diff options
Diffstat (limited to 'megapixels/commands')
| -rw-r--r-- | megapixels/commands/datasets/citations_to_csv.py | 35 | ||||
| -rw-r--r-- | megapixels/commands/datasets/pull_spreadsheet.py | 25 | ||||
| -rw-r--r-- | megapixels/commands/processor/body_roi_video.py | 148 |
3 files changed, 187 insertions, 21 deletions
diff --git a/megapixels/commands/datasets/citations_to_csv.py b/megapixels/commands/datasets/citations_to_csv.py index c6a04bd4..f3277d7e 100644 --- a/megapixels/commands/datasets/citations_to_csv.py +++ b/megapixels/commands/datasets/citations_to_csv.py @@ -35,9 +35,12 @@ def cli(ctx, opt_fp_in, opt_dir_out): else: fps_in = [opt_fp_in] - log.info(f'{fps_in}') + log.info(f'Converting {len(fps_in)} JSON files to CSV') for fp_in in fps_in: + + log.info(f'Processing: {Path(fp_in).name}') + with open(fp_in, 'r') as fp: json_data = json.load(fp) @@ -45,18 +48,22 @@ def cli(ctx, opt_fp_in, opt_dir_out): papers = [] dataset_key = json_data['paper']['key'] dataset_name = json_data['paper']['name'] - papers_main = get_orig_paper(json_data) - papers += papers_main - papers_citations = get_citations(dataset_key, dataset_name, json_data) - papers += papers_citations - papers = [p.to_dict() for p in papers] + try: + papers_main = get_orig_paper(json_data) + papers += papers_main + papers_citations = get_citations(dataset_key, dataset_name, json_data) + papers += papers_citations + papers = [p.to_dict() for p in papers] + except Exception as e: + log.error(f'{e} on {Path(fp_in).name}') + continue # save if not opt_dir_out: # save to same directory replacing ext fp_out = fp_in.replace('.json','.csv') else: - fp_out = join(opt_dir_out, Path(fp_in).name) + fp_out = join(opt_dir_out, f'{Path(fp_in).stem}.csv') df_papers = pd.DataFrame.from_dict(papers) df_papers.index.name = 'id' @@ -76,13 +83,13 @@ def get_citations(dataset_key, dataset_name, json_data): addresses = p.get('addresses', '') if addresses: for a in addresses: - pdf_url = '' if not p['pdf'] else p['pdf'][0] + pdf_url = '' if not p.get('pdf') else p.get('pdf')[0] paper = Paper(dataset_key, dataset_name, p['id'], p['title'], d_type, year, pdf_url, a['name'], a['type'], a['lat'], a['lng'], a['country']) papers.append(paper) else: - pdf_url = '' if not p['pdf'] else p['pdf'][0] + pdf_url = '' if not p.get('pdf') else p.get('pdf')[0] paper = Paper(p['key'], p['name'], d['id'], p['title'], 'main', year, pdf_url) papers.append(paper) return papers @@ -98,13 +105,13 @@ def get_orig_paper(json_data): for a in addresses: if type(a) == str or a is None: continue - pdf_url = '' if not p['pdf'] else p['pdf'][0] - paper = Paper(p['key'], p['name'], p['paper_id'], p['title'], d_type, year, + pdf_url = '' if not p.get('pdf') else p.get('pdf')[0] + paper = Paper(p.get('key'), p.get('name'), p.get('paper_id'), p.get('title'), d_type, year, pdf_url, - a['name'], a['type'], a['lat'], a['lng'], a['country']) + a.get('name'), a.get('type'), a.get('lat'), a.get('lng'), a.get('country')) papers.append(paper) else: - pdf_url = '' if not p['pdf'] else p['pdf'][0] - paper = Paper(p['key'], p['name'], p['paper_id'], p['title'], d_type, year, pdf_url) + pdf_url = '' if not p.get('pdf') else p.get('pdf')[0] + paper = Paper(p.get('key'), p.get('name'), p.get('paper_id'), p.get('title'), d_type, year, pdf_url) papers.append(paper) return papers diff --git a/megapixels/commands/datasets/pull_spreadsheet.py b/megapixels/commands/datasets/pull_spreadsheet.py index b8b68094..caf5eb43 100644 --- a/megapixels/commands/datasets/pull_spreadsheet.py +++ b/megapixels/commands/datasets/pull_spreadsheet.py @@ -21,6 +21,10 @@ from app.utils.logger_utils import Logger log = Logger.getLogger() opt_sheets = ['datasets', 'relationships', 'funding', 'references', 'sources', 'tags', 'citations', 'legal'] +dataset_sheet_keys = ['key', 'name_short', 'name_full', 'url', 'dl_im', 'purpose', 'funded_by', + 'year_start', 'year_end', 'year_published', 'images', 'videos', 'identities', + 'faces_or_persons', 'campus', 'youtube', 'flickr', 'google', 'bing', 'comment'] + @click.command() @click.option('-n', '--name', 'opt_spreadsheets', multiple=True, @@ -30,11 +34,15 @@ opt_sheets = ['datasets', 'relationships', 'funding', 'references', 'sources', ' @click.option('--all', 'opt_all', is_flag=True, help='Get all sheets') @click.option('-o', '--output', 'opt_fp_out', required=True, + type=click.Path(file_okay=False, dir_okay=True), help='Path to directory or filename') +@click.option('--share', 'opt_share', required=True, + type=click.Choice(['nyt', 'ft']), + help='Share filter') @click.option('-f', '--force', 'opt_force', is_flag=True, help='Force overwrite') @click.pass_context -def cli(ctx, opt_spreadsheets, opt_fp_out, opt_all, opt_force): +def cli(ctx, opt_spreadsheets, opt_fp_out, opt_all, opt_share, opt_force): """Fetch Google spreadsheet""" import sys @@ -47,6 +55,12 @@ def cli(ctx, opt_spreadsheets, opt_fp_out, opt_all, opt_force): for sheet_name in opt_spreadsheets: log.info(f'Get spreadsheet: {sheet_name}') + fp_out = join(opt_fp_out, f'{sheet_name}.csv') + fpp_out = Path(fp_out) + if fpp_out.exists() and not opt_force: + log.error(f'File "{fpp_out} exists. Use "-f" to overwrite') + return + sheet_data = fetch_google_sheet_objects(name=sheet_name) df_sheet = pd.DataFrame.from_dict(sheet_data) if sheet_name == 'datasets': @@ -58,22 +72,19 @@ def cli(ctx, opt_spreadsheets, opt_fp_out, opt_all, opt_force): fpp_out = fpp_out.parent else: fpp_out = join(opt_fp_out, f'{sheet_name}.csv') + log.info(f'Writing file: {fpp_out}') df_sheet.to_csv(fpp_out) def clean_datasets_sheet_ft(df): # clean data for FT df = df[df['ft_share'] == 'Y'] - keys = ['key', 'name_short', 'name_full', 'url', 'downloaded', 'purpose', 'wild'] - keys += ['campus', 'year_start', 'year_end', 'year_published', 'images', 'videos', 'identities', 'faces_or_persons', 'youtube', 'flickr', 'google', 'bing', 'comment'] - return df[keys] + return df[dataset_sheet_keys] def clean_datasets_sheet_nyt(df): # clean data for FT df = df[df['ft_share'] == 'Y'] - keys = ['key', 'name_short', 'name_full', 'url', 'downloaded', 'purpose', 'wild'] - keys += ['campus', 'year_start', 'year_end', 'year_published', 'images', 'videos', 'identities', 'faces_or_persons', 'youtube', 'flickr', 'google', 'bing', 'comment'] - return df[keys] + return df[dataset_sheet_keys] def fetch_spreadsheet(): """Open the Google Spreadsheet, which contains the individual worksheets""" diff --git a/megapixels/commands/processor/body_roi_video.py b/megapixels/commands/processor/body_roi_video.py new file mode 100644 index 00000000..84bcebd2 --- /dev/null +++ b/megapixels/commands/processor/body_roi_video.py @@ -0,0 +1,148 @@ +""" +Crop images to prepare for training +""" + +import click +# from PIL import Image, ImageOps, ImageFilter, ImageDraw + +from app.settings import types +from app.utils import click_utils +from app.settings import app_cfg as cfg + +color_filters = {'color': 1, 'gray': 2, 'all': 3} + +@click.command() +@click.option('-i', '--input', 'opt_fp_in', required=True, + help='Override enum input filename CSV') +@click.option('-o', '--output', 'opt_fp_out', required=True, + help='Override enum output filename CSV') +@click.option('--store', 'opt_data_store', + type=cfg.DataStoreVar, + default=click_utils.get_default(types.DataStore.HDD), + show_default=True, + help=click_utils.show_help(types.Dataset)) +@click.option('--size', 'opt_size', + type=(int, int), default=(640, 480), + help='Input image size') +@click.option('-d', '--detector', 'opt_detector_type', + type=cfg.BodyDetectNetVar, + default=click_utils.get_default(types.BodyDetectNet.CVDNN), + help=click_utils.show_help(types.BodyDetectNet)) +@click.option('-g', '--gpu', 'opt_gpu', default=0, + help='GPU index') +@click.option('--conf', 'opt_conf_thresh', default=0.85, type=click.FloatRange(0,1), + help='Confidence minimum threshold') +@click.option('-p', '--pyramids', 'opt_pyramids', default=0, type=click.IntRange(0,4), + help='Number pyramids to upscale for DLIB detectors') +@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None), + help='Slice list of files') +@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False, + help='Display detections to debug') +@click.option('-f', '--force', 'opt_force', is_flag=True, + help='Force overwrite file') +@click.option('--color', 'opt_color_filter', + type=click.Choice(color_filters.keys()), default='color', + help='Filter to keep color or grayscale images (color = keep color') +@click.option('--keep', 'opt_largest', type=click.Choice(['largest', 'all']), default='largest', + help='Only keep largest face') +@click.option('--zone', 'opt_zone', default=(0.0, 0.0), type=(float, float), + help='Face center must be located within zone region (0.5 = half width/height)') +@click.pass_context +def cli(ctx, opt_fp_in, opt_fp_out, opt_data_store, opt_size, opt_detector_type, + opt_gpu, opt_conf_thresh, opt_pyramids, opt_slice, opt_display, opt_force, opt_color_filter, + opt_largest, opt_zone): + """Converts frames with faces to CSV of ROIs""" + + import sys + import os + from os.path import join + from pathlib import Path + from glob import glob + + from tqdm import tqdm + import numpy as np + import dlib # must keep a local reference for dlib + import cv2 as cv + import pandas as pd + + from app.utils import logger_utils, file_utils, im_utils, display_utils, draw_utils + from app.processors import person_detector + from app.models.data_store import DataStore + + # ------------------------------------------------- + # init here + + log = logger_utils.Logger.getLogger() + + opt_fp_out = opt_fp_out + if not opt_force and Path(opt_fp_out).exists(): + log.error('File exists. Use "-f / --force" to overwite') + return + + # set detector + if opt_detector_type == types.BodyDetectNet.CVDNN: + detector = person_detector.DetectorCVDNN() + else: + log.error('{} not yet implemented'.format(opt_detector_type.name)) + return + + # set largest flag, to keep all or only largest + opt_largest = (opt_largest == 'largest') + + # process video + cap = cv.VideoCapture(opt_fp_in) + + bboxes_all = [] + data_out = [] + frame_index = 0 + + while cap.isOpened(): + # get video frame + readable, im = cap.read() + if not readable: + break + + im_resized = im_utils.resize(im, width=opt_size[0], height=opt_size[1]) + + try: + bboxes_norm = detector.detect(im_resized, pyramids=opt_pyramids, largest=opt_largest, + zone=opt_zone, conf=opt_conf_thresh, blob_size=opt_size) + except Exception as e: + log.error('could not detect: {}'.format(frame_index)) + log.error('{}'.format(e)) + continue + + for bbox in bboxes_norm: + roi = { + 'record_index': frame_index, + 'x': bbox.x, + 'y': bbox.y, + 'w': bbox.w, + 'h': bbox.h + } + data_out.append(roi) + + if opt_display and len(bboxes_norm): + # draw each box + for bbox_norm in bboxes_norm: + dim = im_resized.shape[:2][::-1] + bbox_dim = bbox.to_dim(dim) + # if dim[0] > 1000: + # im_resized = im_utils.resize(im_resized, width=1000) + im_resized = draw_utils.draw_bbox(im_resized, bbox_norm) + + # display and wait + cv.imshow('', im_resized) + display_utils.handle_keyboard_video() + + frame_index += 1 + + + # create DataFrame and save to CSV + file_utils.mkdirs(opt_fp_out) + df = pd.DataFrame.from_dict(data_out) + df.index.name = 'index' + df.to_csv(opt_fp_out) + + # save script + file_utils.write_text(' '.join(sys.argv), '{}.sh'.format(opt_fp_out))
\ No newline at end of file |