修改midi2img库img2midi代码批量处理samples文件夹图片生成MIDI

修改后完整代码 #

from PIL import Image
import numpy as np
from music21 import instrument, note, chord, stream
import os
import sys

lowerBoundNote = 21
def column2notes(column):
    notes = []
    for i in range(len(column)):
        if column[i] > 255/2:
            notes.append(i+lowerBoundNote)
    return notes

resolution = 0.25
def updateNotes(newNotes,prevNotes): 
    res = {} 
    for note in newNotes:
        if note in prevNotes:
            res[note] = prev_notes[note] + resolution
        else:
            res[note] = resolution
    return res

def image2midi(image_path):
    with Image.open(image_path) as image:
        im_arr = np.fromstring(image.tobytes(), dtype=np.uint8)
        try:
            im_arr = im_arr.reshape((image.size[1], image.size[0]))
        except:
            im_arr = im_arr.reshape((image.size[1], image.size[0],3))
            im_arr = np.dot(im_arr, [0.33, 0.33, 0.33])

    """ convert the output from the prediction to notes and create a midi file
        from the notes """
    offset = 0
    output_notes = []

    # create note and chord objects based on the values generated by the model

    prev_notes = updateNotes(im_arr.T[0,:],{})
    for column in im_arr.T[1:,:]:
        notes = column2notes(column)
        # pattern is a chord
        notes_in_chord = notes
        old_notes = prev_notes.keys()
        for old_note in old_notes:
            if not old_note in notes_in_chord:
                new_note = note.Note(old_note,quarterLength=prev_notes[old_note])
                new_note.storedInstrument = instrument.Piano()
                if offset - prev_notes[old_note] >= 0:
                    new_note.offset = offset - prev_notes[old_note]
                    output_notes.append(new_note)
                elif offset == 0:
                    new_note.offset = offset
                    output_notes.append(new_note)                    
                else:
                    print(offset,prev_notes[old_note],old_note)

        prev_notes = updateNotes(notes_in_chord,prev_notes)

        # increase offset each iteration so that notes do not stack
        offset += resolution

    for old_note in prev_notes.keys():
        new_note = note.Note(old_note,quarterLength=prev_notes[old_note])
        new_note.storedInstrument = instrument.Piano()
        new_note.offset = offset - prev_notes[old_note]

        output_notes.append(new_note)

    prev_notes = updateNotes(notes_in_chord,prev_notes)

    midi_stream = stream.Stream(output_notes)
    # 优化文件名生成逻辑，适配所有常见图片后缀
    img_filename = os.path.basename(image_path)
    midi_filename = os.path.splitext(img_filename)[0] + ".mid"
    midi_stream.write('midi', fp=midi_filename)

if __name__ == "__main__":
    # 默认读取samples文件夹，也支持通过命令行参数指定其他文件夹路径
    img_dir = sys.argv[1] if len(sys.argv) > 1 else "samples"
    # 支持的图片格式
    support_ext = (".png", ".jpg", ".jpeg", ".bmp")
    # 遍历目录下所有文件
    for filename in os.listdir(img_dir):
        if filename.lower().endswith(support_ext):
            img_path = os.path.join(img_dir, filename)
            print(f"正在处理：{img_path}")
            image2midi(img_path)
    print("所有图片处理完成")

修改说明 #

• 新增os模块导入，用于目录遍历和文件路径处理
• 优化了MIDI文件名生成逻辑，不再仅支持jpeg格式，自动适配所有常见图片后缀
• 替换原有的单文件读取逻辑，默认自动遍历samples目录下的所有符合格式的图片，也支持通过命令行参数指定其他图片文件夹路径
• 新增处理进度提示，控制台会打印当前正在处理的文件路径，处理完成后会给出提示

使用方法 #

直接在终端运行以下命令即可自动处理samples文件夹下的所有图片：

python img2midi.py

如果需要指定其他图片文件夹，也可以传入文件夹路径作为参数：

python img2midi.py 你的图片文件夹路径

内容的提问来源于stack exchange，提问作者mohamed mostapha