megadetector 5.0.7__py3-none-any.whl → 5.0.9__py3-none-any.whl

data_management/databases/remove_corrupted_images_from_db.py

@@ -1,191 +0,0 @@
-########
-#
-# remove_corrupted_images_from_db.py
-#
-# Given a coco-camera-traps .json file, checks all images for corruption
-# and generates a new .json file that only contains the non-corrupted images.
-#
-########
-
-#%% Imports and constants
-
-import argparse
-import gc
-import json
-import sys
-import os
-import time
-
-from multiprocessing.pool import ThreadPool
-
-import humanfriendly
-import numpy as np
-import tensorflow as tf
-
-N_THREADS = 16
-DEBUG_MAX_IMAGES = -1
-IMAGE_PRINT_FREQUENCY = 10
-
-
-#%% Function definitions
-
-def check_images(images, image_file_root):    
-    """
-    Checks all the images in [images] for corruption using TF.
-    
-    [images] is a list of image dictionaries, as they would appear in COCO
-    files.
-    
-    Returns a dictionary mapping image IDs to booleans. 
-    """    
-    
-    # I sometimes pass in a list of images, sometimes a dict with a single
-    # element mapping a job ID to the list of images
-    if isinstance(images,dict):
-        assert(len(images) == 1)
-        jobID = list(images.keys())[0]
-        images = images[jobID]
-    else:
-        jobID = 0
-        
-    keep_im = {im['id']:True for im in images}
-            
-    count = 0
-    nImages = len(images)
-    
-    # We're about to start a lot of TF sessions, and we don't want gobs 
-    # of debugging information printing out for every session.
-    os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
-    config=tf.ConfigProto(log_device_placement=False)
-    
-    # At some point we were creating a single session and looping over images
-    # within that session, but the only way I found to reliably not run out
-    # of GPU memory was to create a session per image and gc.collect() after
-    # each session.
-    for iImage,im in enumerate(images):
-
-        with tf.Session(config=config) as sess:
-
-            if ((DEBUG_MAX_IMAGES > 0) and (iImage >= DEBUG_MAX_IMAGES)):
-                print('Breaking after {} images'.format(DEBUG_MAX_IMAGES))
-                break
-            
-            if (count % IMAGE_PRINT_FREQUENCY == 0):
-                print('Job {}: processed {} of {} images'.format(jobID,count,nImages))
-                
-            count += 1
-            image_file = os.path.join(image_file_root,im['file_name'])
-            assert(os.path.isfile(image_file))
-            
-            try:
-                image_data = tf.gfile.FastGFile(image_file,'rb').read()
-                image = tf.image.decode_jpeg(image_data)
-                sess.run(image)
-            except:
-                keep_im[im['id']] = False
-
-        gc.collect()
-        
-    return keep_im
-
-
-def remove_corrupted_images_from_database(data, image_file_root):
-    """
-    Given the COCO database [data], checks all images for corruption using
-    TF, and returns a subset of [data] containing only non-corrupted images.
-    """
-    
-    # Map Image IDs to boolean (should I keep this image?)
-    images = data['images']
-    
-    if (N_THREADS == 1):
-        
-        keep_im = check_images(images,image_file_root)
-        
-    else:
-        
-        start = time.time()
-        imageChunks = np.array_split(images,N_THREADS)
-        # Convert to lists, append job numbers to the image lists
-        for iChunk in range(0,len(imageChunks)):
-            imageChunks[iChunk] = list(imageChunks[iChunk])
-            imageChunks[iChunk] = {iChunk:imageChunks[iChunk]}
-        pool = ThreadPool(N_THREADS)
-        # results = pool.imap_unordered(lambda x: fetch_url(x,nImages), indexedUrlList)
-        results = pool.map(lambda x: check_images(x,image_file_root), imageChunks)
-        processingTime = time.time() - start
-        
-        # Merge results
-        keep_im = {}
-        for d in results:
-            keep_im.update(d)
-        bValid = keep_im.values()
-            
-        print("Checked image corruption in {}, found {} invalid images (of {})".format(
-                humanfriendly.format_timespan(processingTime),
-                len(bValid)-sum(bValid),len(bValid)))
-        
-    data['images'] = [im for im in data['images'] if keep_im[im['id']]]
-    data['annotations'] = [ann for ann in data['annotations'] if keep_im[ann['image_id']]]
-    
-    return data
-
-
-#%% Interactive driver
-
-if False:    
-    
-    #%%
-    
-    # base_dir = r'D:\temp\snapshot_serengeti_tfrecord_generation'
-    base_dir = r'/data/ss_corruption_check'
-    input_file = os.path.join(base_dir,'imerit_batch7_renamed.json')
-    output_file = os.path.join(base_dir,'imerit_batch7_renamed_uncorrupted.json')
-    image_file_root = os.path.join(base_dir,'imerit_batch7_images_renamed')
-    assert(os.path.isfile(input_file))
-    assert(os.path.isdir(image_file_root))
-
-    # Load annotations
-    with open(input_file,'r') as f:
-            data = json.load(f)    
-            
-    # Check for corruption
-    data_uncorrupted = remove_corrupted_images_from_database(data,image_file_root)
-    
-    # Write out only the uncorrupted data
-    json.dump(data_uncorrupted, open(output_file,'w'))
-    
-    
-#%% Command-line driver 
-
-def main():
-    
-    parser = argparse.ArgumentParser(description = 'Remove images from a .json file that can''t be opened in TF')
-
-    parser.add_argument('--input_file', dest='input_file',
-                         help='Path to .json database that includes corrupted jpegs',
-                         type=str, required=True)
-    parser.add_argument('--image_file_root', dest='image_file_root',
-                         help='Path to image files',
-                         type=str, required=True)
-    parser.add_argument('--output_file', dest='output_file',
-                         help='Path to store uncorrupted .json database',
-                         type=str, required=True)
-
-    if len(sys.argv[1:]) == 0:
-        parser.print_help()
-        parser.exit()
-
-    args = parser.parse_args()
-    
-    print('Reading input file')
-    with open(args.input_file,'r') as f:
-        data = json.load(f)
-    print('Removing corrupted images from database')
-    uncorrupted_data = remove_corrupted_images_from_database(data, args.image_file_root)
-
-    json.dump(uncorrupted_data, open(args.output_file,'w'))
-
-
-if __name__ == '__main__':    
-    main()

detection/detector_training/copy_checkpoints.py

@@ -1,43 +0,0 @@
-########
-#
-# copy_checkpoints.py
-#
-# Run this script with specified source_dir and target_dir while the model is training to make a copy
-# of every checkpoint (checkpoints are kept once an hour by default and is difficult to adjust)
-#
-########
-
-#%% Imports and constants
-
-import time
-import os
-import shutil
-
-check_every_n_minutes = 10
-
-source_dir = '/datadrive/megadetectorv3/experiments/190425'
-target_dir = '/datadrive/megadetectorv3/experiments/0425_checkpoints'
-
-os.makedirs(target_dir, exist_ok=True)
-
-
-#%% Main loop
-
-num_checks = 0
-
-while True:
-    
-    num_checks += 1
-    print('Checking round {}.'.format(num_checks))
-
-    for f in os.listdir(source_dir):
-        # do not copy event or evaluation results
-        if f.startswith('model') or f.startswith('graph'):
-            target_path = os.path.join(target_dir, f)
-            if not os.path.exists(target_path):
-                _ = shutil.copy(os.path.join(source_dir, f), target_path)
-                print('Copied {}.'.format(f))
-
-    print('End of round {}.'.format(num_checks))
-
-    time.sleep(check_every_n_minutes * 60)

md_visualization/visualize_megadb.py

@@ -1,183 +0,0 @@
-########
-#
-# visualize_megadb.py
-#
-# Create visual previews of images/sequences in MegaDB.
-#
-########
-
-#%% Imports
-
-import argparse
-import json
-import os
-import sys
-from random import shuffle
-from multiprocessing.pool import ThreadPool
-from functools import partial
-import io
-
-from tqdm import tqdm
-
-from data_management.megadb.megadb_utils import MegadbUtils
-from md_utils.write_html_image_list import write_html_image_list
-from md_visualization import visualization_utils as vis_utils
-
-
-#%% Support functions
-
-def render_image_info(rendering, args):
-    
-    storage_client = rendering['storage_client']
-    image_obj = io.BytesIO()
-
-    try:
-        storage_client.download_blob(rendering['blob_path']).readinto(image_obj)
-    except Exception as e:
-        print(f'Image not found in blob storage: {rendering["blob_path"]}')
-        print(e)
-        return
-
-    # resize is for displaying them more quickly
-    image = vis_utils.resize_image(
-        vis_utils.open_image(image_obj), args.output_image_width)
-    vis_utils.render_megadb_bounding_boxes(rendering['bbox'], image)
-
-    annotated_img_name = rendering['annotated_img_name']
-    annotated_img_path = os.path.join(
-        args.output_dir, 'rendered_images', annotated_img_name)
-    image.save(annotated_img_path)
-
-
-def visualize_sequences(datasets_table, sequences, args):
-    
-    num_images = 0
-
-    images_html = []
-    rendering_info = []
-
-    for seq in sequences:
-        if 'images' not in seq:
-            continue
-
-        # dataset and seq_id are required fields
-        dataset_name = seq['dataset']
-        seq_id = seq['seq_id']
-
-        # sort the images in the sequence
-
-        images_in_seq = sorted(seq['images'], key=lambda x: x['frame_num']) if len(seq['images']) > 1 else seq['images']
-
-        for im in images_in_seq:
-            if args.trim_to_images_bboxes_labeled and 'bbox' not in im:
-                continue
-
-            num_images += 1
-
-            blob_path = MegadbUtils.get_full_path(
-                datasets_table, dataset_name, im['file'])
-            frame_num = im.get('frame_num', -1)
-
-            # if no class label on the image, show class label on the sequence
-            im_class = im.get('class', None)
-            if im_class is None:
-                im_class = seq.get('class', [])
-
-            rendering = {}
-            rendering['storage_client'] = MegadbUtils.get_storage_client(
-                datasets_table, dataset_name)
-            rendering['blob_path'] = blob_path
-            rendering['bbox'] = im.get('bbox', [])
-
-            annotated_img_name = 'anno_' + blob_path.replace('/', args.pathsep_replacement).replace('\\', args.pathsep_replacement)
-            rendering['annotated_img_name'] = annotated_img_name
-
-            rendering_info.append(rendering)
-
-            images_html.append({
-                'filename': 'rendered_images/{}'.format(annotated_img_name),
-                'title': 'Seq ID: {}. Frame number: {}<br/> Image file: {}<br/> number of boxes: {}, image class labels: {}'.format(seq_id, frame_num, blob_path, len(rendering['bbox']), im_class),
-                'textStyle': 'font-family:verdana,arial,calibri;font-size:80%;text-align:left;margin-top:20;margin-bottom:5'
-            })
-
-        if num_images >= args.num_to_visualize:
-            print('num_images visualized is {}'.format(num_images))
-            break
-
-    # pool = ThreadPool()
-    render_image_info_partial = partial(render_image_info, args=args)
-    # print('len of rendering_info', len(rendering_info))
-    # tqdm(pool.imap_unordered(render_image_info_partial, rendering_info), total=len(rendering_info))
-
-    for rendering in tqdm(rendering_info):
-        render_image_info_partial(rendering)
-
-    print('Making HTML...')
-
-    html_path = os.path.join(args.output_dir, 'index.html')
-    # options = write_html_image_list()
-    # options['headerHtml']
-    write_html_image_list(
-        filename=html_path,
-        images=images_html
-    )
-
-
-#%% Command-line driver
-
-def main():
-    
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        'megadb_entries', type=str,
-        help='Path to a json list of MegaDB entries')
-    parser.add_argument(
-        'output_dir', action='store', type=str,
-        help='Output directory for html and rendered images')
-    parser.add_argument(
-        '--trim_to_images_bboxes_labeled', action='store_true',
-        help='Only include images that have been sent for bbox labeling (but '
-             'may be actually empty). Turn this on if QAing annotations.')
-    parser.add_argument(
-        '--num_to_visualize', action='store', type=int, default=200,
-        help='Number of images to visualize (all comformant images in a '
-             'sequence are shown, so may be a few more than specified). '
-             'Sequences are shuffled. Default: 200. Use -1 to visualize all.')
-    parser.add_argument(
-        '--pathsep_replacement', action='store', type=str, default='~',
-        help='Replace path separators in relative filenames with another '
-             'character (default ~)')
-    parser.add_argument(
-        '-w', '--output_image_width', type=int, default=700,
-        help='an integer indicating the desired width in pixels of the output '
-             'annotated images. Use -1 to not resize.')
-
-    if len(sys.argv[1:]) == 0:
-        parser.print_help()
-        parser.exit()
-
-    args = parser.parse_args()
-
-    assert 'COSMOS_ENDPOINT' in os.environ and 'COSMOS_KEY' in os.environ
-
-    os.makedirs(args.output_dir, exist_ok=True)
-    os.makedirs(os.path.join(args.output_dir, 'rendered_images'))
-
-    print('Connecting to MegaDB to get the datasets table...')
-    megadb_utils = MegadbUtils()
-    datasets_table = megadb_utils.get_datasets_table()
-
-    print('Loading the MegaDB entries...')
-    with open(args.megadb_entries) as f:
-        sequences = json.load(f)
-    print('Total number of sequences: {}'.format(len(sequences)))
-
-    # print('Checking that the MegaDB entries conform to the schema...')
-    # sequences_schema_check.sequences_schema_check(sequences)
-
-    shuffle(sequences)
-    visualize_sequences(datasets_table, sequences, args)
-
-
-if __name__ == '__main__':
-    main()

megadetector-5.0.7.dist-info/RECORD

@@ -1,202 +0,0 @@
-api/batch_processing/api_core/server.py,sha256=BNqM5EK29B0haCW7rdeOzVqcCJDziZiD0Etc1mPs56c,11668
-api/batch_processing/api_core/server_api_config.py,sha256=G8X5wgqEXPrWWQpgDI9ua-JktiUgy9mOpEltXSIazLQ,3318
-api/batch_processing/api_core/server_app_config.py,sha256=tQCFsFv0wJCegHfnu-Za3okdXwEd4U522hiM0YGNkMY,1860
-api/batch_processing/api_core/server_batch_job_manager.py,sha256=K7fMFBJA8Z1SkA4eBM-nymcq7VQjwZ6ZRaNnNKFlat8,10324
-api/batch_processing/api_core/server_job_status_table.py,sha256=Wb8IGwft-_W9pi9ixSe81cCwuSocSP5FrzURzbAqdr4,6240
-api/batch_processing/api_core/server_orchestration.py,sha256=LYHABzhOvP0NrM1VIjI6Vwb95YZ5xjQ52mUJW8oIOQ0,17003
-api/batch_processing/api_core/server_utils.py,sha256=oFusP1E29op5DN1nEaR-jQZgRExqMDdzmRL6BHj8EDk,3314
-api/batch_processing/api_core/batch_service/score.py,sha256=ZuPQV7O1u9QNPhWVSYxQqvYgXo9p15e-XhnUyuz0vLE,17347
-api/batch_processing/api_core_support/aggregate_results_manually.py,sha256=8yDXbw12G8Y6SOv09tY-0hPXMNG_iRPv6mzxBiccsaU,2275
-api/batch_processing/api_support/summarize_daily_activity.py,sha256=SmRGAMWTKXf9bDXUPsTySMiIg8K1LDkAC8KVBVH_mPg,5383
-api/batch_processing/data_preparation/manage_local_batch.py,sha256=Nb9MxJyAJC2e4twWkoGfI-crSSgB9g8Ue28cbbeE5QA,88618
-api/batch_processing/data_preparation/manage_video_batch.py,sha256=fobPIMmfvdqa1OzxsurEYCFVnUTHGrtrGBiCq3xnYHs,9668
-api/batch_processing/integration/digiKam/setup.py,sha256=7P1X3JYrBDXmLUeLRrzxNfDkL5lo-pY8nXsp9Cz8rOI,203
-api/batch_processing/integration/digiKam/xmp_integration.py,sha256=AbGPTe9RjjOkKdiZDSElai61QyfeiLQQqJR2fiJpymA,17775
-api/batch_processing/integration/eMammal/test_scripts/config_template.py,sha256=UnvrgaFRBu59MuVUJa2WpG8ebcOJWcNeZEx6GWuYLzc,73
-api/batch_processing/integration/eMammal/test_scripts/push_annotations_to_emammal.py,sha256=eIzEKiwzCfifCOCGf-jf8G4dMuzyxQMWlrFzt-Z-nVk,3608
-api/batch_processing/integration/eMammal/test_scripts/select_images_for_testing.py,sha256=OYMu97p8vprSv03QcnS6aSxPBocn9sgaozfUqq_JpyM,1369
-api/batch_processing/postprocessing/add_max_conf.py,sha256=y4Xr_OHRxcop3vsLWQJ56eYIemm2HHKqVfvKJonTcQA,1530
-api/batch_processing/postprocessing/categorize_detections_by_size.py,sha256=b_O2OM44zIXewR4RjzeS2ue-32k5jE6KgjiPn8JRxAA,4877
-api/batch_processing/postprocessing/combine_api_outputs.py,sha256=WsOV4EsK9JUCMka1_-u-vinmWc6Ko8B0PD5fmwoXHh0,8233
-api/batch_processing/postprocessing/compare_batch_results.py,sha256=65Kq6mChsPElQfjhWgLDmnO9b6igatQvXiasB2YVHno,34652
-api/batch_processing/postprocessing/convert_output_format.py,sha256=aLboVVZdlGUNYOZhme0w8LtYrd04i15oK0apOgZaYWk,12947
-api/batch_processing/postprocessing/load_api_results.py,sha256=1BwpXUUQiGJeOUDfQTiA9thNd5jbSbOU3siTO1_Dw5s,6997
-api/batch_processing/postprocessing/md_to_coco.py,sha256=dRAkCGWtcNy_vsSTkX1h_0DZAsW6zNO7F-8XSkR8wAo,10139
-api/batch_processing/postprocessing/md_to_labelme.py,sha256=lfheIrXqzjq6lInmlYgYq354PrVvH2SPNXKr8e3S_DQ,7075
-api/batch_processing/postprocessing/merge_detections.py,sha256=B4QnqW9nvcEJpXzAK20TVB0t6L8c7PR5OjPy8FX-5Z8,15930
-api/batch_processing/postprocessing/postprocess_batch_results.py,sha256=l_uyOTTINq9GBZlHsAnPteEvA-rWmKZH-eWVcqbMPUM,73653
-api/batch_processing/postprocessing/render_detection_confusion_matrix.py,sha256=h-a7tWNBSe3VRUg-Z4aX-ySUzrF8NfiEYWA1lHbZrmo,25040
-api/batch_processing/postprocessing/separate_detections_into_folders.py,sha256=l5NKxDDxROc2EXt8EslrswXAZkQXgWTy5FSqCqa09Ug,28720
-api/batch_processing/postprocessing/subset_json_detector_output.py,sha256=EROwcj4K-abAwzyZjPCQocuayIVma85lV-D6WvvRMuc,26368
-api/batch_processing/postprocessing/top_folders_to_bottom.py,sha256=etJK9DmHppMe3WqGXypuilW-n-7hOjOO9w_k1khlaVU,5476
-api/batch_processing/postprocessing/repeat_detection_elimination/find_repeat_detections.py,sha256=fYqPZhaL-6cbpKHz96O3Ch65Y8xux2LQ2-ZlMGhOlM0,9053
-api/batch_processing/postprocessing/repeat_detection_elimination/remove_repeat_detections.py,sha256=YdMvM814TX0ZRTnP7BfowE62PoMoCOYcJOFl69DlKhQ,2189
-api/batch_processing/postprocessing/repeat_detection_elimination/repeat_detections_core.py,sha256=D-q20g9kLXCNB8IMyeLYxdMSvipzmgu2buEh--HJrC0,62882
-api/synchronous/api_core/animal_detection_api/api_backend.py,sha256=PJXV0RFb6FoPBmdRug5W_5nbFwY2C_8CvDpFHjDs9w4,4934
-api/synchronous/api_core/animal_detection_api/api_frontend.py,sha256=_FGLf5C2tXQABFEGaA2Kzq05hj_D60BaIfWLCI-Os_4,10690
-api/synchronous/api_core/animal_detection_api/config.py,sha256=yEf7JZwRJCtHEV80kYvnNnUFJNds_AYLhomffwfFQi0,1017
-api/synchronous/api_core/animal_detection_api/data_management/annotations/annotation_constants.py,sha256=P2CZCbAE0ImLLfaNRb1SMlP3q1fULWAIjgrYOrF9L0g,1566
-api/synchronous/api_core/animal_detection_api/detection/process_video.py,sha256=b2xcQThAdlgirumxynHULYLviCr_q5sCDfdkKEqVFyU,22089
-api/synchronous/api_core/animal_detection_api/detection/pytorch_detector.py,sha256=nI2xctI6FSdbWjSFHYlMT0LTH6CCATOe9DF-I8MLEpc,11505
-api/synchronous/api_core/animal_detection_api/detection/run_detector.py,sha256=LBveNOLE3AWSTcQ1MUbbWXaQIutr9e2vtz6RG2SjlWQ,23821
-api/synchronous/api_core/animal_detection_api/detection/run_detector_batch.py,sha256=eivQu5yee5WtBmNQRQ2p636Gf8IB5slyrQL4QRZ2HeM,41849
-api/synchronous/api_core/animal_detection_api/detection/run_inference_with_yolov5_val.py,sha256=yxMFxQQDvkydWVpM0ecopDXtPi89gaqMX0TKjyxNyjI,22118
-api/synchronous/api_core/animal_detection_api/detection/run_tiled_inference.py,sha256=cs1IehE2DXj8Nr3CbnYMXqwcFM1vUBT1Rm5We5nlcSM,28785
-api/synchronous/api_core/animal_detection_api/detection/tf_detector.py,sha256=xOO8kzd-Um2X_sAZyop524LM53nipv5pNx8YueGTJrc,6760
-api/synchronous/api_core/animal_detection_api/detection/video_utils.py,sha256=E96hywSwA_jTUcJNFdkneKPcH0XH_e2qRT5ovV-5SFM,18317
-api/synchronous/api_core/animal_detection_api/detection/detector_training/copy_checkpoints.py,sha256=t2c3Q4Pf82tAp_OjSG-veIjRPrX0tJYi-bSQmGL2m4c,1091
-api/synchronous/api_core/animal_detection_api/detection/detector_training/model_main_tf2.py,sha256=YwNsZ7hkIFaEuwKU0rHG_VyqiR_0E01BbdlD0Yx4Smo,4936
-api/synchronous/api_core/animal_detection_api/md_utils/azure_utils.py,sha256=SVoQNSknYlBcpZeGrH2v3Qgm5kXxBrqM5Sx2L_Lax-I,6243
-api/synchronous/api_core/animal_detection_api/md_utils/ct_utils.py,sha256=3_8p5wNnopQZPCIbchQXYnJmhuUTcDw46I4SK3qb--g,7600
-api/synchronous/api_core/animal_detection_api/md_utils/directory_listing.py,sha256=b3yUwZqK7LdvswXenDo4Y0ue4f4zjgpvncfZmzPGBpI,9598
-api/synchronous/api_core/animal_detection_api/md_utils/matlab_porting_tools.py,sha256=9IFR_uWM1egCMZT3MgoUmdOP8mp7CcF7L9HEbN_A_1E,2005
-api/synchronous/api_core/animal_detection_api/md_utils/path_utils.py,sha256=9ZMyzejC_kzAQlymXGghAAgp_WjCjLuOxWJrAC13TAk,12397
-api/synchronous/api_core/animal_detection_api/md_utils/process_utils.py,sha256=_LMebsTQX2PFxERj0-LoC-XCua23RPw3heu-ckp0Tjo,3049
-api/synchronous/api_core/animal_detection_api/md_utils/sas_blob_utils.py,sha256=GpjHn33N2b-XeBAtU3xhGbTIYcBs4YrXHtbQDmlGFvY,16955
-api/synchronous/api_core/animal_detection_api/md_utils/string_utils.py,sha256=tFTC9TarPFGa7_UkKF0_t6Q2naH9IEsDVM2DOxwkFTQ,1277
-api/synchronous/api_core/animal_detection_api/md_utils/url_utils.py,sha256=aFN7_WvzMJqYHL9t-SGCP2A0-mlYu1-P0HkZwgzUsKg,4598
-api/synchronous/api_core/animal_detection_api/md_utils/write_html_image_list.py,sha256=myXMdOwUERZWp9p2RPu8TcStCsu2X7aJNtcomlhoeqA,7573
-api/synchronous/api_core/animal_detection_api/md_visualization/visualization_utils.py,sha256=Up8hfM_KYyToIUhTv3sSrXGoYl8Hm57NO5t5AHMW3tk,31680
-api/synchronous/api_core/tests/load_test.py,sha256=Xiq2JFv9mnSHehwrm-grZ1Flv9qtkW-zUrTu1cYPry8,3386
-classification/aggregate_classifier_probs.py,sha256=1X5hpC2JRj790jyFEWES2RI1UbcjzhGcslhMJpvMpDM,3488
-classification/analyze_failed_images.py,sha256=WG2ubdkClRo6-v3JqD6dQ7X0aah1L_rYry2BHzirOYE,8463
-classification/cache_batchapi_outputs.py,sha256=EyVG8ynGSX3R7aiz6cN7mDhX7miyMg7FnMXnO2OzScQ,6400
-classification/create_classification_dataset.py,sha256=cBsuL_1KRZXIxBBnPI3xZmgDVMsfBv1_i1ZHR4W6oqE,25578
-classification/crop_detections.py,sha256=Xs_jnwgbfyUPGyOAi_AkYGstQyHzelw1avNcdfV8K2s,20510
-classification/csv_to_json.py,sha256=Di3kl8CRMlM63MqsBauAr0Jn42uTmrTs3eRA4RFkHq8,6088
-classification/detect_and_crop.py,sha256=LHKismSArVy23JeeGOKFGK2JdgcCwSOlsnwACiRCFxk,37158
-classification/evaluate_model.py,sha256=pyKY7ABcuCe4h0yfAquFVDNtnyV45yun-ttAa0etM-E,19378
-classification/identify_mislabeled_candidates.py,sha256=pHB9U_7LFBeLyY1AngIAtbrnma4luJVpwe7BWh9Qhhw,5111
-classification/json_to_azcopy_list.py,sha256=o57wLHJPDrP9OPSY-3x81WI3mmcH1DyIOUh3VQmMwxg,1670
-classification/json_validator.py,sha256=ZizcEPpW1J26p-oGyfvcffBy2voNRKCNXKF8NtxIt5A,26618
-classification/map_classification_categories.py,sha256=2B4K-TdE77VNw8XG1h8X7CuUvw0JSIrALdy6a1FvkXw,10738
-classification/merge_classification_detection_output.py,sha256=2FDTauvkbMZ3putJH837Ux67HTGsCAnGCOXhnnqjt6g,20123
-classification/prepare_classification_script.py,sha256=7xwqws57Fkn0rmH5sADlem9trOJkiriSRwPredeIXho,5952
-classification/prepare_classification_script_mc.py,sha256=IMCsLyGL70cViVTH0eow0sYDM9E81AsBGrctNveXP10,7440
-classification/run_classifier.py,sha256=eBpkZzP7TtrnwOIlc99fTpe1QocmDuERaIw9mXqwAWI,9363
-classification/save_mislabeled.py,sha256=WmOKNXgrvvIkUdehiiWHNiKc5M7q0UM2If0vea0_7K8,3466
-classification/train_classifier.py,sha256=M5hsPP-xdx94t6S5AhjzRrmNYcQAUMnUBL6Tkts6-F0,32329
-classification/train_classifier_tf.py,sha256=LhTteMic5CP5Zp3Q4tdh--ySa2rGwPB2Lg-IlrO04eI,28096
-classification/train_utils.py,sha256=o12OxP8ozli3e9DmOvzrjRDX278S3Ik5oz5EKD9mkIg,11355
-classification/efficientnet/__init__.py,sha256=e-jfknjzCc5a0CSW-TaZ2vi0SPU1OMIsayoz2s94QAo,182
-classification/efficientnet/model.py,sha256=qJHWV9-rYKa4E_TIee5N_OjRhqDdM-icPpoMap3Q5HM,17040
-classification/efficientnet/utils.py,sha256=TF5S2cn2lvlCO2dFhdFPdzjbBBs-SyZGZmEx_dsJMbo,24846
-data_management/cct_json_to_filename_json.py,sha256=AxYeOzZHkHF1UxHCUBtofXNKVdUK-5xTfZp3_iE7hFc,2416
-data_management/cct_json_utils.py,sha256=JX5pJh5QLyKDhcXheUYgbRSd99uB9Ui-EfsRZ_Fhw_I,12570
-data_management/cct_to_csv.py,sha256=urIL8IUByhKZ4FLLa9TKlzT6mu8upLzAPN1WNnDZdIY,3859
-data_management/cct_to_md.py,sha256=0QtqUdUkrema2BSNTeJqHYkDuwOLc7tOQwq1KxTbtPE,4485
-data_management/cct_to_wi.py,sha256=nJKUhLXcZXKE5tAR9UxbqCjeikfaABfB746wpv-1BmI,8336
-data_management/coco_to_yolo.py,sha256=8c-9cCjelKTwMOL6gQc9oAWum7UPxIr0FP_tiK8NyLc,25880
-data_management/generate_crops_from_cct.py,sha256=m6HJ8bB4N50HYV4SXAUV43k1XJl71QZmmWZ4L-9T45Y,4283
-data_management/get_image_sizes.py,sha256=yUCI5zQmA9G_GDaQiApwoafmO37cUi97dw-Ekh5leOE,4220
-data_management/labelme_to_coco.py,sha256=9RpOp-IV5miJag4KInLijR7koH8eZSztKdAmArhoMx4,14204
-data_management/labelme_to_yolo.py,sha256=XjhrmoGxyo1N-N8kueGzmy_m6FWR4SO8sNHFppoH-GQ,8480
-data_management/ocr_tools.py,sha256=8cVJMQvzvv_6HXV8zMR4nJH72-L_f3Dy9IjIb3E32Js,29920
-data_management/read_exif.py,sha256=HGCp5gvD8MHQ0xGGTX2_PD5JHFTdMtqjZ8ql2pt5Fn0,19036
-data_management/remove_exif.py,sha256=_WDrKfRwK0UWCkj4SiLutGCd7-WRaKYoTgLfBWPDhGU,1555
-data_management/resize_coco_dataset.py,sha256=pG1yVktPSp6Vc3DThrJO7lmo67_KvOdqEtFpwM6QjOA,7398
-data_management/yolo_output_to_md_output.py,sha256=vxUdn4bqg0S67ozvxtnlX77X6S7nCvyZbKAyvCh_Suc,16313
-data_management/yolo_to_coco.py,sha256=Xb9UVO-HHYrkJyxbASWJDZrZCyW3JwBPI_WN5SQHys4,8078
-data_management/annotations/annotation_constants.py,sha256=P2CZCbAE0ImLLfaNRb1SMlP3q1fULWAIjgrYOrF9L0g,1566
-data_management/databases/add_width_and_height_to_db.py,sha256=71mOEK3xo9gbxK1TVZzBA9nNi-1ElmBZbIPKrUm9XG0,619
-data_management/databases/combine_coco_camera_traps_files.py,sha256=cwu_REQXdHWfVLtCvTvFEIvM7z8GwHVoawVuHcWv2aw,6888
-data_management/databases/integrity_check_json_db.py,sha256=aQe36eEnhxHFpm9XGmFXCf4jsTvfXuBWMfKdIKKN4tU,14535
-data_management/databases/remove_corrupted_images_from_db.py,sha256=Dod8UQDFveAUJlrH9Svcp_HezdILRHp74TbAl3YGf84,6138
-data_management/databases/subset_json_db.py,sha256=UeVn3jlcpEw-K9E-QyRwxdzl7zaV80iv_u4v6kHUd_E,2749
-data_management/importers/add_nacti_sizes.py,sha256=qsBHPyJ7MPzl0vgJX5iErZxWkTJ6QRcyLJ8GM2YBu2U,1172
-data_management/importers/add_timestamps_to_icct.py,sha256=8XhQAIt_qw63qTMPobCKGl4O9RQZvZmhbmiSetOyNvA,2459
-data_management/importers/animl_results_to_md_results.py,sha256=tzYaPpiUte5A1VHulAbYO9-hzUIpE1xI5lJp6hS_JoI,4899
-data_management/importers/auckland_doc_test_to_json.py,sha256=9Fg-n_Kj2jK5iZVaPrioNkhlLNxGnrU5GS_44lsadKo,12910
-data_management/importers/auckland_doc_to_json.py,sha256=qSjBcR7FTd5_J2LO6WOoIFxSnE2IiIIqRkhbydULV7s,5952
-data_management/importers/awc_to_json.py,sha256=jLXmwGaq81wgH7HcpbAJoNMQP2CqkdfI1mvShdTGeqw,5307
-data_management/importers/bellevue_to_json.py,sha256=d5QhZMrOY4hRC9vghojCulX6G8qnVrymnKDx_mUlsRE,7909
-data_management/importers/cacophony-thermal-importer.py,sha256=0Y21Hx8Y4dMvpUpbKKMDYb0r-AqFD2k8N0Bf9q75geY,28621
-data_management/importers/carrizo_shrubfree_2018.py,sha256=pEdCh3z458dOnGIM_nXJIKlSb8Yv5yjr7Jjp32AwhaI,7827
-data_management/importers/carrizo_trail_cam_2017.py,sha256=Kw0SnOMt7DwIhnSEz5wjLpJ4pMjEx5n5PNPW36vrskk,8830
-data_management/importers/cct_field_adjustments.py,sha256=Kw1_gIxqXLovGa65jCRm9MIms6qfpqwTiOdM5unw9K8,1351
-data_management/importers/channel_islands_to_cct.py,sha256=DmEhjm7iG11yuJUVkXhqWuAXOLYQvV3AXY8nkwyf2oY,29483
-data_management/importers/ena24_to_json.py,sha256=XkJX0clvJREilzDByuoP6cuaOXvXnQoFkG25XoA8opU,8248
-data_management/importers/filenames_to_json.py,sha256=wzleV-02pwNHKAVvqhkAwahIJ6La_-OCPEXTOg64ezM,10526
-data_management/importers/helena_to_cct.py,sha256=imo-SRsib7c7NIM0vSE_6zbb3X7jA5XiIJrM6RbAoQA,8701
-data_management/importers/idaho-camera-traps.py,sha256=xKXfrwTpdMWJM1U92eWXxKhtW57iIjB9YyS4b_nA4e0,54058
-data_management/importers/idfg_iwildcam_lila_prep.py,sha256=emnKiw1TckZFsCI1uMgFIZUw1CERAVqufr9Tay94YAc,8166
-data_management/importers/jb_csv_to_json.py,sha256=u3IZwDboObYlxtUSa35G8P3t_L48m2Ak5v7Fl8hCnGM,3730
-data_management/importers/mcgill_to_json.py,sha256=ZxsNW9qFi6Kyu8SJ0BB5uK7AMuBW92QOOKXHPbIgPwY,6718
-data_management/importers/missouri_to_json.py,sha256=y9lbLaD8bGM4m9iqGHIicyZOByeJGfZOF51RikHMSFU,14840
-data_management/importers/nacti_fieldname_adjustments.py,sha256=57PyfOft2Ws-1AcG4_9mzOcB3uW4IFxaZ3z0LsItUUU,2045
-data_management/importers/noaa_seals_2019.py,sha256=wYcjhARv4IUJgawXcAnwIAOGZq5GORG8ElE_7JZSVCk,5145
-data_management/importers/pc_to_json.py,sha256=9Nin7R47aaE5bjXjvq7A2trv2vFdJVYzhLHwLFji5Tg,10718
-data_management/importers/plot_wni_giraffes.py,sha256=V_kAzbYjtXEBUCdSwSGsEEemLN9aVyZuKhoSZQEvkCI,3787
-data_management/importers/prepare-noaa-fish-data-for-lila.py,sha256=WIkuR4ozEeHwzQPs54jIDIbAgKf1I4taZNgpHHzh-Rc,12774
-data_management/importers/prepare_zsl_imerit.py,sha256=9wTh9w6kyQXJoA2h0kuzzcoCF1lFNfO9eRlSTnV6unY,3754
-data_management/importers/rspb_to_json.py,sha256=L-E4IcwvnwZ_I142dQ6BbQpAqZmNoAcVIuiwtuYGDXw,9834
-data_management/importers/save_the_elephants_survey_A.py,sha256=OpGLHXLj1VGZQefZ1R59_mSiQ2KkKN11PyvKWWJnVbY,10639
-data_management/importers/save_the_elephants_survey_B.py,sha256=qex23iOkUBttfDvoCeBw3NLVSbkf1xQtS8VhrvN4SgM,11167
-data_management/importers/snapshot_safari_importer.py,sha256=h5xSAlFgxckBXmKLKrIIs9Hegq5StgGMaG5pTCPSpc8,23591
-data_management/importers/snapshot_safari_importer_reprise.py,sha256=yRzgIYvcvMnlNL0sWv3ZUCNzo2e5_sy3k4DC18xh0Mc,22996
-data_management/importers/snapshot_serengeti_lila.py,sha256=mZ_hR7yHfeZFkLtuAO1U7kWRq3_wDtBE28-qXUZmBzo,33854
-data_management/importers/sulross_get_exif.py,sha256=nc9MwF_5_Nlsv7f0W74G71G-MF5EZDZIvLqDeKvcwWc,2088
-data_management/importers/timelapse_csv_set_to_json.py,sha256=7g1senO7SWUavktI9n214M2SwApN84TPuNTJPxHhZ3A,15902
-data_management/importers/ubc_to_json.py,sha256=MP_whIR-CVhNPCE3vQF_tk-6_EpmxWwR40E7pOA10mI,14869
-data_management/importers/umn_to_json.py,sha256=emUVCtNfbJmgHS22fBL8GaAMiblaJen52-IuqiFiWyI,16177
-data_management/importers/wellington_to_json.py,sha256=QFcVfAxflUVHTMuGhXGxe3z3iMKJ0B8Nziwpx6XcoLE,7671
-data_management/importers/wi_to_json.py,sha256=xuHFXE6tuaUnZmiFik18_3UCSCQx9abaG_2TnaRn0Xg,13656
-data_management/importers/zamba_results_to_md_results.py,sha256=UV0Iczxf_ghR3yL8D8KUAEg1j81_BavdzWhAFtg6wHQ,5594
-data_management/importers/eMammal/copy_and_unzip_emammal.py,sha256=gVB0drYUeCghWXFDpaJkCL0qdmFjMW75YAEEhFe38js,6080
-data_management/importers/eMammal/eMammal_helpers.py,sha256=Sv6PBAMDdlgwiek6Q3R6Rjio2RjtA-JpfgBr_Fmr9kA,6838
-data_management/importers/eMammal/make_eMammal_json.py,sha256=6C_-6Qk-Xhz_87DEPHA-txw90AvXrybJy1PbQXQbqwo,6987
-data_management/importers/snapshotserengeti/make_full_SS_json.py,sha256=khE3W0pO3Uq-UCfrLW_rpzWqjLll2JoBc360XeAuUGc,4126
-data_management/importers/snapshotserengeti/make_per_season_SS_json.py,sha256=sAwvcR2siwblgY3LfTsbH4mXOXvJZCA246QIsQWuQBA,4316
-data_management/lila/add_locations_to_island_camera_traps.py,sha256=nsIJXyw2IhOwwM9A0SCn108Fg297fRUdADXGUAN8Y34,2561
-data_management/lila/add_locations_to_nacti.py,sha256=KVMWwSJx-gYI_J6J8y-AqsWnOTgidtebotJjYPfsj00,5017
-data_management/lila/create_lila_blank_set.py,sha256=ScGlqalOySsmZEvYtEn4pGNxGOj0qHyxGs-F5URTmk8,16359
-data_management/lila/create_lila_test_set.py,sha256=WxM-LuhtNiee3CLeVPxUEWsfbybgZd7oluZu6epl69A,4825
-data_management/lila/create_links_to_md_results_files.py,sha256=f0pXY2Lyj9DtRlgFpmLqNBs2qWd--B8N6UAt8E26tcM,3916
-data_management/lila/download_lila_subset.py,sha256=nJjzKuMOYJa2lBJcXOEZloWjbFlQW_USke49DJdNruM,5283
-data_management/lila/generate_lila_per_image_labels.py,sha256=b0FDiYbs5BI8wdk221ysr-p1PsprfRFwMIgv65BYS6Y,17351
-data_management/lila/get_lila_annotation_counts.py,sha256=QVSKCmeLzliFZimjzi8AClS0Gz94pDMYckjw2cOm-7E,5490
-data_management/lila/get_lila_image_counts.py,sha256=r5p2wPL5vuKKO8DWia3Tll-EZZWFNUvax6ljaYtrKsk,3625
-data_management/lila/lila_common.py,sha256=vzazQR3UzvRxbxdBvRBcCbQ9pw0DUD3iWjUscV-nUvo,8785
-data_management/lila/test_lila_metadata_urls.py,sha256=jDInoM5WD_EoahR_b5yTjrj6pkiitvj_Kz_1U0uSDzE,3966
-detection/process_video.py,sha256=wuMoV-DJde_QlTiNAxsRjlDttiLl2e2BiJuyTQBINIE,26825
-detection/pytorch_detector.py,sha256=WG6Q4KueBoA8lCZCdR2PrgbQAHs3HCO6MF01Ful4tfc,11992
-detection/run_detector.py,sha256=XmQ4s-B7IlkxJye56y6uvx2vx6Ml3IBTo3Wx0SalO1Q,26036
-detection/run_detector_batch.py,sha256=dgPwvEAOTutpuEKE6TCopjj5w9J1Eb9jOvT3lyEmoNc,46937
-detection/run_inference_with_yolov5_val.py,sha256=tjHovM8I2YWvDsBcWV0h6hJaAjckTEN7foJ_X6IetIo,33755
-detection/run_tiled_inference.py,sha256=mL1WxA4bWEf2TaT3xK-hXjA4_5ABBwfXx9zVbmhaWB4,33930
-detection/tf_detector.py,sha256=xOO8kzd-Um2X_sAZyop524LM53nipv5pNx8YueGTJrc,6760
-detection/video_utils.py,sha256=70dx6_D9zQhAHatzHA0Bo3LreOJe98A859O243dFIvs,19425
-detection/detector_training/copy_checkpoints.py,sha256=t2c3Q4Pf82tAp_OjSG-veIjRPrX0tJYi-bSQmGL2m4c,1091
-detection/detector_training/model_main_tf2.py,sha256=YwNsZ7hkIFaEuwKU0rHG_VyqiR_0E01BbdlD0Yx4Smo,4936
-md_utils/azure_utils.py,sha256=SVoQNSknYlBcpZeGrH2v3Qgm5kXxBrqM5Sx2L_Lax-I,6243
-md_utils/ct_utils.py,sha256=CbuSL-XqI5jU9ShxEgnvIKqQF_BzbDPSTULPBmEVAnU,12908
-md_utils/directory_listing.py,sha256=dgxMczSOEH352YXdWRuNo_ujsonRrPJXFeuS7ocpe9k,9615
-md_utils/md_tests.py,sha256=FWqv74nBmN5772cSgRxnFZX8zZ3tikwMFr_rhvdV24Y,33316
-md_utils/path_utils.py,sha256=g_ASvwJCeN6eGtypuwrSfCxNM7Gx15oeC6TXwJ6yYJc,16573
-md_utils/process_utils.py,sha256=YkD38KLgceuqvMvDXIcVyzY51npUuUT3tOAjjF5Mvf8,4316
-md_utils/sas_blob_utils.py,sha256=GpjHn33N2b-XeBAtU3xhGbTIYcBs4YrXHtbQDmlGFvY,16955
-md_utils/split_locations_into_train_val.py,sha256=psiWoXkYYLLOfjVHUyOhaa3fh9mmlm7HGFthklWbMaA,9241
-md_utils/string_utils.py,sha256=Edwa07IWu7-QTNoMmvQYNnYgpwxxNh9VhXQ8AXMX3Qg,1600
-md_utils/url_utils.py,sha256=2Ee459ZRQ4Ms-52WRhyiEBICHACKmigrRnYRi6JtCdQ,4593
-md_utils/write_html_image_list.py,sha256=VLbeJnrRPm-D-_KFDVAnrU3alrXUr6eOr4WOv4-ugwk,7036
-md_visualization/plot_utils.py,sha256=eppaGgI0k73jhvOCruNrNO-VLH3EEFpFP2la_rZo57E,10712
-md_visualization/render_images_with_thumbnails.py,sha256=XJcL5qxu5pe2LQ4MqnD-O6dM_cPxGGNoqk5U_rZzFUQ,10391
-md_visualization/visualization_utils.py,sha256=2OJKG_L70XYCCdhLGmQ5-HD9nCaHisqIJoRGIYb0L1g,35297
-md_visualization/visualize_db.py,sha256=x6Y--RazaPvUayEch_Dr10NV0P0C7l0ZB29-vjW5WjI,18931
-md_visualization/visualize_detector_output.py,sha256=aeg8DbwfddW5CDe84V2dt07eWMyxr4QdFcwTYbC_Lnk,15814
-md_visualization/visualize_megadb.py,sha256=ZHFMgQv-zjXwvyT6gEfLe2BzodvBNfQYEh0b6P_59TE,6188
-taxonomy_mapping/map_lila_taxonomy_to_wi_taxonomy.py,sha256=kFDp6r25LhYVkyrm-35TgBc2vgXXh6SmoARqO4aE9PU,16517
-taxonomy_mapping/map_new_lila_datasets.py,sha256=rJlj-HuP9wNN2RvIlcWfqnW5N7cyiGLWglbe3FsFG0Q,4324
-taxonomy_mapping/prepare_lila_taxonomy_release.py,sha256=Ser_lwpbYR75fMMcE49uT90t7o02dRZ7wY0GUyhzK9c,4357
-taxonomy_mapping/preview_lila_taxonomy.py,sha256=iCcvf8dDsh1WZIZWq2ppua5wloAst6F6lphsS9vRTKQ,20144
-taxonomy_mapping/retrieve_sample_image.py,sha256=BySUy69DeGwPiIs9Ws5vIILJCTXeVImE5AVoawOiECM,1992
-taxonomy_mapping/simple_image_download.py,sha256=dXXVhhaR_bI-Elmk4Tmjt2ftdYzHbkuJCTzIMOJfLKs,6874
-taxonomy_mapping/species_lookup.py,sha256=oRqaUbiH_xULH7z5mkrtaFhacxlyM8KT-V-c4FnNq4w,28303
-taxonomy_mapping/taxonomy_csv_checker.py,sha256=xmV2SBOfQEuZBMGmXyUzbuNxvd_oXKysXkxU6-IhKJg,4874
-taxonomy_mapping/taxonomy_graph.py,sha256=ZDm2enGanBlm8KXWvCndqmeerOp9LREaetSl-Lxy07s,12361
-taxonomy_mapping/validate_lila_category_mappings.py,sha256=CApYVWIZ8TTJ3vvQTgfjIvWDGHpPo-Zn9jqJFaw3DNw,2314
-megadetector-5.0.7.dist-info/LICENSE,sha256=RMa3qq-7Cyk7DdtqRj_bP1oInGFgjyHn9-PZ3PcrqIs,1100
-megadetector-5.0.7.dist-info/METADATA,sha256=xgK96jYJkxj6kXvCzY3y8HlYb0-Oa44nmfETb2Ba7xI,7513
-megadetector-5.0.7.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-megadetector-5.0.7.dist-info/top_level.txt,sha256=-mFGpqnmviVz0Vyr2GxZ_kTo_PBPNoK6h4JtqIMjZGQ,88
-megadetector-5.0.7.dist-info/RECORD,,