Hey @billyblu2000

I am getting a strange tensor error on my test melody. So I was wondering if you can help me out to figure out what I am doing wrong...

Here is the traceback:

Searching for Phrase 1 Searching for Phrase 2 Searching for Phrase 3 Reference chosen: [(144, '倒带'), (144, '倒带'), (144, '倒带')] Pitch Transposition (Fit by Model): [-3, 2, 2] Generating... Traceback (most recent call last): File "demo.py", line 14, in <module> cdt.generate_save(demo_name + '_output_results') File "/content/AccoMontage2/chorderator/interaction.py", line 91, in generate_save return _core.generate_save(output_name=output_name, task=task, log=log, wav=wav, **kwargs) File "/content/AccoMontage2/chorderator/core.py", line 392, in generate_save log=True, **kwargs) File "/content/AccoMontage2/chorderator/core.py", line 361, in generate gen = self.run(cut_in, cut_in_arg, with_texture, **kwargs) File "/content/AccoMontage2/chorderator/core.py", line 294, in run **kwargs) File "/content/AccoMontage2/chorderator/utils/pipeline.py", line 62, in send_in self.final_output = self.__add_textures(self.chord_gen_output, self.final_output_log, **kwargs) File "/content/AccoMontage2/chorderator/utils/pipeline.py", line 113, in __add_textures processor.solve() File "/content/AccoMontage2/chorderator/utils/models/accomontage/AccoMontage.py", line 122, in solve midi = render_acc(piano_roll, chord_table, query_seg, path, shift, acc_pool, state_dict=self.state_dict) File "/content/AccoMontage2/chorderator/utils/models/accomontage/util_tools/AccoMontage.py", line 248, in render_acc est_x = model.inference(pr_matrix, gt_chord, sample=False) File "/content/AccoMontage2/chorderator/utils/models/accomontage/models/model.py", line 139, in inference dec_z = torch.cat([z_chd, z_rhy], dim=-1) RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 10 but got size 8 for tensor number 1 in the list.

My demo.py file is setup as such:

`import chorderator as cdt

if name == 'main':

demo_name = 'test'
input_melody_path = 'MIDI demos/inputs/' + demo_name + '/melody.mid'

cdt.set_melody(input_melody_path)
cdt.set_meta(tonic=cdt.Key.D)
cdt.set_segmentation('A4B8A4')
cdt.set_texture_prefilter((0, 2))
cdt.set_note_shift(0)
cdt.set_output_style(cdt.Style.POP_STANDARD)
cdt.generate_save(demo_name + '_output_results')`

And the melody MIDI is attached.

Thank you. melody.zip

Hello,

First of all, I wanted to thank you very much for your great work! Its awesome and I really like it. :)

I have a question... Is it possible to generate output with a custom melody? Or is it not supported yet?

I tried replacing melody.mid with my own midi but it does not work.

I attached my midi file for your review and your help with this issue would be really appreciated.

Thank you.

Here is the error I am getting on my midi: melody.zip

@Chorderator 2022-09-03 20:12:51,076 - INFO - Melody length 4, generate progression with 63 templates no matched length Traceback (most recent call last): File "demo.py", line 14, in <module> cdt.generate_save(demo_name + '_output_results') File "/content/AccoMontage2/chorderator/interaction.py", line 91, in generate_save return _core.generate_save(output_name=output_name, task=task, log=log, wav=wav, **kwargs) File "/content/AccoMontage2/chorderator/core.py", line 392, in generate_save log=True, **kwargs) File "/content/AccoMontage2/chorderator/core.py", line 361, in generate gen = self.run(cut_in, cut_in_arg, with_texture, **kwargs) File "/content/AccoMontage2/chorderator/core.py", line 294, in run **kwargs) File "/content/AccoMontage2/chorderator/utils/pipeline.py", line 53, in send_in progression_list = self.__main_model(splited_melo, self.meta) File "/content/AccoMontage2/chorderator/utils/pipeline.py", line 78, in __main_model processor.solve() File "/content/AccoMontage2/chorderator/utils/models/DP.py", line 153, in solve max_score = max([self._dp[-1][i][1] for i in range(min([self.max_num, len(templates[-1])]))]) ValueError: max() arg is an empty sequence

Hi there @billyblu2000,

Looks like very cool work you're doing here - thanks 🙂

I tried to run your project, and I found that several data files required to be in the 'chorderator/static' directory are missing (as per your .gitignore file). For example, the 'chorderator/static/model_master_final.pt' seems to be missing, as also 'chorderator/static/phrase_data0714.npz' and 'edge_weights_0714.npz'.

Would you be able to share these files by any chance please? It'd be great to try out your project 🙂

Thanks & all the best, Shaun

Issue 1 says: https://github.com/billyblu2000/AccoMontage2/issues/1 But I can't find them. Where are files model_master_final.pt and phrase_data0714.npz ?

I'm trying demo.pyusing one of data in pop909 dataset (only keep melody track), but it didn't work, full message as below. The file is as attach, can you help me to check whats the problem? Thanks!

  warnings.warn('Could not import FluidSynth, audio formats writing disabled')
/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/core.py:238: UserWarning: Meter auto set to 4/4/. Please set meter if this is not your expectation
  warnings.warn('Meter auto set to 4/4/. Please set meter if this is not your expectation')
/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/core.py:241: UserWarning: Mode auto set to major. Please set mode if this is not your expectation
  warnings.warn('Mode auto set to major. Please set mode if this is not your expectation')
@Chorderator 2022-11-01 16:52:42,695 - INFO -  start read progressions from dict 
@Chorderator 2022-11-01 16:52:48,565 - INFO -  read progressions done 
@Chorderator 2022-11-01 16:52:48,566 - INFO -  start read progression library from source_base.pnt 
@Chorderator 2022-11-01 16:52:55,625 - INFO -  read library done 
@Chorderator 2022-11-01 16:52:55,626 - WARNING -  Pre-processing... 
{'tonic': 'G', 'meter': '4/4', 'mode': 'maj', 'pos': ['x', 'x', 'x', 'x'], 'tempo': 61.000034566686246, 'unit': 0.24590150000000002}
Traceback (most recent call last):
  File "demo.py", line 15, in <module>
    cdt.generate_save(demo_name + '_output_results')
  File "/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/interaction.py", line 91, in generate_save
    return _core.generate_save(output_name=output_name, task=task, log=log, wav=wav, **kwargs)
  File "/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/core.py", line 391, in generate_save
    gen, chord_gen, gen_log = self.generate(cut_in=cut_in, cut_in_arg=cut_in_arg, with_texture=with_texture,
  File "/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/core.py", line 361, in generate
    gen = self.run(cut_in, cut_in_arg, with_texture, **kwargs)
  File "/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/core.py", line 275, in run
    self.pipeline.send_in(self.midi_path,
  File "/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/utils/pipeline.py", line 49, in send_in
    self.melo, splited_melo, self.meta = self.__preprocess(midi_path, **kwargs)
  File "/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/utils/pipeline.py", line 71, in __preprocess
    return processor.get()
  File "/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/utils/models/PreProcessor.py", line 40, in get
    handle_exception(312)
  File "/mnt/e2203fdf-08ef-4193-9c98-04fcd3f8df26/AccoMontage2/chorderator/utils/excp.py", line 59, in handle_exception
    raise ValueError('[Error {e}] '.format(e=code) + msg + website)
ValueError: [Error 312] Phrase length not accepted. Up to the current version, only the following length is supported: 4, 8, 12, 16, 24, 32. For more information, please visit https://...com.```


[melody.zip](https://github.com/billyblu2000/AccoMontage2/files/9908706/melody.zip)