PixelCNN 训练错误“keepdims”答案

【问题标题】：PixelCNN training error 'keepdims'PixelCNN 训练错误“keepdims”
【发布时间】：2023-03-12 10:30:01
【问题描述】：

尝试使用 PixelCNN 我收到以下输入参数错误：

C:\Users\cknau\Downloads\pixel-cnn-master\pixel-cnn-master>python train2.py
input args:
 {
    "data_dir":"D:\\PixelCNN\\dataset",
    "save_dir":"D:\\PixelCNN\\samples",
    "data_set":"cifar",
    "save_interval":20,
    "load_params":false,
    "nr_resnet":5,
    "nr_filters":160,
    "nr_logistic_mix":10,
    "resnet_nonlinearity":"concat_elu",
    "class_conditional":false,
    "energy_distance":false,
    "learning_rate":0.001,
    "lr_decay":0.999995,
    "batch_size":16,
    "init_batch_size":16,
    "dropout_p":0.5,
    "max_epochs":5000,
    "nr_gpu":8,
    "polyak_decay":0.9995,
    "num_samples":1,
    "seed":1
}

错误：

T

raceback (most recent call last):
      File "train2.py", line 120, in <module>
        loss_gen.append(loss_fun(tf.stop_gradient(xs[i]), out))
      File "C:\Users\cknau\Downloads\pixel-cnn-master\pixel-cnn-master\pixel_cnn_pp\nn.py", line 83, in discretized_mix_logistic_loss
        log_probs = tf.reduce_sum(log_probs,3) + log_prob_from_logits(logit_probs)
      File "C:\Users\cknau\Downloads\pixel-cnn-master\pixel-cnn-master\pixel_cnn_pp\nn.py", line 27, in log_prob_from_logits
        m = tf.reduce_max(x, axis, keepdims=True)
    TypeError: reduce_max() got an unexpected keyword argument 'keepdims'

谁能帮帮我？我有 NumPy 1.13，所以这不是问题。

【问题讨论】：

标签： python numpy artificial-intelligence

【解决方案1】：

我猜你的 tensorflow 版本可能与 Pixelnet 不兼容正如keep_dims: Deprecated alias for keepdims. 所描述的here，也许你有一个像0.rxx 这样的旧版本，尝试升级tf 或从keepdims to keep_dims 更改关键字

【讨论】：

【解决方案2】：

我正在使用 facenet，我已经更改了 detect_face.py 文件中的 softmax 函数。

正确的代码是：

@layer
def softmax(self, target, axis, name=None):
        max_axis = tf.reduce_max(target, axis, keep_dims =True)
        target_exp = tf.exp(target-max_axis)
        normalize = tf.reduce_sum(target_exp, axis, keep_dims =True)
        softmax = tf.div(target_exp, normalize, name)
        return softmax

【讨论】：