kentsommer / keras-posenet Goto Github PK
View Code? Open in Web Editor NEWImplementation of the PoseNet Architecture in Keras
Implementation of the PoseNet Architecture in Keras
unable to print model summary for posenet.
Also couldn't find where to give num_classes parameter.
Can someone help me with this?
from keras.utils.np_utils import convert_kernel
cannot import convert_kernel,tried googling but no luck
Pre-trained weights don't seem to be up for downloading. Can you re-upload a link for them?
Thanks in advance
Hi.
I'm new to Keras and was wondering whether the model runs on CPU or GPU. As in posenet.py line no 58, we have with tf.device('/cpu:0'): and what i found after googling is that this is to specify that cpu has to be used. And when change this from '/cpu:0' to '/gpu:0' I get an error "Cannot merge devices with incompatible types: '/GPU:0' and '/CPU:0' " . Can you please help me with this?
Hi, I can't download the weights.
Do you know where I can find it?
I recently came across posenet and tried to experiment with it. I modified the original architecture of posenet and now my input layer size is 1x100x224x224x3 where 1 is the batch size and 100 are the frames. Actually I have implemented lstm version of posenet. Now I have tried to run training on my own data, first on gtx750 and then on quadro k1200 4 GB gpu with tensorflow backend for keras(i am using posenet,written in keras) and also tried theano backend but everytime I get "out of memory" error. I want to ask what hardware specs your computer had on which you ran your training?
Hi,
when I try to run this implementation I am getting the following error.
Not sure if thats related to a Tensorflow or Keras version. (Im using Python 2.7.12, Tensorflow 1.12.0, Keras 1.2.0)
Will be grateful for any hints.
Cheers
Artur
Using TensorFlow backend.
Traceback (most recent call last):
File "/home/artur/Desktop/PhD_QUT/PROJECTS/keras-posenet-master/test.py", line 9, in
model = posenet.create_posenet()
File "/home/artur/Desktop/PhD_QUT/PROJECTS/keras-posenet-master/posenet.py", line 81, in create_posenet
icp2_in = merge([icp1_out0, icp1_out1, icp1_out2, icp1_out3],mode='concat',concat_axis=3,name='icp2_in')
File "/home/artur/venv/local/lib/python2.7/site-packages/keras/engine/topology.py", line 1674, in merge
name=name)
File "/home/artur/venv/local/lib/python2.7/site-packages/keras/engine/topology.py", line 1295, in init
self.add_inbound_node(layers, node_indices, tensor_indices)
File "/home/artur/venv/local/lib/python2.7/site-packages/keras/engine/topology.py", line 632, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/home/artur/venv/local/lib/python2.7/site-packages/keras/engine/topology.py", line 170, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors, mask=input_masks))
File "/home/artur/venv/local/lib/python2.7/site-packages/keras/engine/topology.py", line 1388, in call
return K.concatenate(inputs, axis=self.concat_axis)
File "/home/artur/venv/local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 1222, in concatenate
return tf.concat(axis, [to_dense(x) for x in tensors])
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1121, in concat
dtype=dtypes.int32).get_shape().assert_is_compatible_with(
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1050, in convert_to_tensor
as_ref=False)
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1146, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 971, in _autopacking_conversion_function
return _autopacking_helper(v, dtype, name or "packed")
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 923, in _autopacking_helper
return gen_array_ops.pack(elems_as_tensors, name=scope)
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 4875, in pack
"Pack", values=values, axis=axis, name=name)
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1792, in init
control_input_ops)
File "/home/artur/venv/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1631, in _create_c_op
raise ValueError(str(e))
ValueError: Dimension 3 in both shapes must be equal, but are 128 and 32. Shapes are [?,27,27,128] and [?,27,27,32].
From merging shape 1 with other shapes. for 'concat/concat_dim' (op: 'Pack') with input shapes: [?,27,27,64], [?,27,27,128], [?,27,27,32], [?,27,27,32].
This link is not work, someone can help me?
Send to my email [email protected], pls!
Or teachs me some other methods to achieve this.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.