liyu95/supportnet

SupportNet: solving catastrophic forgetting in class incremental learning with support data

supportnet's Issues

breakhis and hela10 data

Hello， can you upload the breakhis and hela10 dataset in the src_image_data folder?

DataSet

#load Pfam dataset and encoding them into array functional_domain_encoding_list=Pfam.Pfam_from_pickle_file_encoding( '/home/liy0f/ec_project/data_and_feature/Pfam_name_list_new_data.pickle', '/home/liy0f/ec_project/data_and_feature/Pfam_model_names_list.pickle')
Hello，about the two pickles,can you tell me how to get these and what datasets they belong to in your paper, can you provide the two pickles for me ? thank you very much.

where is the data file xxx.pickle comes from?

New Dataset in the code

Can I use other data sets in the code that you provide? Do I need to modify the data format?

Fisher information using the test data?

Hi,

I noticed that the fisher information is calculated by the test data. See line 345 in src_image_data/train_procedures.py

fisher_info_val=previous_network.compute_fisher_information(X_test_converted,session)

But I think we should calculate it using the training data. Did I misunderstand something or is there any reason to use the test data? Thanks.

Best!

Dataset

Hello，Because I don’t know how to deal with the data set when I run the experiment, can you provide the data set used in the code, thank you very much.

About the Memory storage problem

When the program is running to the end, there is a state of insufficient memory. My server's memory is 128G. Is it not enough for this program?

where is

Question

ok，I don't know why the last issues is closed, there is a question.

Traceback (most recent call last):
File "supportnet_ec.py", line 94, in
lambda: tf.constant(0.5, dtype=tf.float32))
File "/home/xiaolin/.local/lib/python2.7/site-packages/tensorflow/python/util/ deprecation.py", line 432, in new_func
return func(*args, **kwargs)
File "/home/xiaolin/.local/lib/python2.7/site-packages/tensorflow/python/ops/c ontrol_flow_ops.py", line 2040, in cond
orig_res_t, res_t = context_t.BuildCondBranch(true_fn)
File "/home/xiaolin/.local/lib/python2.7/site-packages/tensorflow/python/ops/c ontrol_flow_ops.py", line 1890, in BuildCondBranch
original_result = fn()
File "supportnet_ec.py", line 93, in
tf.gather(final_feature, support_ind))/tf.cast(tf.size(support_ind),dtype=tf .float32),
File "/home/xiaolin/.local/lib/python2.7/site-packages/tensorflow/python/ops/m ath_ops.py", line 874, in r_binary_op_wrapper
x = ops.convert_to_tensor(x, dtype=y.dtype.base_dtype, name="x")
File "/home/xiaolin/.local/lib/python2.7/site-packages/tensorflow/python/frame work/ops.py", line 1011, in convert_to_tensor
as_ref=False)
File "/home/xiaolin/.local/lib/python2.7/site-packages/tensorflow/python/frame work/ops.py", line 1107, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/xiaolin/.local/lib/python2.7/site-packages/tensorflow/python/frame work/constant_op.py", line 217, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/home/xiaolin/.local/lib/python2.7/site-packages/tensorflow/python/frame work/constant_op.py", line 196, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/home/xiaolin/.local/lib/python2.7/site-packages/tensorflow/python/frame work/tensor_util.py", line 424, in make_tensor_proto
raise ValueError("None values not supported.")
ValueError: None values not supported.
Now, I am searching the solution about the problem.