Yolo V1单级单盒训练

发布于 2025-02-12 08:06:39 字数 1458 浏览 1 评论 0原文

我是 cnns 和对象检测模型的新手。因此，我试图基于 yolo yolo v1 v1 v1 from

我的想法是让s = 7个单元格一个仅B = 1个单元格。此外，我只对检测一个课程感兴趣。然后，每个单元格包含一个预测，例如[p，x，y，w，h]，y_train具有尺寸[7x7x5]。

我正在 colaBoRagoratoration 带有 keras 。完整的代码可以在我的github存储库中找到：“ https：//github.com/frapasti/human hands.git”

我已经深入研究了论文。

我的问题是，损失在训练的早期就出现了，模型仅输出NAN。

这是我使用过的自定义损失：

import keras.backend as K

def custom_loss(y_true, y_pred):
  yes_obj = y_true[..., 0]

  lxy = K.sum((K.square(y_pred[..., 1] - y_true[..., 1]) + K.square(y_pred[..., 2] - y_true[..., 2]))*yes_obj)
  lwh = K.sum((K.square(K.sqrt(y_pred[..., 3]) - K.sqrt(y_true[..., 3])) + K.square(K.sqrt(y_pred[..., 4]) - K.sqrt(y_true[..., 4])))*yes_obj)
  lp = K.sum(K.square(y_true[..., 0] - y_pred[..., 0])*yes_obj)

  return lxy + lwh + lp

yolo.compile(loss=custom_loss, optimizer='adam', metrics=['accuracy'])
yolo.fit(X_train, Y_train, batch_size=25, epochs=5, verbose=1)

我真的不明白为什么... 我已经跳过了卷积层的预训练，而我认为这不是引起问题的原因。

原文

I'm rather new to CNNs and object detection models.
For this reason I'm trying to implement an object detection model based on YOLO v1 from scratch.

My idea is to have S = 7 cells an just B = 1 box per cell.
Furthermore, I'm only interested in detecting one class. Each cell then contains a prediction like [P, x, y, w, h] and y_train has dimensions [7x7x5].

I'm implementing the model on Colaboratory with Keras. The full code can be found in my GitHub repository: "https://github.com/frapasti/Human-Hands.git"

I've deeply studied the paper.

My problem is that the loss diverges early in the training and the model outputs only NaN.

Here's the custom loss that I've used:

import keras.backend as K

def custom_loss(y_true, y_pred):
  yes_obj = y_true[..., 0]

  lxy = K.sum((K.square(y_pred[..., 1] - y_true[..., 1]) + K.square(y_pred[..., 2] - y_true[..., 2]))*yes_obj)
  lwh = K.sum((K.square(K.sqrt(y_pred[..., 3]) - K.sqrt(y_true[..., 3])) + K.square(K.sqrt(y_pred[..., 4]) - K.sqrt(y_true[..., 4])))*yes_obj)
  lp = K.sum(K.square(y_true[..., 0] - y_pred[..., 0])*yes_obj)

  return lxy + lwh + lp

yolo.compile(loss=custom_loss, optimizer='adam', metrics=['accuracy'])
yolo.fit(X_train, Y_train, batch_size=25, epochs=5, verbose=1)

I really don't understand why...
I've skipped the pre-training of the convolutional layer on just classification, but I don't think that's what causes the problem.

分享到QQ

分享到微博