Hello, when I run the seq_seq_annot_aami.py, the terminal shows
" sm = SMOTE(random_state=12, ratio=ratio)
File "E:\Sensor\tensor\envs\tensorflow\lib\site-packages\imblearn\utils_validation.py", line 594, in inner_f
return f(**kwargs)
TypeError: init() got an unexpected keyword argument 'ratio'
"

Is there something wrong in"ratio = {0: n_oversampling, 1: nums[1], 2: n_oversampling, 3: n_oversampling}"?

Hey is the code to the ECGNET: Learning where to attend for detection of atrial fibrillation with deep visual attention paper made public.

Hi Sajad

I get the following error when running the code.

Traceback (most recent call last):
  File "seq_seq_annot_DS1DS2.py", line 441, in <module>
    main()
  File "seq_seq_annot_DS1DS2.py", line 226, in main
    run_program(args)
  File "seq_seq_annot_DS1DS2.py", line 242, in run_program
    X_train, y_train = read_mitbih(filename, max_time, classes=classes, max_nlabel=50000,trainset=1)
  File "seq_seq_annot_DS1DS2.py", line 78, in read_mitbih
    data = _data[:(len(_data)/ max_time) * max_time, :]
TypeError: slice indices must be integers or None or have an __index__ method

Could you upload the code of data pre-process? I want to know how to pre-process.Thank you!

Hello author, may I ask why class F is so difficult to identify? I have tried a lot of methods, as well as the code on github, basically have difficulty recognizing F, but which do not open source code can be recognized and recall is also high.

I have this error with lstm_enc, I didn't understand if the problem was with the input size or with LSTMCell.
data_input_embed Tensor("Reshape_3:0", shape=(?, 10, 384), dtype=int32)
Argument inputs must be a sequence. Received: Tensor("Reshape_3:0", shape=(?, 10, 384), dtype=int32)

Hello
First of all, congratulation on your model. I tried to run it and have some issues.

on the reshape section I have this error, and cannot figure out how to resolve it.
inputs = tf.reshape(inputs, [-1, n_channels, input_depth / n_channels])

Error:
Value passed to parameter 'shape' has DataType float32 not in list of allowed values: int32, int64

Thank you for any help

hi ,
in file "seq_seq_annot_aami.py" line 299,

shouldn't 1:nums[1] be 1:n_oversampling like the other elements of the dictionary?
or there's a logic behind this?

regards
Ed

First of all, thank you very much for your code! When I read your code, I found the process of generating ECG sequence in the original code is as follows.
Firstly, the heartbeat segmented by ECG records in the training set is stored into a two-dimensional
array, then the heartbeats of each kind (one of N S V) are selected and shuffled to get three smaller
two-dimensional arrays. Next, the three two-dimensional arrays are concatenated by rows to get a
larger two-dimensional array. Finally, the array is split into a sequence every max_time(the default is
10) line.
So I would like to ask why you want to group all the heartbeats according to categories in advance?
If you do this, the labels of each sequence are almost the same, and the heartbeats contained in each
sequence are not split from the same record at all (due to shuffle). This seems very different from the
actual situation, where the sequences should be composed of heartbeats from the same ECG record.
I wonder if this is a hidden trick of data processing? Why do we do that? Thank you very much for your reply! Here are some of the code that puzzles me.
data = np.asarray(data)
shape_v = data.shape
data = np.reshape(data, [shape_v[0], -1])
t_lables = np.array(t_lables)
_data = np.asarray([],dtype=np.float64).reshape(0,shape_v[1])
_labels = np.asarray([],dtype=np.dtype('|S1')).reshape(0,)
for cl in classes:
_label = np.where(t_lables == cl)
permute = np.random.permutation(len(_label[0]))
_label = _label[0][permute[:max_nlabel]]
_data = np.concatenate((_data, data[_label]))
_labels = np.concatenate((_labels, t_lables[_label]))

data = _data[:(len(_data)// max_time) * max_time, :]
_labels = _labels[:(len(_data) // max_time) * max_time]
data = [data[i:i + max_time] for i in range(0, len(data), max_time)]
labels = [_labels[i:i + max_time] for i in range(0, len(_labels), max_time)]
permute = np.random.permutation(len(labels))
data = np.asarray(data)
labels = np.asarray(labels)
data= data[permute]
labels = labels[permute]

Hi, we're trying to replicate the result of the paper. Could you tell us which version of tensorflow you used for the training ?

Thanks for your impressive work, however, is pytorch code available at present?

Does the number of parameters mentioned in your paper refer to the number of parameters / 1024/1024?