我正在尝试使用 keras 测试经过训练的 cnn 模型,但是当我运行代码时,出现错误:
expected inputs to have 4 dimensions, but got array with shape (32, 549, 1).
那 (32,549,1) 是我用来训练和测试我的 cnn 并获得良好结果的对数频谱图的大小。除了最后一个错误。
我尝试使用 np.rezise(-1, amp) 和 y=(-1, amp) 来尝试增加我的向量,但它不起作用,我真的不知道该怎么做。
DIR = 'C:/Users/ROBERTO VILCHEZ/Desktop/Redes/TRAIN/ayuda/ayuda_1.wav'
SAMPLE_RATE = 88200
model=load_model('C:/Users/ROBERTO VILCHEZ/Desktop/Redes/mi_modelo.h5')
def read_wav_file(x):
_, wav = wavfile.read(x)
# Normalize
wav = wav.astype(np.float32) / np.iinfo(np.int16).max
return wav
def log_spectrogram(wav):
freqs, times, spec = stft(wav, SAMPLE_RATE, nperseg = 400, noverlap = 240, nfft = 512, padded = False, boundary = None)
# Log spectrogram
amp = np.log(np.abs(spec)+1e-10)
return freqs, times, amp
threshold_freq=5500
eps=1e-10
x=DIR
wav = read_wav_file(x)
L = 88200
if len(wav) > L:
i = np.random.randint(0, len(wav) - L)
wav = wav[i:(i+L)]
elif len(wav) < L:
rem_len = L - len(wav)
silence_part = np.random.randint(-100,100,88200).astype(np.float32) /
np.iinfo(np.int16).max
j = np.random.randint(0, rem_len)
silence_part_left = silence_part[0:j]
silence_part_right = silence_part[j:rem_len]
wav = np.concatenate([silence_part_left, wav, silence_part_right])
freqs, times, spec = stft(wav, L, nperseg = 400, noverlap = 240, nfft =
512, padded = False, boundary = None)
if threshold_freq is not None:
spec = spec[freqs <= threshold_freq,:]
freqs = freqs[freqs <= threshold_freq]
amp = np.log(np.abs(spec)+eps)
y = np.expand_dims(amp, axis=3)
res = model.predict(y)
所有其余代码都工作正常,但只有最后一部分告诉我错误预期输入有 4 个维度,但得到形状为 (32, 549, 1) 的数组。
完全错误:
Traceback (most recent call last): File "C:\Users\ROBERTO VILCHEZ\Desktop\Redes\prueba.py", line 76, in <module> res = model.predict(y) File "C:\Users\ROBERTO VILCHEZ\AppData\Roaming\Python\Python36\site-packages\keras\engine\training.py", line 1149, in predict x, _, _ = self._standardize_user_data(x) File "C:\Users\ROBERTO VILCHEZ\AppData\Roaming\Python\Python36\site-packages\keras\engine\training.py", line 751, in _standardize_user_data exception_prefix='input') File "C:\Users\ROBERTO VILCHEZ\AppData\Roaming\Python\Python36\site-packages\keras\engine\training_utils.py", line 128, in standardize_input_data 'with shape ' + str(data_shape))
ValueError:检查输入时出错:预期输入有 4 尺寸,但得到形状为 (32, 549, 1) 的数组
请您参考如下方法:
如果您只想预测一个输入,则需要将测试数据扩展为 (Batch_size, .., .., ..)。
所以这里如果你的 y 的形状是 (32, 549, 1),做一个简单的:
y = np.expand_dims(y, axis=0) # y shape = (1, 32, 549, 1)
Ans 然后运行您的预测。
