paddlex 2.1.0__py3-none-any.whl → 3.0.0rc0__py3-none-any.whl

paddlex/ppdet/modeling/mot/utils.py

@@ -1,263 +0,0 @@
-# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import os
-import cv2
-import time
-import numpy as np
-from .visualization import plot_tracking_dict, plot_tracking
-
-__all__ = [
-    'MOTTimer',
-    'Detection',
-    'write_mot_results',
-    'save_vis_results',
-    'load_det_results',
-    'preprocess_reid',
-    'get_crops',
-    'clip_box',
-    'scale_coords',
-]
-
-
-class MOTTimer(object):
-    """
-    This class used to compute and print the current FPS while evaling.
-    """
-
-    def __init__(self):
-        self.total_time = 0.
-        self.calls = 0
-        self.start_time = 0.
-        self.diff = 0.
-        self.average_time = 0.
-        self.duration = 0.
-
-    def tic(self):
-        # using time.time instead of time.clock because time time.clock
-        # does not normalize for multithreading
-        self.start_time = time.time()
-
-    def toc(self, average=True):
-        self.diff = time.time() - self.start_time
-        self.total_time += self.diff
-        self.calls += 1
-        self.average_time = self.total_time / self.calls
-        if average:
-            self.duration = self.average_time
-        else:
-            self.duration = self.diff
-        return self.duration
-
-    def clear(self):
-        self.total_time = 0.
-        self.calls = 0
-        self.start_time = 0.
-        self.diff = 0.
-        self.average_time = 0.
-        self.duration = 0.
-
-
-class Detection(object):
-    """
-    This class represents a bounding box detection in a single image.
-
-    Args:
-        tlwh (Tensor): Bounding box in format `(top left x, top left y,
-            width, height)`.
-        score (Tensor): Bounding box confidence score.
-        feature (Tensor): A feature vector that describes the object
-            contained in this image.
-        cls_id (Tensor): Bounding box category id.
-    """
-
-    def __init__(self, tlwh, score, feature, cls_id):
-        self.tlwh = np.asarray(tlwh, dtype=np.float32)
-        self.score = float(score)
-        self.feature = np.asarray(feature, dtype=np.float32)
-        self.cls_id = int(cls_id)
-
-    def to_tlbr(self):
-        """
-        Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
-        `(top left, bottom right)`.
-        """
-        ret = self.tlwh.copy()
-        ret[2:] += ret[:2]
-        return ret
-
-    def to_xyah(self):
-        """
-        Convert bounding box to format `(center x, center y, aspect ratio,
-        height)`, where the aspect ratio is `width / height`.
-        """
-        ret = self.tlwh.copy()
-        ret[:2] += ret[2:] / 2
-        ret[2] /= ret[3]
-        return ret
-
-
-def write_mot_results(filename, results, data_type='mot', num_classes=1):
-    # support single and multi classes
-    if data_type in ['mot', 'mcmot']:
-        save_format = '{frame},{id},{x1},{y1},{w},{h},{score},{cls_id},-1,-1\n'
-    elif data_type == 'kitti':
-        save_format = '{frame} {id} car 0 0 -10 {x1} {y1} {x2} {y2} -10 -10 -10 -1000 -1000 -1000 -10\n'
-    else:
-        raise ValueError(data_type)
-
-    f = open(filename, 'w')
-    for cls_id in range(num_classes):
-        for frame_id, tlwhs, tscores, track_ids in results[cls_id]:
-            if data_type == 'kitti':
-                frame_id -= 1
-            for tlwh, score, track_id in zip(tlwhs, tscores, track_ids):
-                if track_id < 0: continue
-                if data_type == 'mot':
-                    cls_id = -1
-
-                x1, y1, w, h = tlwh
-                x2, y2 = x1 + w, y1 + h
-                line = save_format.format(
-                    frame=frame_id,
-                    id=track_id,
-                    x1=x1,
-                    y1=y1,
-                    x2=x2,
-                    y2=y2,
-                    w=w,
-                    h=h,
-                    score=score,
-                    cls_id=cls_id)
-                f.write(line)
-    print('MOT results save in {}'.format(filename))
-
-
-def save_vis_results(data,
-                     frame_id,
-                     online_ids,
-                     online_tlwhs,
-                     online_scores,
-                     average_time,
-                     show_image,
-                     save_dir,
-                     num_classes=1):
-    if show_image or save_dir is not None:
-        assert 'ori_image' in data
-        img0 = data['ori_image'].numpy()[0]
-        if online_ids is None:
-            online_im = img0
-        else:
-            if isinstance(online_tlwhs, dict):
-                online_im = plot_tracking_dict(
-                    img0,
-                    num_classes,
-                    online_tlwhs,
-                    online_ids,
-                    online_scores,
-                    frame_id=frame_id,
-                    fps=1. / average_time)
-            else:
-                online_im = plot_tracking(
-                    img0,
-                    online_tlwhs,
-                    online_ids,
-                    online_scores,
-                    frame_id=frame_id,
-                    fps=1. / average_time)
-    if show_image:
-        cv2.imshow('online_im', online_im)
-    if save_dir is not None:
-        cv2.imwrite(
-            os.path.join(save_dir, '{:05d}.jpg'.format(frame_id)), online_im)
-
-
-def load_det_results(det_file, num_frames):
-    assert os.path.exists(det_file) and os.path.isfile(det_file), \
-        '{} is not exist or not a file.'.format(det_file)
-    labels = np.loadtxt(det_file, dtype='float32', delimiter=',')
-    assert labels.shape[1] == 7, \
-        "Each line of {} should have 7 items: '[frame_id],[x0],[y0],[w],[h],[score],[class_id]'.".format(det_file)
-    results_list = []
-    for frame_i in range(num_frames):
-        results = {'bbox': [], 'score': [], 'cls_id': []}
-        lables_with_frame = labels[labels[:, 0] == frame_i + 1]
-        # each line of lables_with_frame:
-        # [frame_id],[x0],[y0],[w],[h],[score],[class_id]
-        for l in lables_with_frame:
-            results['bbox'].append(l[1:5])
-            results['score'].append(l[5:6])
-            results['cls_id'].append(l[6:7])
-        results_list.append(results)
-    return results_list
-
-
-def scale_coords(coords, input_shape, im_shape, scale_factor):
-    # Note: ratio has only one value, scale_factor[0] == scale_factor[1]
-    #
-    # This function only used for JDE YOLOv3 or other detectors with
-    # LetterBoxResize and JDEBBoxPostProcess, coords output from detector had
-    # not scaled back to the origin image.
-
-    ratio = scale_factor[0]
-    pad_w = (input_shape[1] - int(im_shape[1])) / 2
-    pad_h = (input_shape[0] - int(im_shape[0])) / 2
-    coords[:, 0::2] -= pad_w
-    coords[:, 1::2] -= pad_h
-    coords[:, 0:4] /= ratio
-    coords[:, :4] = np.clip(coords[:, :4], a_min=0, a_max=coords[:, :4].max())
-    return coords.round()
-
-
-def clip_box(xyxy, ori_image_shape):
-    H, W = ori_image_shape
-    xyxy[:, 0::2] = np.clip(xyxy[:, 0::2], a_min=0, a_max=W)
-    xyxy[:, 1::2] = np.clip(xyxy[:, 1::2], a_min=0, a_max=H)
-    w = xyxy[:, 2:3] - xyxy[:, 0:1]
-    h = xyxy[:, 3:4] - xyxy[:, 1:2]
-    mask = np.logical_and(h > 0, w > 0)
-    keep_idx = np.nonzero(mask)
-    return xyxy[keep_idx[0]], keep_idx
-
-
-def get_crops(xyxy, ori_img, w, h):
-    crops = []
-    xyxy = xyxy.astype(np.int64)
-    ori_img = ori_img.numpy()
-    ori_img = np.squeeze(
-        ori_img, axis=0).transpose(1, 0, 2)  # [h,w,3]->[w,h,3]
-    for i, bbox in enumerate(xyxy):
-        crop = ori_img[bbox[0]:bbox[2], bbox[1]:bbox[3], :]
-        crops.append(crop)
-    crops = preprocess_reid(crops, w, h)
-    return crops
-
-
-def preprocess_reid(imgs,
-                    w=64,
-                    h=192,
-                    mean=[0.485, 0.456, 0.406],
-                    std=[0.229, 0.224, 0.225]):
-    im_batch = []
-    for img in imgs:
-        img = cv2.resize(img, (w, h))
-        img = img[:, :, ::-1].astype('float32').transpose((2, 0, 1)) / 255
-        img_mean = np.array(mean).reshape((3, 1, 1))
-        img_std = np.array(std).reshape((3, 1, 1))
-        img -= img_mean
-        img /= img_std
-        img = np.expand_dims(img, axis=0)
-        im_batch.append(img)
-    im_batch = np.concatenate(im_batch, 0)
-    return im_batch

paddlex/ppdet/modeling/mot/visualization.py

@@ -1,150 +0,0 @@
-# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import cv2
-import numpy as np
-
-
-def get_color(idx):
-    idx = idx * 3
-    color = ((37 * idx) % 255, (17 * idx) % 255, (29 * idx) % 255)
-    return color
-
-
-def plot_tracking(image,
-                  tlwhs,
-                  obj_ids,
-                  scores=None,
-                  frame_id=0,
-                  fps=0.,
-                  ids2names=[]):
-    im = np.ascontiguousarray(np.copy(image))
-    im_h, im_w = im.shape[:2]
-
-    top_view = np.zeros([im_w, im_w, 3], dtype=np.uint8) + 255
-
-    text_scale = max(1, image.shape[1] / 1600.)
-    text_thickness = 2
-    line_thickness = max(1, int(image.shape[1] / 500.))
-
-    radius = max(5, int(im_w / 140.))
-    cv2.putText(
-        im,
-        'frame: %d fps: %.2f num: %d' % (frame_id, fps, len(tlwhs)),
-        (0, int(15 * text_scale)),
-        cv2.FONT_HERSHEY_PLAIN,
-        text_scale, (0, 0, 255),
-        thickness=2)
-
-    for i, tlwh in enumerate(tlwhs):
-        x1, y1, w, h = tlwh
-        intbox = tuple(map(int, (x1, y1, x1 + w, y1 + h)))
-        obj_id = int(obj_ids[i])
-        id_text = '{}'.format(int(obj_id))
-        if ids2names != []:
-            assert len(
-                ids2names) == 1, "plot_tracking only supports single classes."
-            id_text = '{}_'.format(ids2names[0]) + id_text
-        _line_thickness = 1 if obj_id <= 0 else line_thickness
-        color = get_color(abs(obj_id))
-        cv2.rectangle(
-            im,
-            intbox[0:2],
-            intbox[2:4],
-            color=color,
-            thickness=line_thickness)
-        cv2.putText(
-            im,
-            id_text, (intbox[0], intbox[1] - 10),
-            cv2.FONT_HERSHEY_PLAIN,
-            text_scale, (0, 0, 255),
-            thickness=text_thickness)
-
-        if scores is not None:
-            text = '{:.2f}'.format(float(scores[i]))
-            cv2.putText(
-                im,
-                text, (intbox[0], intbox[1] + 10),
-                cv2.FONT_HERSHEY_PLAIN,
-                text_scale, (0, 255, 255),
-                thickness=text_thickness)
-    return im
-
-
-def plot_tracking_dict(image,
-                       num_classes,
-                       tlwhs_dict,
-                       obj_ids_dict,
-                       scores_dict,
-                       frame_id=0,
-                       fps=0.,
-                       ids2names=[]):
-    im = np.ascontiguousarray(np.copy(image))
-    im_h, im_w = im.shape[:2]
-
-    top_view = np.zeros([im_w, im_w, 3], dtype=np.uint8) + 255
-
-    text_scale = max(1, image.shape[1] / 1600.)
-    text_thickness = 2
-    line_thickness = max(1, int(image.shape[1] / 500.))
-
-    radius = max(5, int(im_w / 140.))
-
-    for cls_id in range(num_classes):
-        tlwhs = tlwhs_dict[cls_id]
-        obj_ids = obj_ids_dict[cls_id]
-        scores = scores_dict[cls_id]
-        cv2.putText(
-            im,
-            'frame: %d fps: %.2f num: %d' % (frame_id, fps, len(tlwhs)),
-            (0, int(15 * text_scale)),
-            cv2.FONT_HERSHEY_PLAIN,
-            text_scale, (0, 0, 255),
-            thickness=2)
-
-        for i, tlwh in enumerate(tlwhs):
-            x1, y1, w, h = tlwh
-            intbox = tuple(map(int, (x1, y1, x1 + w, y1 + h)))
-            obj_id = int(obj_ids[i])
-
-            id_text = '{}'.format(int(obj_id))
-            if ids2names != []:
-                id_text = '{}_{}'.format(ids2names[cls_id], id_text)
-            else:
-                id_text = 'class{}_{}'.format(cls_id, id_text)
-
-            _line_thickness = 1 if obj_id <= 0 else line_thickness
-            color = get_color(abs(obj_id))
-            cv2.rectangle(
-                im,
-                intbox[0:2],
-                intbox[2:4],
-                color=color,
-                thickness=line_thickness)
-            cv2.putText(
-                im,
-                id_text, (intbox[0], intbox[1] - 10),
-                cv2.FONT_HERSHEY_PLAIN,
-                text_scale, (0, 0, 255),
-                thickness=text_thickness)
-
-            if scores is not None:
-                text = '{:.2f}'.format(float(scores[i]))
-                cv2.putText(
-                    im,
-                    text, (intbox[0], intbox[1] + 10),
-                    cv2.FONT_HERSHEY_PLAIN,
-                    text_scale, (0, 255, 255),
-                    thickness=text_thickness)
-    return im

paddlex/ppdet/modeling/necks/__init__.py

@@ -1,30 +0,0 @@
-# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-from . import fpn
-from . import yolo_fpn
-from . import hrfpn
-from . import ttf_fpn
-from . import centernet_fpn
-from . import bifpn
-from . import csp_pan
-
-from .fpn import *
-from .yolo_fpn import *
-from .hrfpn import *
-from .ttf_fpn import *
-from .centernet_fpn import *
-from .blazeface_fpn import *
-from .bifpn import *
-from .csp_pan import *