haebeom-lee / l2b Goto Github PK

Tensorflow implementation of "Learning to Balance: Bayesian Meta-learning for Imbalanced and Out-of-distribution Tasks" (ICLR 2020 oral)

Python 91.19% Shell 8.81%

l2b's People

Contributors

Stargazers

Watchers

Forkers

yuanwanglll nanqiaobei eunjuyang boul503 tongwu2020 duoyi1 brictobrick yuyiqiu123 safeami jingmingcn

l2b's Issues

The meaning of "--alpha_on --omega_on --gamma_on --z_on" in command line

In the main.py, these four parameters are default False. So do we still need to add "--alpha_on --omega_on --gamma_on --z_on" in the command?

Also, I did not find where we use "--alpha_on, --z_on" in the main.py file.

When I follow the exact instruction of the experiment (CIFAR, SVHN), I have the following results: The results are similar to that of MAML, not better than Bayesian TAML. Do you have any ideas?

The time consumption of testing

In the meta-test phase, setting the MC approsimation with large sample size which means we need to perform multiple forward processing, which will cause large time consumption with large network?

KeyError: 'content-length' occurs when I try to download some datasets.

Hi.
When I try to download some datasets (mimgnet, CUB, quickdraw), an error occurs and cannot download them.

Traceback (most recent call last):
  File "get_data.py", line 37, in <module>
    download_file('http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/CUB_200_2011.tgz','CUB_200_2011.tgz')
  File "get_data.py", line 28, in download_file
    pbar = tqdm( unit="B", total=int( r.headers['Content-Length'] ) )
  File "/home/dmsl/miniconda3/envs/tf-1.15/lib/python3.7/site-packages/requests/structures.py", line 54, in __getitem__
    return self._store[key.lower()][1]
KeyError: 'content-length'

In the case of CUB, the URL redirects me to a Google drive link so it can be solved by manually download it.
But for mimgnet and quickdraw, the URL can be accessed because of error 404.

running problem of MiniImageNet/CUB

Hi Hae Beom,
Sorry to bother you again. I run some experiments:

cifar/SVHN:
I tried two times w/ and w/o --alpha_on --omega_on --gamma_on --z_on.

keep alpha omega gamma z all off, train/test work very well.
keep --alpha_on --omega_on --gamma_on --z_on all on, train/test work very well.

MiniImageNet/CUB:
I tried two as well. one of them does not work. I am finding out where is wrong. That would be great if you could also give some ideas. Thank you!

keep alpha omega gamma z all off, train/test work very well.
keep --alpha_on --omega_on --gamma_on --z_on all on, there will appear this error when training:

Traceback (most recent call last):
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call
    return fn(*args)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1319, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 2328480 values, but the requested shape requires a multiple of 3072
	 [[{{node map/while/Reshape}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _class=["loc:@gradients/map/while/encoder/conv1/Conv2D_grad/ShapeN/f_acc"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](map/while/TensorArrayReadV3, map/while/Reshape/shape)]]
	 [[{{node Mean_1/_267}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_16025_Mean_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/cxl173430/l2b/main_2.py", line 266, in <module>
    meta_train()
  File "/home/cxl173430/l2b/main_2.py", line 147, in meta_train
    sess.run(meta_train_to_run, feed_dict=fd_mtr))
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 929, in run
    run_metadata_ptr)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1152, in _run
    feed_dict_tensor, options, run_metadata)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1328, in _do_run
    run_metadata)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1348, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 2328480 values, but the requested shape requires a multiple of 3072
	 [[node map/while/Reshape (defined at /home/cxl173430/l2b/encoder.py:35)  = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _class=["loc:@gradients/map/while/encoder/conv1/Conv2D_grad/ShapeN/f_acc"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](map/while/TensorArrayReadV3, map/while/Reshape/shape)]]
	 [[{{node Mean_1/_267}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_16025_Mean_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

Caused by op 'map/while/Reshape', defined at:
  File "/home/cxl173430/l2b/main_2.py", line 90, in <module>
    net = model.forward_outer_multiple(sample=True, reuse=False)
  File "/home/cxl173430/l2b/model.py", line 169, in forward_outer_multiple
    parallel_iterations=self.metabatch)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/ops/functional_ops.py", line 494, in map_fn
    maximum_iterations=n)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3291, in while_loop
    return_same_structure)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3004, in BuildLoop
    pred, body, original_loop_vars, loop_vars, shape_invariants)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2939, in _BuildLoop
    body_result = body(*packed_vars_for_body)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3260, in <lambda>
    body = lambda i, lv: (i + 1, orig_body(*lv))
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/ops/functional_ops.py", line 483, in compute
    packed_fn_values = fn(packed_values)
  File "/home/cxl173430/l2b/model.py", line 163, in <lambda>
    self.forward_outer(inputs, sample=sample, reuse=reuse)
  File "/home/cxl173430/l2b/model.py", line 100, in forward_outer
    (xtr, ytr), sample, reuse=reuse)
  File "/home/cxl173430/l2b/encoder.py", line 106, in forward
    q_omega, q_gamma, q_z = self.get_posterior(inputs, reuse=reuse)
  File "/home/cxl173430/l2b/encoder.py", line 35, in get_posterior
    x = tf.reshape(x, [-1, self.xdim, self.xdim, self.input_channel])
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/ops/gen_array_ops.py", line 6482, in reshape
    "Reshape", tensor=tensor, shape=shape, name=name)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
    return func(*args, **kwargs)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
    op_def=op_def)
  File "/home/cxl173430/anaconda3/envs/py35/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1770, in __init__
    self._traceback = tf_stack.extract_stack()

InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 2328480 values, but the requested shape requires a multiple of 3072
	 [[node map/while/Reshape (defined at /home/cxl173430/l2b/encoder.py:35)  = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _class=["loc:@gradients/map/while/encoder/conv1/Conv2D_grad/ShapeN/f_acc"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](map/while/TensorArrayReadV3, map/while/Reshape/shape)]]
	 [[{{node Mean_1/_267}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_16025_Mean_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.