megadetector 5.0.5__py3-none-any.whl → 5.0.7__py3-none-any.whl

taxonomy_mapping/species_lookup.py

@@ -36,14 +36,23 @@ taxonomy_urls = {
 }
 
 files_to_unzip = {
-    'GBIF': ['backbone/Taxon.tsv', 'backbone/VernacularName.tsv'],
+    # GBIF used to put everything in a "backbone" folder within the zipfile, but as of
+    # 12.2023, this is no longer the case.
+    # 'GBIF': ['backbone/Taxon.tsv', 'backbone/VernacularName.tsv'],
+    'GBIF': ['Taxon.tsv', 'VernacularName.tsv'],
     'iNaturalist': ['taxa.csv']
 }
 
 # As of 2020.05.12:
 #
 # GBIF: ~777MB zipped, ~1.6GB taxonomy
-# iNat: ~2.2GB zipped, ~51MB taxonomy
+# iNat: ~2.2GB zipped, ~51MB taxonomy (most of the zipfile is observations)
+
+# As of 2023.12.29:
+#
+# GBIF: ~948MB zipped, ~2.2GB taxonomy
+# iNat: ~6.7GB zipped, ~62MB taxonomy (most of the zipfile is observations)
+
 
 os.makedirs(taxonomy_download_dir, exist_ok=True)
 for taxonomy_name in taxonomy_urls:
@@ -99,15 +108,16 @@ def initialize_taxonomy_lookup(force_init=False) -> None:
         gbif_taxon_id_to_scientific,\
         gbif_scientific_to_taxon_id
 
+
     ## Load serialized taxonomy info if we've already saved it
 
     if (not force_init) and (inat_taxonomy is not None):
         print('Skipping taxonomy re-init')
         return
     
-    if os.path.isfile(serialized_structures_file):
+    if (not force_init) and (os.path.isfile(serialized_structures_file)):
 
-        print(f'Reading taxonomy data from {serialized_structures_file}')
+        print(f'De-serializing taxonomy data from {serialized_structures_file}')
 
         with open(serialized_structures_file, 'rb') as f:
             structures_to_serialize = pickle.load(f)
@@ -125,6 +135,7 @@ def initialize_taxonomy_lookup(force_init=False) -> None:
         gbif_vernacular_to_taxon_id,\
         gbif_taxon_id_to_scientific,\
         gbif_scientific_to_taxon_id = structures_to_serialize
+        
         return
 
 
@@ -135,6 +146,9 @@ def initialize_taxonomy_lookup(force_init=False) -> None:
     for taxonomy_name, zip_url in taxonomy_urls.items():
 
         need_to_download = False
+        
+        if force_init:
+            need_to_download = True
 
         # Don't download the zipfile if we've already unzipped what we need
         for fn in files_to_unzip[taxonomy_name]:
@@ -150,11 +164,11 @@ def initialize_taxonomy_lookup(force_init=False) -> None:
         zipfile_path = os.path.join(
             taxonomy_download_dir, zip_url.split('/')[-1])
 
-        # Bypasses download if the file exists already
+        # Bypasses download if the file exists already (unless force_init is set)
         url_utils.download_url(
             zip_url, os.path.join(zipfile_path),
             progress_updater=url_utils.DownloadProgressBar(),
-            verbose=True)
+            verbose=True,force_download=force_init)
 
         # Unzip the files we need
         files_we_need = files_to_unzip[taxonomy_name]
@@ -166,7 +180,7 @@ def initialize_taxonomy_lookup(force_init=False) -> None:
                 target_file = os.path.join(
                     taxonomy_download_dir, taxonomy_name, os.path.basename(fn))
 
-                if os.path.isfile(target_file):
+                if (not force_init) and (os.path.isfile(target_file)):
                     print(f'Bypassing unzip of {target_file}, file exists')
                 else:
                     os.makedirs(os.path.basename(target_file),exist_ok=True)
@@ -185,13 +199,16 @@ def initialize_taxonomy_lookup(force_init=False) -> None:
     # name file
 
     # Load iNat taxonomy
-    inat_taxonomy = pd.read_csv(os.path.join(taxonomy_download_dir, 'iNaturalist', 'taxa.csv'))
+    inat_taxonomy_file = os.path.join(taxonomy_download_dir, 'iNaturalist', 'taxa.csv')
+    print('Loading iNat taxonomy from {}'.format(inat_taxonomy_file))
+    inat_taxonomy = pd.read_csv(inat_taxonomy_file)
     inat_taxonomy['scientificName'] = inat_taxonomy['scientificName'].fillna('').str.strip()
     inat_taxonomy['vernacularName'] = inat_taxonomy['vernacularName'].fillna('').str.strip()
 
     # Load GBIF taxonomy
-    gbif_taxonomy = pd.read_csv(os.path.join(
-        taxonomy_download_dir, 'GBIF', 'Taxon.tsv'), sep='\t')
+    gbif_taxonomy_file = os.path.join(taxonomy_download_dir, 'GBIF', 'Taxon.tsv')
+    print('Loading GBIF taxonomy from {}'.format(gbif_taxonomy_file))
+    gbif_taxonomy = pd.read_csv(gbif_taxonomy_file, sep='\t')
     gbif_taxonomy['scientificName'] = gbif_taxonomy['scientificName'].fillna('').str.strip()
     gbif_taxonomy['canonicalName'] = gbif_taxonomy['canonicalName'].fillna('').str.strip()
 
@@ -249,7 +266,8 @@ def initialize_taxonomy_lookup(force_init=False) -> None:
 
     # Build iNat dictionaries
 
-    # row = inat_taxonomy.iloc[0]
+    print('Building lookup dictionaries for iNat taxonomy')
+    
     for i_row, row in tqdm(inat_taxonomy.iterrows(), total=len(inat_taxonomy)):
 
         taxon_id = row['taxonID']
@@ -267,6 +285,8 @@ def initialize_taxonomy_lookup(force_init=False) -> None:
 
     # Build GBIF dictionaries
 
+    print('Building lookup dictionaries for GBIF taxonomy')
+    
     for i_row, row in tqdm(gbif_taxonomy.iterrows(), total=len(gbif_taxonomy)):
 
         taxon_id = row['taxonID']
@@ -320,13 +340,13 @@ def initialize_taxonomy_lookup(force_init=False) -> None:
         gbif_scientific_to_taxon_id
     ]
 
-    print('Serializing...', end='')
+    print('Serializing to {}...'.format(serialized_structures_file), end='')
     if not os.path.isfile(serialized_structures_file):
         with open(serialized_structures_file, 'wb') as p:
             pickle.dump(structures_to_serialize, p)
     print(' done')
 
-# ...def initialize_taxonomy_lookup()
+# ...def initialize_taxonomy_lookup(...)
 
 
 def get_scientific_name_from_row(r):

taxonomy_mapping/taxonomy_csv_checker.py

@@ -45,7 +45,7 @@ def check_taxonomy_csv(csv_path: str) -> None:
     num_taxon_level_errors = 0
     num_scientific_name_errors = 0
 
-    for i, row in taxonomy_df.iterrows():
+    for i_row, row in taxonomy_df.iterrows():
         
         ds = row['dataset_name']
         ds_label = row['query']
@@ -81,14 +81,14 @@ def check_taxonomy_csv(csv_path: str) -> None:
             node.add_id(id_source, int(taxon_id))  # np.int64 -> int
             if j == 0:
                 if level != taxon_level:
-                    print(f'row: {i}, {ds}, {ds_label}')
+                    print(f'row: {i_row}, {ds}, {ds_label}')
                     print(f'- taxonomy_level column: {level}, '
                           f'level from taxonomy_string: {taxon_level}')
                     print()
                     num_taxon_level_errors += 1
 
                 if scientific_name != taxon_name:
-                    print(f'row: {i}, {ds}, {ds_label}')
+                    print(f'row: {i_row}, {ds}, {ds_label}')
                     print(f'- scientific_name column: {scientific_name}, '
                           f'name from taxonomy_string: {taxon_name}')
                     print()
@@ -97,7 +97,7 @@ def check_taxonomy_csv(csv_path: str) -> None:
             taxon_child = node
     
     # ...for each row in the taxonomy file        
-            
+
     assert nx.is_directed_acyclic_graph(graph)
 
     for node in graph.nodes:
@@ -123,6 +123,8 @@ def check_taxonomy_csv(csv_path: str) -> None:
     except AssertionError as e:
         print(f'At least one node has unresolved ambiguous parents: {e}')
 
+    print('Processed {} rows from {}'.format(len(taxonomy_df),csv_path))
+    
     print('num taxon level errors:', num_taxon_level_errors)
     print('num scientific name errors:', num_scientific_name_errors)
 
@@ -154,4 +156,4 @@ if False:
     import os
     csv_path = os.path.expanduser('~/lila/lila-taxonomy-mapping_release.csv')
     check_taxonomy_csv(csv_path)
-    
+    

api/synchronous/api_core/yolov5/detect.py

@@ -1,252 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Run inference on images, videos, directories, streams, etc.
-
-Usage - sources:
-    $ python path/to/detect.py --weights yolov5s.pt --source 0              # webcam
-                                                             img.jpg        # image
-                                                             vid.mp4        # video
-                                                             path/          # directory
-                                                             path/*.jpg     # glob
-                                                             'https://youtu.be/Zgi9g1ksQHc'  # YouTube
-                                                             'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
-
-Usage - formats:
-    $ python path/to/detect.py --weights yolov5s.pt                 # PyTorch
-                                         yolov5s.torchscript        # TorchScript
-                                         yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
-                                         yolov5s.xml                # OpenVINO
-                                         yolov5s.engine             # TensorRT
-                                         yolov5s.mlmodel            # CoreML (macOS-only)
-                                         yolov5s_saved_model        # TensorFlow SavedModel
-                                         yolov5s.pb                 # TensorFlow GraphDef
-                                         yolov5s.tflite             # TensorFlow Lite
-                                         yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
-"""
-
-import argparse
-import os
-import sys
-from pathlib import Path
-
-import torch
-import torch.backends.cudnn as cudnn
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[0]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
-
-from models.common import DetectMultiBackend
-from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
-from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
-                           increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
-from utils.plots import Annotator, colors, save_one_box
-from utils.torch_utils import select_device, time_sync
-
-
-@torch.no_grad()
-def run(
-        weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
-        source=ROOT / 'data/images',  # file/dir/URL/glob, 0 for webcam
-        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
-        imgsz=(640, 640),  # inference size (height, width)
-        conf_thres=0.25,  # confidence threshold
-        iou_thres=0.45,  # NMS IOU threshold
-        max_det=1000,  # maximum detections per image
-        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
-        view_img=False,  # show results
-        save_txt=False,  # save results to *.txt
-        save_conf=False,  # save confidences in --save-txt labels
-        save_crop=False,  # save cropped prediction boxes
-        nosave=False,  # do not save images/videos
-        classes=None,  # filter by class: --class 0, or --class 0 2 3
-        agnostic_nms=False,  # class-agnostic NMS
-        augment=False,  # augmented inference
-        visualize=False,  # visualize features
-        update=False,  # update all models
-        project=ROOT / 'runs/detect',  # save results to project/name
-        name='exp',  # save results to project/name
-        exist_ok=False,  # existing project/name ok, do not increment
-        line_thickness=3,  # bounding box thickness (pixels)
-        hide_labels=False,  # hide labels
-        hide_conf=False,  # hide confidences
-        half=False,  # use FP16 half-precision inference
-        dnn=False,  # use OpenCV DNN for ONNX inference
-):
-    source = str(source)
-    save_img = not nosave and not source.endswith('.txt')  # save inference images
-    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
-    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
-    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
-    if is_url and is_file:
-        source = check_file(source)  # download
-
-    # Directories
-    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
-    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
-
-    # Load model
-    device = select_device(device)
-    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
-    stride, names, pt = model.stride, model.names, model.pt
-    imgsz = check_img_size(imgsz, s=stride)  # check image size
-
-    # Dataloader
-    if webcam:
-        view_img = check_imshow()
-        cudnn.benchmark = True  # set True to speed up constant image size inference
-        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
-        bs = len(dataset)  # batch_size
-    else:
-        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
-        bs = 1  # batch_size
-    vid_path, vid_writer = [None] * bs, [None] * bs
-
-    # Run inference
-    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz))  # warmup
-    dt, seen = [0.0, 0.0, 0.0], 0
-    for path, im, im0s, vid_cap, s in dataset:
-        t1 = time_sync()
-        im = torch.from_numpy(im).to(device)
-        im = im.half() if model.fp16 else im.float()  # uint8 to fp16/32
-        im /= 255  # 0 - 255 to 0.0 - 1.0
-        if len(im.shape) == 3:
-            im = im[None]  # expand for batch dim
-        t2 = time_sync()
-        dt[0] += t2 - t1
-
-        # Inference
-        visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
-        pred = model(im, augment=augment, visualize=visualize)
-        t3 = time_sync()
-        dt[1] += t3 - t2
-
-        # NMS
-        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
-        dt[2] += time_sync() - t3
-
-        # Second-stage classifier (optional)
-        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
-
-        # Process predictions
-        for i, det in enumerate(pred):  # per image
-            seen += 1
-            if webcam:  # batch_size >= 1
-                p, im0, frame = path[i], im0s[i].copy(), dataset.count
-                s += f'{i}: '
-            else:
-                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
-
-            p = Path(p)  # to Path
-            save_path = str(save_dir / p.name)  # im.jpg
-            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
-            s += '%gx%g ' % im.shape[2:]  # print string
-            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
-            imc = im0.copy() if save_crop else im0  # for save_crop
-            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
-            if len(det):
-                # Rescale boxes from img_size to im0 size
-                det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
-
-                # Print results
-                for c in det[:, -1].unique():
-                    n = (det[:, -1] == c).sum()  # detections per class
-                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
-
-                # Write results
-                for *xyxy, conf, cls in reversed(det):
-                    if save_txt:  # Write to file
-                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
-                        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
-                        with open(f'{txt_path}.txt', 'a') as f:
-                            f.write(('%g ' * len(line)).rstrip() % line + '\n')
-
-                    if save_img or save_crop or view_img:  # Add bbox to image
-                        c = int(cls)  # integer class
-                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
-                        annotator.box_label(xyxy, label, color=colors(c, True))
-                    if save_crop:
-                        save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
-
-            # Stream results
-            im0 = annotator.result()
-            if view_img:
-                cv2.imshow(str(p), im0)
-                cv2.waitKey(1)  # 1 millisecond
-
-            # Save results (image with detections)
-            if save_img:
-                if dataset.mode == 'image':
-                    cv2.imwrite(save_path, im0)
-                else:  # 'video' or 'stream'
-                    if vid_path[i] != save_path:  # new video
-                        vid_path[i] = save_path
-                        if isinstance(vid_writer[i], cv2.VideoWriter):
-                            vid_writer[i].release()  # release previous video writer
-                        if vid_cap:  # video
-                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
-                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-                        else:  # stream
-                            fps, w, h = 30, im0.shape[1], im0.shape[0]
-                        save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
-                        vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
-                    vid_writer[i].write(im0)
-
-        # Print time (inference-only)
-        LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
-
-    # Print results
-    t = tuple(x / seen * 1E3 for x in dt)  # speeds per image
-    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
-    if save_txt or save_img:
-        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
-        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
-    if update:
-        strip_optimizer(weights)  # update model (to fix SourceChangeWarning)
-
-
-def parse_opt():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)')
-    parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for webcam')
-    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
-    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
-    parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
-    parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
-    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
-    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
-    parser.add_argument('--view-img', action='store_true', help='show results')
-    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
-    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
-    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
-    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
-    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
-    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
-    parser.add_argument('--augment', action='store_true', help='augmented inference')
-    parser.add_argument('--visualize', action='store_true', help='visualize features')
-    parser.add_argument('--update', action='store_true', help='update all models')
-    parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
-    parser.add_argument('--name', default='exp', help='save results to project/name')
-    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
-    parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
-    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
-    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
-    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
-    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
-    opt = parser.parse_args()
-    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
-    print_args(vars(opt))
-    return opt
-
-
-def main(opt):
-    check_requirements(exclude=('tensorboard', 'thop'))
-    run(**vars(opt))
-
-
-if __name__ == "__main__":
-    opt = parse_opt()
-    main(opt)