faster rcnn python layer学习

学习ｆａｓｔ ｒｎｎ 里面代码的目的是为了熟悉ｃａｆｆｅ的ｐｙｔｈｏｎ接口，以及Python Layer的书写方式。

下面就以ｆａｓｔ rcnn里面的RoIDataLayer层入手逐步学习：

class RoIDataLayer(caffe.Layer):
"""Fast R-CNN data layer used for training."""

def _shuffle_roidb_inds(self):
"""Randomly permute the training roidb."""
self._perm = np.random.permutation(np.arange(len(self._roidb)))
self._cur = 0

def _get_next_minibatch_inds(self):
"""Return the roidb indices for the next minibatch."""
if self._cur + cfg.TRAIN.IMS_PER_BATCH >= len(self._roidb):
self._shuffle_roidb_inds()

db_inds = self._perm[self._cur:self._cur + cfg.TRAIN.IMS_PER_BATCH]
self._cur += cfg.TRAIN.IMS_PER_BATCH
return db_inds

def _get_next_minibatch(self):
"""Return the blobs to be used for the next minibatch.

If cfg.TRAIN.USE_PREFETCH is True, then blobs will be computed in a
separate process and made available through self._blob_queue.
"""
if cfg.TRAIN.USE_PREFETCH:
return self._blob_queue.get()
else:
db_inds = self._get_next_minibatch_inds()
minibatch_db = [self._roidb[i] for i in db_inds]
return get_minibatch(minibatch_db, self._num_classes)

def set_roidb(self, roidb):
"""Set the roidb to be used by this layer during training."""
self._roidb = roidb
self._shuffle_roidb_inds()
if cfg.TRAIN.USE_PREFETCH:
self._blob_queue = Queue(10)
self._prefetch_process = BlobFetcher(self._blob_queue,
self._roidb,
self._num_classes)
self._prefetch_process.start()
# Terminate the child process when the parent exists
def cleanup():
print 'Terminating BlobFetcher'
self._prefetch_process.terminate()
self._prefetch_process.join()
import atexit
atexit.register(cleanup)
　　　#这个函数相当于ｃａｆｆｅ　ｃ＋＋接口的ＳｅｔＵｐ
def setup(self, bottom, top):
"""Setup the RoIDataLayer."""

# parse the layer parameter string, which must be valid YAML
#下面的这句的作用是解析输入的参数（输入的参数是ｐｙｔｈｏｎ字典的形式的字符串），通过下面的函数就生成ｌａｙｅｒ_params这个字典变量
layer_params = yaml.load(self.param_str_)

self._num_classes = layer_params['num_classes']

self._name_to_top_map = {
'data': 0,
'rois': 1,
'labels': 2}

# data blob: holds a batch of N images, each with 3 channels
# The height and width (100 x 100) are dummy values
top[0].reshape(1, 3, 100, 100)

# rois blob: holds R regions of interest, each is a 5-tuple
# (n, x1, y1, x2, y2) specifying an image batch index n and a
# rectangle (x1, y1, x2, y2)　ｒｅｇｉｏｎ of interest 这个表示ｆａｓｔ　ｒｃｎｎ使用的预选框（ｓｅｌｅｃｔ　ｓｅａｒｃｈ）
top[1].reshape(1, 5)

# labels blob: R categorical labels in [0, ..., K] for K foreground
# classes plus background
top[2].reshape(1)
　　　　　#训练的时候需要输出ｇｒｏｕｎｄ　ｔｒｕｔｈ和ｂｏｕｎｄｉｎｇ　ｂｏｘ的ｌｏｓｓ权重
if cfg.TRAIN.BBOX_REG:
self._name_to_top_map['bbox_targets'] = 3
self._name_to_top_map['bbox_loss_weights'] = 4

# bbox_targets blob: R bounding-box regression targets with 4
# targets per class
top[3].reshape(1, self._num_classes * 4)

# bbox_loss_weights blob: At most 4 targets per roi are active;
# thisbinary vector sepcifies the subset of active targets
top[4].reshape(1, self._num_classes * 4)

def forward(self, bottom, top):
"""Get blobs and copy them into this layer's top blob vector."""
blobs = self._get_next_minibatch()
#字典的遍历方式
for blob_name, blob in blobs.iteritems():
top_ind = self._name_to_top_map[blob_name]
# Reshape net's input blobs
top[top_ind].reshape(*(blob.shape))
# Copy data into net's input blobs
top[top_ind].data[...] = blob.astype(np.float32, copy=False)

def backward(self, top, propagate_down, bottom):
"""This layer does not propagate gradients."""
pass

def reshape(self, bottom, top):
"""Reshaping happens during the call to forward."""
pass

小总结：

现在使用ｃａｆｆｅ做目标检测，通常存放ｂｏｕｎｄｉｎｇ ｂｏｘ都是使用ｂａｔｃｈ的ｉｄｘ后面在加ｂｏｕｎｄｉｎｇ box

，在加ｌａｂｅｌ