-
Notifications
You must be signed in to change notification settings - Fork 2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Reland Reland "Port DW Pose preprocessor" (#1892)
* Port DW Pose preprocessor (#1856) * ➕ Add dependencies * 🚧 wip * 🚧 wip * 🚧 download models * 🚧 Minor fixes * 🔧 update gitignore * 🐛 Fix normalization issue * 🚧 load DW model only when DW preprocessor is selected * ✅ Change test config * 🎨 nits * 🐛 Fix A1111 safe torch issue 📝 v1.1.235 (#1859) Revert "Port DW Pose preprocessor (#1856)" (#1860) This reverts commit 0d3310f. Reland "Port DW Pose preprocessor" (#1861) * Revert "Revert "Port DW Pose preprocessor (#1856)" (#1860)" This reverts commit 17e100e. * 🐛 Fix install.py 📝 v1.1.236 (#1862) :bug: Delay import of mmpose (#1866) :memo: v1.1.237 (#1868) :bug: Fix all keypoints invalid issue (#1871) :bug: lazy import :construction: update test expectation :construction: Switch to onnx :construction: solve onnx package issue :wrench: Check cuda in more efficient way :art: Format code :wrench: Make onnx runtime optional * Use cv2 to load and run model on cpu * nit
- Loading branch information
Showing
14 changed files
with
703 additions
and
41 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,124 @@ | ||
import cv2 | ||
import numpy as np | ||
|
||
def nms(boxes, scores, nms_thr): | ||
"""Single class NMS implemented in Numpy.""" | ||
x1 = boxes[:, 0] | ||
y1 = boxes[:, 1] | ||
x2 = boxes[:, 2] | ||
y2 = boxes[:, 3] | ||
|
||
areas = (x2 - x1 + 1) * (y2 - y1 + 1) | ||
order = scores.argsort()[::-1] | ||
|
||
keep = [] | ||
while order.size > 0: | ||
i = order[0] | ||
keep.append(i) | ||
xx1 = np.maximum(x1[i], x1[order[1:]]) | ||
yy1 = np.maximum(y1[i], y1[order[1:]]) | ||
xx2 = np.minimum(x2[i], x2[order[1:]]) | ||
yy2 = np.minimum(y2[i], y2[order[1:]]) | ||
|
||
w = np.maximum(0.0, xx2 - xx1 + 1) | ||
h = np.maximum(0.0, yy2 - yy1 + 1) | ||
inter = w * h | ||
ovr = inter / (areas[i] + areas[order[1:]] - inter) | ||
|
||
inds = np.where(ovr <= nms_thr)[0] | ||
order = order[inds + 1] | ||
|
||
return keep | ||
|
||
def multiclass_nms(boxes, scores, nms_thr, score_thr): | ||
"""Multiclass NMS implemented in Numpy. Class-aware version.""" | ||
final_dets = [] | ||
num_classes = scores.shape[1] | ||
for cls_ind in range(num_classes): | ||
cls_scores = scores[:, cls_ind] | ||
valid_score_mask = cls_scores > score_thr | ||
if valid_score_mask.sum() == 0: | ||
continue | ||
else: | ||
valid_scores = cls_scores[valid_score_mask] | ||
valid_boxes = boxes[valid_score_mask] | ||
keep = nms(valid_boxes, valid_scores, nms_thr) | ||
if len(keep) > 0: | ||
cls_inds = np.ones((len(keep), 1)) * cls_ind | ||
dets = np.concatenate( | ||
[valid_boxes[keep], valid_scores[keep, None], cls_inds], 1 | ||
) | ||
final_dets.append(dets) | ||
if len(final_dets) == 0: | ||
return None | ||
return np.concatenate(final_dets, 0) | ||
|
||
def demo_postprocess(outputs, img_size, p6=False): | ||
grids = [] | ||
expanded_strides = [] | ||
strides = [8, 16, 32] if not p6 else [8, 16, 32, 64] | ||
|
||
hsizes = [img_size[0] // stride for stride in strides] | ||
wsizes = [img_size[1] // stride for stride in strides] | ||
|
||
for hsize, wsize, stride in zip(hsizes, wsizes, strides): | ||
xv, yv = np.meshgrid(np.arange(wsize), np.arange(hsize)) | ||
grid = np.stack((xv, yv), 2).reshape(1, -1, 2) | ||
grids.append(grid) | ||
shape = grid.shape[:2] | ||
expanded_strides.append(np.full((*shape, 1), stride)) | ||
|
||
grids = np.concatenate(grids, 1) | ||
expanded_strides = np.concatenate(expanded_strides, 1) | ||
outputs[..., :2] = (outputs[..., :2] + grids) * expanded_strides | ||
outputs[..., 2:4] = np.exp(outputs[..., 2:4]) * expanded_strides | ||
|
||
return outputs | ||
|
||
def preprocess(img, input_size, swap=(2, 0, 1)): | ||
if len(img.shape) == 3: | ||
padded_img = np.ones((input_size[0], input_size[1], 3), dtype=np.uint8) * 114 | ||
else: | ||
padded_img = np.ones(input_size, dtype=np.uint8) * 114 | ||
|
||
r = min(input_size[0] / img.shape[0], input_size[1] / img.shape[1]) | ||
resized_img = cv2.resize( | ||
img, | ||
(int(img.shape[1] * r), int(img.shape[0] * r)), | ||
interpolation=cv2.INTER_LINEAR, | ||
).astype(np.uint8) | ||
padded_img[: int(img.shape[0] * r), : int(img.shape[1] * r)] = resized_img | ||
|
||
padded_img = padded_img.transpose(swap) | ||
padded_img = np.ascontiguousarray(padded_img, dtype=np.float32) | ||
return padded_img, r | ||
|
||
def inference_detector(session, oriImg): | ||
input_shape = (640,640) | ||
img, ratio = preprocess(oriImg, input_shape) | ||
|
||
input = img[None, :, :, :] | ||
outNames = session.getUnconnectedOutLayersNames() | ||
session.setInput(input) | ||
output = session.forward(outNames) | ||
|
||
predictions = demo_postprocess(output[0], input_shape)[0] | ||
|
||
boxes = predictions[:, :4] | ||
scores = predictions[:, 4:5] * predictions[:, 5:] | ||
|
||
boxes_xyxy = np.ones_like(boxes) | ||
boxes_xyxy[:, 0] = boxes[:, 0] - boxes[:, 2]/2. | ||
boxes_xyxy[:, 1] = boxes[:, 1] - boxes[:, 3]/2. | ||
boxes_xyxy[:, 2] = boxes[:, 0] + boxes[:, 2]/2. | ||
boxes_xyxy[:, 3] = boxes[:, 1] + boxes[:, 3]/2. | ||
boxes_xyxy /= ratio | ||
dets = multiclass_nms(boxes_xyxy, scores, nms_thr=0.45, score_thr=0.1) | ||
if dets is not None: | ||
final_boxes, final_scores, final_cls_inds = dets[:, :4], dets[:, 4], dets[:, 5] | ||
isscore = final_scores>0.3 | ||
iscat = final_cls_inds == 0 | ||
isbbox = [ i and j for (i, j) in zip(isscore, iscat)] | ||
final_boxes = final_boxes[isbbox] | ||
|
||
return final_boxes |
Oops, something went wrong.