This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
@aguila, Thank you! Some bugs in proposal layer have been fixed. To make this model work correctly you need to apply changes from a PR https://github.com/opencv/opencv/pull/11221
As you mentioned, we need to modify .prototxt in the following way:
layer {
name: 'm3@ssh_proposal'
# type: 'Python'
type: 'Proposal'
bottom: 'm3@ssh_cls_prob_reshape_output'
bottom: 'm3@ssh_bbox_pred_output'
bottom: 'im_info'
top: 'm3@ssh_boxes'
top: 'm3@ssh_cls_prob'
# python_param {
# module: 'SSH.layers.proposal_layer'
# layer: 'ProposalLayer'
# param_str: "{'feat_stride': 32,'scales': [16,32], 'ratios':[1,]}"
proposal_param {
feat_stride: 32
scale: 16
scale: 32
ratio: 1.0
nms_thresh: 1.0
}
}
...
layer {
name: 'm2@ssh_proposal'
# type: 'Python'
type: 'Proposal'
bottom: 'm2@ssh_cls_prob_reshape_output'
bottom: 'm2@ssh_bbox_pred_output'
bottom: 'im_info'
top: 'm2@ssh_boxes'
top: 'm2@ssh_cls_prob'
# python_param {
# module: 'SSH.layers.proposal_layer'
# layer: 'ProposalLayer'
# param_str: "{'feat_stride': 16,'scales': [4,8], 'ratios':[1,]}"
proposal_param {
feat_stride: 16
scale: 4
scale: 8
ratio: 1.0
nms_thresh: 1.0
}
}
...
layer {
name: 'm1@ssh_proposal'
# type: 'Python'
type: 'Proposal'
bottom: 'm1@ssh_cls_prob_reshape_output'
bottom: 'm1@ssh_bbox_pred_output'
bottom: 'im_info'
top: 'm1@ssh_boxes'
top: 'm1@ssh_cls_prob'
# python_param {
# module: 'SSH.layers.proposal_layer'
# layer: 'ProposalLayer'
# param_str: "{'feat_stride': 8,'scales': [1,2], 'ratios':[1,]}"
proposal_param {
feat_stride: 8
scale: 1
scale: 2
ratio: 1.0
nms_thresh: 1.0
}
}
The most of arguments are mapped correspondingly but nms_thresh: 1.0 is used to disable NMS postprocessing as model's authors did (see https://github.com/mahyarnajibi/SSH/blob/5f41b5c569a3e60720651833b0f804db96f4f20d/SSH/layers/proposal_layer.py#L157)
NOTE: without non-maximum suppression these layers just produce all the predicted bounding boxes (no more than 300 by default). They are sorted by confidence and almost all of them have a quite small confidence close to zero. However if you know that your image has more than 300 faces (that's hardly not possible), add an extra parameter post_nms_topn which equals 300 by default. In example, post_nms_topn: 1000.
To get bounding boxes and scores prediction, run OpenCV:
import cv2 as cv
import numpy as np
imInfo = np.array([224, 224, 1.6], dtype=np.float32)
CONF_THRESH = 0.5
NMS_THRESH = 0.45
net = cv.dnn.readNet('test_ssh.prototxt', 'SSH.caffemodel')
img = cv.imread('/path/to/image)
imgHeight = img.shape[0]
imgWidth = img.shape[1]
inp = cv.dnn.blobFromImage(img, 1.0, (224, 224), (102.9801, 115.9465, 122.7717), False, False)
net.setInput(inp)
net.setInput(imInfo, 'im_info')
outs = net.forward(['ssh_cls_prob', 'ssh_boxes'])
Then you need to apply NMS to filter predicted faces:
scores = outs[0].flatten().tolist()
boxes = []
for box in outs[1]:
left = int(box[1] / 224 * imgWidth)
top = int(box[2] / 224 * imgHeight)
right = int(box[3] / 224 * imgWidth)
bottom = int(box[4] / 224 * imgHeight)
boxes.append([left, top, right - left + 1, bottom - top + 1])
ids = cv.dnn.NMSBoxes(boxes, scores, CONF_THRESH, NMS_THRESH)
for idx in ids:
idx = idx[0]
score = scores[idx]
box = boxes[idx]
left = box[0]
top = box[1]
right = left + box[2] - 1
bottom = top + box[3] - 1
cv.rectangle(img, (left, top), (right, bottom), (0, 255, 0))
cv.imshow('ssh', img)
cv.waitKey()
| | 2 | No.2 Revision |
@aguila, Thank you! Some bugs in proposal layer have been fixed. To make this model work correctly you need to apply changes from a PR https://github.com/opencv/opencv/pull/11221
As you mentioned, we need to modify .prototxt in the following way:
layer {
name: 'm3@ssh_proposal'
# type: 'Python'
type: 'Proposal'
bottom: 'm3@ssh_cls_prob_reshape_output'
bottom: 'm3@ssh_bbox_pred_output'
bottom: 'im_info'
top: 'm3@ssh_boxes'
top: 'm3@ssh_cls_prob'
# python_param {
# module: 'SSH.layers.proposal_layer'
# layer: 'ProposalLayer'
# param_str: "{'feat_stride': 32,'scales': [16,32], 'ratios':[1,]}"
proposal_param {
feat_stride: 32
scale: 16
scale: 32
ratio: 1.0
nms_thresh: 1.0
}
}
...
layer {
name: 'm2@ssh_proposal'
# type: 'Python'
type: 'Proposal'
bottom: 'm2@ssh_cls_prob_reshape_output'
bottom: 'm2@ssh_bbox_pred_output'
bottom: 'im_info'
top: 'm2@ssh_boxes'
top: 'm2@ssh_cls_prob'
# python_param {
# module: 'SSH.layers.proposal_layer'
# layer: 'ProposalLayer'
# param_str: "{'feat_stride': 16,'scales': [4,8], 'ratios':[1,]}"
proposal_param {
feat_stride: 16
scale: 4
scale: 8
ratio: 1.0
nms_thresh: 1.0
}
}
...
layer {
name: 'm1@ssh_proposal'
# type: 'Python'
type: 'Proposal'
bottom: 'm1@ssh_cls_prob_reshape_output'
bottom: 'm1@ssh_bbox_pred_output'
bottom: 'im_info'
top: 'm1@ssh_boxes'
top: 'm1@ssh_cls_prob'
# python_param {
# module: 'SSH.layers.proposal_layer'
# layer: 'ProposalLayer'
# param_str: "{'feat_stride': 8,'scales': [1,2], 'ratios':[1,]}"
proposal_param {
feat_stride: 8
scale: 1
scale: 2
ratio: 1.0
nms_thresh: 1.0
}
}
The most of arguments are mapped correspondingly but nms_thresh: 1.0 is used to disable NMS postprocessing as model's authors did (see https://github.com/mahyarnajibi/SSH/blob/5f41b5c569a3e60720651833b0f804db96f4f20d/SSH/layers/proposal_layer.py#L157)
NOTE: without non-maximum suppression these layers just produce all the predicted bounding boxes (no more than 300 by default). They are sorted by confidence and almost all of them have a quite small confidence close to zero. However if you know that your image has more than 300 faces (that's hardly not possible), add an extra parameter post_nms_topn which equals 300 by default. In example, post_nms_topn: 1000.
To get bounding boxes and scores prediction, run OpenCV:
import cv2 as cv
import numpy as np
imInfo = np.array([224, 224, 1.6], dtype=np.float32)
CONF_THRESH = 0.5
NMS_THRESH = 0.45
net = cv.dnn.readNet('test_ssh.prototxt', 'SSH.caffemodel')
img = cv.imread('/path/to/image)
cv.imread('/path/to/image')
imgHeight = img.shape[0]
imgWidth = img.shape[1]
inp = cv.dnn.blobFromImage(img, 1.0, (224, 224), (102.9801, 115.9465, 122.7717), False, False)
net.setInput(inp)
net.setInput(imInfo, 'im_info')
outs = net.forward(['ssh_cls_prob', 'ssh_boxes'])
Then you need to apply NMS to filter predicted faces:
scores = outs[0].flatten().tolist()
boxes = []
for box in outs[1]:
left = int(box[1] / 224 * imgWidth)
top = int(box[2] / 224 * imgHeight)
right = int(box[3] / 224 * imgWidth)
bottom = int(box[4] / 224 * imgHeight)
boxes.append([left, top, right - left + 1, bottom - top + 1])
ids = cv.dnn.NMSBoxes(boxes, scores, CONF_THRESH, NMS_THRESH)
for idx in ids:
idx = idx[0]
score = scores[idx]
box = boxes[idx]
left = box[0]
top = box[1]
right = left + box[2] - 1
bottom = top + box[3] - 1
cv.rectangle(img, (left, top), (right, bottom), (0, 255, 0))
cv.imshow('ssh', img)
cv.waitKey()