conv neural network - Keras PReLU layer not working with variable input size -


i want implement sample pnet model this paper. purpose using functional api instead of sequential model, since @ end need concatenate 2 outputs.

this code:

from  keras import backend k keras.models import sequential, model, input keras.layers import conv2d, maxpooling2d, dense, activation keras.layers.advanced_activations import prelu k.set_image_dim_ordering('tf') def get_p_net():     main_input = input(shape=(none, none, 3), dtype='float32', name='main_input')     x = conv2d(10, (3, 3), strides=(1, 1), padding='valid', name='conv1')(main_input)     x = prelu(name='prelu1', alpha_constraint=none)(x)     x = maxpooling2d(pool_size=(2, 2), strides=(2,2), padding='same', name='pool1')(x)     x = conv2d(16, (3, 3), strides=(1,1), padding='valid', name='conv2')(x)     x = prelu(name='prelu2')(x)     x = conv2d(32, (3, 3), strides=(1,1), padding='valid', name='conv3')(x)     x = prelu(name='prelu3')(x)     binary_face_output = conv2d(2, (1, 1), strides=(1,1), padding='same', name='conv4-1')(x)     binary_face_output = dense(2, activation='softmax', name='prob1')(binary_face_output)     bbox_output = conv2d(4, (1, 1), strides=(1,1), padding='same', name='conv4-2')(x)     model = model(inputs=[main_input], outputs=[binary_face_output, bbox_output])     model.summary()     # model.compile(optimizer='rmsprop', loss='binary_crossentropy',     #           loss_weights=[1., 1.])  get_p_net()

this exception:

  file "p_net.py", line 23, in <module>     get_p_net()   file "p_net.py", line 9, in get_p_net     x = prelu(name='prelu1', alpha_constraint=none)(x)   file "d:\anaconda2\envs\tensorflow\lib\site-packages\keras\engine\topology.py", line 569, in __call__     self.build(input_shapes[0])   file "d:\anaconda2\envs\tensorflow\lib\site-packages\keras\layers\advanced_activations.py", line 111, in build     constraint=self.alpha_constraint)   file "d:\anaconda2\envs\tensorflow\lib\site-packages\keras\legacy\interfaces.py", line 87, in wrapper     return func(*args, **kwargs)   file "d:\anaconda2\envs\tensorflow\lib\site-packages\keras\engine\topology.py", line 391, in add_weight     weight = k.variable(initializer(shape), dtype=dtype, name=name)   file "d:\anaconda2\envs\tensorflow\lib\site-packages\keras\initializers.py", line 29, in __call__     return k.constant(0, shape=shape, dtype=dtype)   file "d:\anaconda2\envs\tensorflow\lib\site-packages\keras\backend\tensorflow_backend.py", line 358, in constant     return tf.constant(value, dtype=dtype, shape=shape, name=name)   file "d:\anaconda2\envs\tensorflow\lib\site-packages\tensorflow\python\framework\constant_op.py", line 102, in constant     tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))   file "d:\anaconda2\envs\tensorflow\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 371, in make_tensor_proto     if np.prod(shape) == 0:   file "d:\anaconda2\envs\tensorflow\lib\site-packages\numpy\core\fromnumeric.py", line 2518, in prod     out=out, **kwargs)   file "d:\anaconda2\envs\tensorflow\lib\site-packages\numpy\core\_methods.py", line 35, in _prod     return umr_prod(a, axis, dtype, out, keepdims) typeerror: unsupported operand type(s) *: 'nonetype' , 'nonetype'

it clear somehow not input shape of layer (output of last convolutional layer). so, changing first line to:

main_input = input(shape=(12, 12, 3), dtype='float32', name='main_input')

fixed problem , model summary. want ask if there way of processing variable size inputs through network contains prelu layers.


Comments

Post a Comment

Popular posts from this blog

ubuntu - PHP script to find files of certain extensions in a directory, returns populated array when run in browser, but empty array when run from terminal -

i running os ububtu 16.04. ultimate goal able run php script cron job every minute. here php script located @ /var/www/html/tests/test/index.php : <?php $directorypath = $_server['document_root']."/tests/test/data/"; echo "directorypath: $directorypath<br><br>";//check $imagefilepathsarray = glob($directorypath . "*.{png,gif}", glob_brace); echo "<br><br>imagefilepathsarray: "; print_r($imagefilepathsarray);//check ?> when open php script in browser visiting url my-ip-address/tests/test/index.php , get: directorypath: /var/www/html/tests/test/data/ imagefilepathsarray:array( [0] => /var/www/html/tests/test/data/pic.png [1] => /var/www/html/tests/test/data/pic.gif ) before writing cron job in crontab file, need check if can run anywhere using terminal . opened ubuntu terminal @ /home/ location, , executed in terminal: sudo php /var/www/html/tests/test/index.php i got following out...
Read more

php - How can i create a user dashboard -

today have questions you, want create user dashboard site, include (obviously), users data, example -email -username -and others stuff how can information, , print them in html page? if can, how can these information via php sessions? shuld use session? example, if user login, , start new session ( session_start() ), how can data print in dashboard? should use php "project"? in advice, have day , thank time!
Read more

javascript - How to detect toggling of the fullscreen-toolbar in jQuery Mobile? -

i have jquery mobile page fixed full-screen toolbar, data-tap-toggle enabled. straight under toolbar have positioned banner should slide upwards when toolbar hiding , slide downward when toolbar showing. jquery mobile toggles toolbar applying , removing ui-fixed-hidden class - sadly, can't find in documentation of toolbar widget toggle , hide or show event that. how can detect when toolbar toggled, reposition banner? .banner { position: fixed; background-color: darkseagreen; top: 46px; min-height: 48px; width: 100%; text-align: center; line-height: 48px; } <!doctype html> <html> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=no"> <link rel="stylesheet" href="https://code.jquery.com/mobile/1.4.5/jquery.mobile-1.4.5.css"> <script src="https://code.jquery.com/jquery-1....
Read more