File size: 7,197 Bytes
fd4c083
0d7d207
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6d01d0c
0d7d207
 
 
 
 
 
50f85db
 
0d7d207
 
 
 
 
 
 
50f85db
0d7d207
 
 
 
 
 
 
 
 
 
50f85db
0d7d207
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88d8b6d
50f85db
0d7d207
88d8b6d
 
 
 
 
0d7d207
 
6d01d0c
 
0d7d207
6d01d0c
0d7d207
6d01d0c
0d7d207
 
 
6d01d0c
0d7d207
 
 
 
 
 
 
6d01d0c
0d7d207
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
# https://huggingface.co/spaces/asigalov61/Advanced-MIDI-Classifier

import os
import time as reqtime
import datetime
from pytz import timezone

import torch

import spaces
import gradio as gr

from x_transformer_1_23_2 import *
import random
import tqdm

from midi_to_colab_audio import midi_to_colab_audio
import TMIDIX

import matplotlib.pyplot as plt

in_space = os.getenv("SYSTEM") == "spaces"
         
# =================================================================================================
                       
@spaces.GPU
def ClassifyMIDI(input_midi):
    print('=' * 70)
    print('Req start time: {:%Y-%m-%d %H:%M:%S}'.format(datetime.datetime.now(PDT)))
    start_time = reqtime.time()

    print('Loading model...')

    SEQ_LEN = 1024
    PAD_IDX = 14627
    DEVICE = 'cuda' # 'cuda'

    # instantiate the model

    model = TransformerWrapper(
        num_tokens = PAD_IDX+1,
        max_seq_len = SEQ_LEN,
        attn_layers = Decoder(dim = 1024, depth = 12, heads = 16, attn_flash = True)
        )
    
    model = AutoregressiveWrapper(model, ignore_index = PAD_IDX)

    model.to(DEVICE)
    print('=' * 70)

    print('Loading model checkpoint...')

    model.load_state_dict(
        torch.load('Annotated_MIDI_Dataset_Classifier_Trained_Model_21269_steps_0.4335_loss_0.8716_acc.pth',
                   map_location=DEVICE))
    print('=' * 70)

    model.eval()

    if DEVICE == 'cpu':
        dtype = torch.bfloat16
    else:
        dtype = torch.bfloat16

    ctx = torch.amp.autocast(device_type=DEVICE, dtype=dtype)

    print('Done!')
    print('=' * 70)
    seed_melody = seed_melodies_data[input_melody_seed_number]
    print('Input melody seed number:', input_melody_seed_number)
    print('-' * 70)

    #==================================================================

    print('=' * 70)
    
    print('Sample output events', seed_melody[:16])
    print('=' * 70)
    print('Generating...')

    x = (torch.tensor(seed_melody, dtype=torch.long, device='cuda')[None, ...])

    with ctx:
      out = model.generate(x,
                          1536,
                          temperature=0.9,
                          return_prime=False,
                          verbose=False)
    
    output = out[0].tolist()
        
    print('=' * 70)
    print('Done!')
    print('=' * 70)
    
    #===============================================================================
    print('Rendering results...')
    
    print('=' * 70)
    print('Sample INTs', output[:15])
    print('=' * 70)
    
    out1 = output

    if len(out1) != 0:
    
        song = out1
        song_f = []
    
        time = 0
        dur = 0
        vel = 90
        pitch = 0
        channel = 0
    
        patches = [0] * 16
        patches[3] = 40
    
        for ss in song:
    
            if 0 < ss < 128:
    
                time += (ss * 32)
    
            if 128 < ss < 256:
    
                dur = (ss-128) * 32
    
            if 256 < ss < 512:
    
                pitch = (ss-256) % 128
    
                channel = (ss-256) // 128
    
                if channel == 1:
                    channel = 3
                    vel = 110 + (pitch % 12)
                    song_f.append(['note', time, dur, channel, pitch, vel, 40])
                    
                else:
                    vel = 80 + (pitch % 12)
                    channel = 0
                    song_f.append(['note', time, dur, channel, pitch, vel, 0])

    fn1 = "Melody2Song-Seq2Seq-Music-Transformer-Composition"
    
    detailed_stats = TMIDIX.Tegridy_ms_SONG_to_MIDI_Converter(song_f,
                                                              output_signature = 'Melody2Song Seq2Seq Music Transformer',
                                                              output_file_name = fn1,
                                                              track_name='Project Los Angeles',
                                                              list_of_MIDI_patches=patches
                                                              )
    
    new_fn = fn1+'.mid'
            
    
    audio = midi_to_colab_audio(new_fn, 
                        soundfont_path=soundfont,
                        sample_rate=16000,
                        volume_scale=10,
                        output_for_gradio=True
                        )
    
    print('Done!')
    print('=' * 70)

    #========================================================

    output_midi_title = str(fn1)
    output_midi_summary = str(song_f[:3])
    output_midi = str(new_fn)
    output_audio = (16000, audio)
    
    output_plot = TMIDIX.plot_ms_SONG(song_f, plot_title=output_midi, return_plt=True)

    print('Output MIDI file name:', output_midi)
    print('Output MIDI title:', output_midi_title)
    print('Output MIDI summary:', output_midi_summary)
    print('=' * 70) 
    

    #========================================================
    
    print('-' * 70)
    print('Req end time: {:%Y-%m-%d %H:%M:%S}'.format(datetime.datetime.now(PDT)))
    print('-' * 70)
    print('Req execution time:', (reqtime.time() - start_time), 'sec')

    return output_midi_title, output_midi_summary, output_midi, output_audio, output_plot

# =================================================================================================

if __name__ == "__main__":
    
    PDT = timezone('US/Pacific')
    
    print('=' * 70)
    print('App start time: {:%Y-%m-%d %H:%M:%S}'.format(datetime.datetime.now(PDT)))
    print('=' * 70)

    soundfont = "SGM-v2.01-YamahaGrand-Guit-Bass-v2.7.sf2"

    print('Loading Annotated MIDI Dataset processed scores...')
    seed_melodies_data = TMIDIX.Tegridy_Any_Pickle_File_Reader('processed_scores')
    print('=' * 70)

    print('Loading Annotated MIDI Dataset Classifier Songs Artists Labels...')
    seed_melodies_data = TMIDIX.Tegridy_Any_Pickle_File_Reader('Annotated_MIDI_Dataset_Classifier_Songs_Artists_Labels')
    print('=' * 70)

    app = gr.Blocks()
    with app:
        gr.Markdown("<h1 style='text-align: center; margin-bottom: 1rem'>Advanced MIDI Classifier</h1>")
        gr.Markdown("<h1 style='text-align: center; margin-bottom: 1rem'>Detailed MIDI classification with transformers</h1>")
        gr.Markdown(
            "![Visitors](https://api.visitorbadge.io/api/visitors?path=asigalov61.Advanced-MIDI-Classifier&style=flat)\n\n")
        
        input_midi = gr.File(label="Input MIDI", file_types=[".midi", ".mid", ".kar"])

        run_btn = gr.Button("generate", variant="primary")

        gr.Markdown("## Classification results")

        output_midi_title = gr.Textbox(label="Output MIDI title")
        output_midi_summary = gr.Textbox(label="Output MIDI summary")
        output_audio = gr.Audio(label="Output MIDI audio", format="wav", elem_id="midi_audio")
        output_plot = gr.Plot(label="Output MIDI score plot")
        output_midi = gr.File(label="Output MIDI file", file_types=[".mid"])

        run_event = run_btn.click(ClassifyMIDI, [input_midi],
                                  [output_midi_title, output_midi_summary, output_midi, output_audio, output_plot])

        app.queue().launch()