python_shape_fn, require_shape_fn)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line 675, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Negative dimension size caused by subtracting 2 from 1 for 'MaxPool_1' (op: 'MaxPool') with input shapes: [?,1,112,128].

Using Theano backend.
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
Traceback (most recent call last):
File "HumanActionRecognition.py", line 110, in
model.layers[k].set_weights(weights)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/keras/engine/topology.py", line 985, in set_weights
'provided weight shape ' + str(w.shape))
ValueError: Layer weight shape (3, 3, 224, 64) not compatible with provided weight shape (64, 3, 3, 3)

Using Theano backend.
Traceback (most recent call last):
File "HumanActionRecognition.py", line 18, in
from regularizers import EigenvalueRegularizer
ImportError: No module named regularizers

I have used the command ¨sudo pip install git+git://github.com/fchollet/keras.git --upgrade¨ to get the new keras,but still come up this problem?help!

Hi, I'm pretty new to deep-learning and keras in general. I want to know about that top-model weights file (Line No: 34). Where do I get that file (can you attach it)? or how do I train to get that .h5 file? I followed that blog.keras.io post but his top layer is different from yours and also he is training on dog vs cat (only 2 labels) whereas you are training on a dataset having ten output labels. I in fact tried modifying his code by replacing his top layer with your specifications. When I use the resulting bottleneck_fc_model.h5 as the file for your program, some dimension mismatch error is occurring. Any help?

I ran the line:
THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32,exception_verbosity=high python HumanActionRecognition.py

for 160 epochs initially, then for 120 and finally for 10. Each time I keep getting this error:

22424/22424 [==============================] - 620s - loss: 12.7184 - mean_squared_logarithmic_error: 0.0349 - acc: 0.4296 - val_loss: 1.5969 - val_mean_squared_logarithmic_error: 0.0334 - val_acc: 0.4687
Traceback (most recent call last):
  File "HumanActionRecognition.py", line 173, in <module>
    aux = model.predict_generator(test_generator, nb_test_samples)
  File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 945, in predict_generator
    pickle_safe=pickle_safe)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1634, in predict_generator
    outs = self.predict_on_batch(x)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1268, in predict_on_batch
    self.internal_input_shapes)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 70, in standardize_input_data
    'Found: ' + str(data)[:200] + '...')
Exception: Error when checking : data should be a Numpy array, or list/dict of Numpy arrays. Found: None

...
Exception in thread Thread-12:
Traceback (most recent call last):
  File "/usr/lib/python2.7/threading.py", line 810, in __bootstrap_inner
    self.run()
  File "/usr/lib/python2.7/threading.py", line 763, in run
    self.__target(*self.__args, **self.__kwargs)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 425, in data_generator_task
    generator_output = next(generator)
  File "/usr/local/lib/python2.7/dist-packages/keras/preprocessing/image.py", line 596, in next
    index_array, current_index, current_batch_size = next(self.index_generator)
  File "/usr/local/lib/python2.7/dist-packages/keras/preprocessing/image.py", line 444, in _flow_index
    current_index = (self.batch_index * batch_size) % N
ZeroDivisionError: integer division or modulo by zero

However, I did get a 65.3 MB whole_model.h5 file at the end of it. Could you guide me if this error is worth ignoring? How does this actually work?