wy1iu / dcnets Goto Github PK
View Code? Open in Web Editor NEWImplementation for <Decoupled Networks> in CVPR'18.
License: MIT License
Implementation for <Decoupled Networks> in CVPR'18.
License: MIT License
thank you for your greate jobs. I see you report the result with res-18 for imagenet in your paper. Do you have trained more deep layers for imagenet or some other largescale dataset? for example res101, or res152 ? can you share some experience for that?
Traceback (most recent call last):
File "/home/tanglin/data/Code/DCNets/dcnet_cifar100/linear_cos/train_resnet.py", line 161, in
train(args.base_lr, args.batch_size)
File "/home/tanglin/data/Code/DCNets/dcnet_cifar100/linear_cos/train_resnet.py", line 49, in train
vgg.build(images, n_class, is_training)
File "/home/tanglin/data/Code/DCNets/dcnet_cifar100/linear_cos/architecture.py", line 168, in build
name='root', bn=True, pad='SAME', norm=True, reg=False, orth=True)
File "/home/tanglin/data/Code/DCNets/dcnet_cifar100/linear_cos/architecture.py", line 118, in _conv_layer
self._add_orthogonal_constraint(filt, n_filt)
File "/home/tanglin/data/Code/DCNets/dcnet_cifar100/linear_cos/architecture.py", line 99, in _add_orthogonal_constraint
wnorm = self._get_filter_norm(filt)
File "/home/tanglin/data/Code/DCNets/dcnet_cifar100/linear_cos/architecture.py", line 87, in _get_filter_norm
return tf.sqrt(tf.reduce_sum(filt*filt, [0, 1, 2], keep_dims=True)+eps)
File "/home/tanglin/anaconda3/envs/tf1.9/lib/python2.7/site-packages/tensorflow/python/ops/math_ops.py", line 1206, in reduce_sum
name=name)
File "/home/tanglin/anaconda3/envs/tf1.9/lib/python2.7/site-packages/tensorflow/python/ops/gen_math_ops.py", line 2804, in _sum
keep_dims=keep_dims, name=name)
File "/home/tanglin/anaconda3/envs/tf1.9/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 763, in apply_op
op_def=op_def)
File "/home/tanglin/anaconda3/envs/tf1.9/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2329, in create_op
set_shapes_for_outputs(ret)
File "/home/tanglin/anaconda3/envs/tf1.9/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1717, in set_shapes_for_outputs
shapes = shape_func(op)
File "/home/tanglin/anaconda3/envs/tf1.9/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1667, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/home/tanglin/anaconda3/envs/tf1.9/lib/python2.7/site-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn
debug_python_shape_fn, require_shape_fn)
File "/home/tanglin/anaconda3/envs/tf1.9/lib/python2.7/site-packages/tensorflow/python/framework/common_shapes.py", line 676, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Invalid reduction dimension 2 for input with 2 dimensions. for 'root/Sum' (op: 'Sum') with input shapes: [27,96], [3].
rt。Do you plan to implement with pytorch?? Or someone want to try??
Hi, I am a little confused with the code.
Do you decoupled all the conv layers except for the last one( Fully connection layer) ?
So the vector w is 3D filter and vectorized into columns ?
Thx.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.