渴望在Muliti级数据准备和可视化上进行射击对象检测

Question

我遵循此

应该直接扩展此操作以处理多个类。

但是失败了。感谢您的帮助！

数据预定：

# By convention, our non-background classes start counting at 1.  Given
# that we will be predicting just one class, we will therefore assign it a
# `class id` of 1.
duck_class_id = 1
num_classes = 1

category_index = {duck_class_id: {'id': duck_class_id, 'name': 'rubber_ducky'}}

# Convert class labels to one-hot; convert everything to tensors.
# The `label_id_offset` here shifts all classes by a certain number of indices;
# we do this here so that the model receives one-hot labels where non-background
# classes start counting at the zeroth index.  This is ordinarily just handled
# automatically in our training binaries, but we need to reproduce it here.
label_id_offset = 1
train_image_tensors = []
gt_classes_one_hot_tensors = []
gt_box_tensors = []
for (train_image_np, gt_box_np) in zip(
    train_images_np, gt_boxes):
  train_image_tensors.append(tf.expand_dims(tf.convert_to_tensor(
      train_image_np, dtype=tf.float32), axis=0))
  gt_box_tensors.append(tf.convert_to_tensor(gt_box_np, dtype=tf.float32))
  zero_indexed_groundtruth_classes = tf.convert_to_tensor(
      np.ones(shape=[gt_box_np.shape[0]], dtype=np.int32) - label_id_offset)
  gt_classes_one_hot_tensors.append(tf.one_hot(
      zero_indexed_groundtruth_classes, num_classes))
print('Done prepping data.')

我认为问题是 Zero_indexed_groundTruth_classes ，如果有三个类，并且映射如何更改此行

zero_indexed_groundtruth_classes = tf.convert_to_tensor(
      np.ones(shape=[gt_box_np.shape[0]], dtype=np.int32) - label_id_offset)

数据可视化：

如何更改可视化代码相应？

dummy_scores = np.array([1.0], dtype=np.float32)  # give boxes a score of 100%

plt.figure(figsize=(30, 15))
for idx in range(5):
  plt.subplot(2, 3, idx+1)
  plot_detections(
      train_images_np[idx],
      gt_boxes[idx],
      np.ones(shape=[gt_boxes[idx].shape[0]], dtype=np.int32),
      dummy_scores, category_index)
plt.show()

非常

category_index = {
    1: {'id': 1, 'name': 'a'},
    2: {'id': 2, 'name': 'b'},
    3: {'id': 2, 'name': 'c'}
}

num_classes = 3
 
and three pictures that No.1 has five boxes as a,b,b,c,c;
                        No.2 has two boxes as a,a; 
                        No.3 has four boxes as a,b,c,a.

感谢！

Answer 1

对于多个类，您只需创建一个带有类的数组，然后将数组传递到该代码的这一部分，

for (train_image_np, gt_box_np, gt_class) in zip(train_images_np, gt_boxes, gt_classes):
    train_image_tensors.append(tf.expand_dims(tf.convert_to_tensor(train_image_np, dtype=tf.float32), axis=0))
    gt_box_tensors.append(tf.convert_to_tensor(gt_box_np, dtype=tf.float32))
    
    gt_classes_one_hot_tensors.append(tf.one_hot([gt_class], num_classes))

其中gt_classes = [1,1,1 ...，2,2,2，]，根据类的数量。这将帮助您进行多类对象检测。

如果您有其他疑问，您可以联系