Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, and more
do you have any post in the discussion forum https://discuss.mxnet.io/ ?
I just woke up it is 5:16 am in Adelaide
Let me get coffee and laptop
File "main.py", line 229, in <module>
main()
File "main.py", line 214, in main
train(args)
File "main.py", line 82, in train
style_model.setTarget(style_image)
File "/Users/sam/dev/incubator-mxnet/example/gluon/style_transfer/net.py", line 236, in setTarget
F = self.model1(Xs)
File "/Users/sam/anaconda2/lib/python2.7/site-packages/mxnet/gluon/block.py", line 304, in __call__
return self.forward(*args)
File "/Users/sam/anaconda2/lib/python2.7/site-packages/mxnet/gluon/block.py", line 516, in forward
return self.hybrid_forward(ndarray, x, *args, **params)
File "/Users/sam/anaconda2/lib/python2.7/site-packages/mxnet/gluon/nn/basic_layers.py", line 111, in hybrid_forward
x = block(x)
File "/Users/sam/anaconda2/lib/python2.7/site-packages/mxnet/gluon/block.py", line 304, in __call__
return self.forward(*args)
File "/Users/sam/anaconda2/lib/python2.7/site-packages/mxnet/gluon/block.py", line 507, in forward
params = {i: j.data(ctx) for i, j in self._reg_params.items()}
File "/Users/sam/anaconda2/lib/python2.7/site-packages/mxnet/gluon/block.py", line 507, in <dictcomp>
params = {i: j.data(ctx) for i, j in self._reg_params.items()}
File "/Users/sam/anaconda2/lib/python2.7/site-packages/mxnet/gluon/parameter.py", line 389, in data
return self._check_and_get(self._data, ctx)
File "/Users/sam/anaconda2/lib/python2.7/site-packages/mxnet/gluon/parameter.py", line 189, in _check_and_get
"nested child Blocks"%(self.name,type(self)))
RuntimeError: Parameter net0_instancenorm0_beta <class 'mxnet.gluon.parameter.Parameter'> has not been initialized. Note that you should initialize parameters and create Trainer with Block.collect_params() instead of Block.params because the later does not include Parameters of nested child Blocks
There : samhodge/incubator-mxnet@949993f
I may have no idea what I am doing
here is my command line args
python main.py train --dataset dataset --style-folder images/styles --save-model-dir models --cuda 0
you will need to download the images and the model
but repro yes
To be honest I am still learning
but the objective is clear, convert Gluon model to Symbolic model and then run in C++
I am stuck at step 1
@anirudh2290 Thank you for being generous with your time
I might be able to look into it on my lunch break here at work.
Just training now, I will let it cook until the morning CPU only
OK nearly there, it seems to be training a model OK, but when I go to save the model the issue is in the Inspiration(HybridBlock) the current code which was (poorly) converted from Block to HybridBlock, is not using a Symbol in the args for return value from HybridForward, it is a NDArray, the errors tell me this, but now I am stuck with the issue that the infer_shapes code keeps givng me back and error
terminate called after throwing an instance of 'std::logic_error'
what(): basic_string::_S_construct null not valid
what(): basic_string::_S_construct null not valid
so basically the question comes back to
class Inspiration(HybridBlock):
""" Inspiration Layer (from MSG-Net paper)
tuning the featuremap with target Gram Matrix
ref https://arxiv.org/abs/1703.06953
"""
def __init__(self, C, B=1):
super(Inspiration, self).__init__()
# B is equal to 1 or input mini_batch
self.C = C
self.weight = self.params.get('weight', shape=(1,C,C),
init=mx.initializer.Uniform(),
allow_deferred_init=True)
self.gram = self.params.get('gram', shape=(B,C,C),
init=mx.initializer.Uniform(),
allow_deferred_init=True,
lr_mult=0)
def setTarget(self, target):
self.gram.set_data(target)
def forward(self, X):
# input X is a 3D feature map
self.P = F.batch_dot(F.broadcast_to(self.weight.data(), shape=(self.gram.shape)), self.gram.data())
return F.batch_dot(F.SwapAxis(self.P,1,2).broadcast_to((X.shape[0], self.C, self.C)), X.reshape((0,0,X.shape[2]*X.shape[3]))).reshape(X.shape)
def __repr__(self):
return self.__class__.__name__ + '(' \
+ 'N x ' + str(self.C) + ')'Anyone want to throw me a hand?
I have been able to train on GPU and CPU, but I am not able to save the symbolic moel
I will be able to commit my changes to repro the error in about 7 hours from now.
the shape should be inferred when data is bound to the symbolic inputs to the model
that is not a good start
With this
`class Inspiration(HybridBlock):
""" Inspiration Layer (from MSG-Net paper)
tuning the featuremap with target Gram Matrix
ref https://arxiv.org/abs/1703.06953
"""
def init(self, C, B=1, ctx=mx.cpu(0)):
super(Inspiration, self).init()
""" Inspiration Layer (from MSG-Net paper)
tuning the featuremap with target Gram Matrix
ref https://arxiv.org/abs/1703.06953
"""
def init(self, C, B=1, ctx=mx.cpu(0)):
super(Inspiration, self).init()
# B is equal to 1 or input mini_batch
self.C = C
self.B = B
self.weight = self.collect_params().get('weight', shape=(1,self.C,self.C),
init=mx.initializer.Uniform(),
allow_deferred_init=True)
self.gram = self.collect_params().get('gram', shape=(self.B,self.C,self.C),
init=mx.initializer.Uniform(),
allow_deferred_init=True,
lr_mult=0)
self.weight.initialize(ctx=ctx)
self.gram.initialize(ctx=ctx)
def setTarget(self, target):
self.gram.set_data(target)
def hybrid_forward(self, F, X, gram, weight):
P = F.batch_dot(F.broadcast_to(weight, shape=(self.gram.shape)), gram)
if not isinstance(X,symbol.Symbol):
return F.batch_dot(F.SwapAxis(P,1,2).broadcast_to((X.shape[0], self.C, self.C)), X.reshape((0,0,X.shape[2]*X.shape[3]))).reshape(X.shape)
else:
#print "Hooppla", interals
#for i in dir(interals):
# print "kk:", i
in_shapes,out_shapes,arg_shapes= X.infer_shape(self.gram.shape)
#print out_shapes
#raise Exception
#arg_shapes, out_shapes, aux_shapes = interals.infer_shape(self.gram.shape)
#print "A", arg_shapes, "O", out_shapes, "AU", aux_shapes
return F.batch_dot(F.SwapAxis(P,1,2).broadcast_to((in_shapes[0], self.C, self.C)), X.reshape((0,0,in_shapes[2]*in_shapes[3]))).reshape(in_shapes)
def __repr__(self):
return self.__class__.__name__ + '(' \
+ 'N x ' + str(self.C) + ')'`
i get the following error