megadetector 5.0.7__tar.gz → 5.0.8__tar.gz

{megadetector-5.0.7/megadetector.egg-info → megadetector-5.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: megadetector
-Version: 5.0.7
+Version: 5.0.8
 Summary: MegaDetector is an AI model that helps conservation folks spend less time doing boring things with camera trap images.
 Author-email: Your friendly neighborhood MegaDetector team <cameratraps@lila.science>
 Maintainer-email: Your friendly neighborhood MegaDetector team <cameratraps@lila.science>
@@ -60,7 +60,7 @@ If you want to learn more about what MegaDetector is all about, head over to the
 
 ### If you are an ecologist...
 
-If you are an ecologist looking to use MegaDetector to help you get through your camera trap images, you probably don't want this package.  We recommend starting with our "[Getting started with MegaDetector](https://github.com/agentmorris/MegaDetector/blob/main/collaborations.md)" page, then digging in to the [MegaDetector User Guide](https://github.com/agentmorris/MegaDetector/blob/main/megadetector.md), which will walk you through the process of using MegaDetector.  That journey will <i>not</i> involve this package.
+If you are an ecologist looking to use MegaDetector to help you get through your camera trap images, you probably don't want this package.  We recommend starting with our "[Getting started with MegaDetector](https://github.com/agentmorris/MegaDetector/blob/main/collaborations.md)" page, then digging in to the [MegaDetector User Guide](https://github.com/agentmorris/MegaDetector/blob/main/megadetector.md), which will walk you through the process of using MegaDetector.  That journey will <i>not</i> involve this Python package.
 
 ### If you are a computer-vision-y type...
 
@@ -95,15 +95,13 @@ temporary_filename = url_utils.download_url(image_url)
 
 image = vis_utils.load_image(temporary_filename)
 
-# This will automatically download MDv5a to the system temp folder;
-# you can also specify a filename explicitly, or set the $MDV5A
-# environment variable to point to the model file.
+# This will automatically download MDv5a; you can also specify a filename.
 model = run_detector.load_detector('MDV5A')
 
 result = model.generate_detections_one_image(image)
 
 detections_above_threshold = [d for d in result['detections'] if d['conf'] > 0.2]
-print('Found {} detection above threshold'.format(len(detections_above_threshold)))
+print('Found {} detections above threshold'.format(len(detections_above_threshold)))
 ```
 
 #### Run MegaDetector on a folder of images
@@ -120,14 +118,14 @@ output_file = os.path.expanduser('~/megadetector_output_test.json')
 # Recursively find images
 image_file_names = path_utils.find_images(image_folder,recursive=True)
 
-# This will automatically download MDv5a to the system temp folder;
-# you can also specify a filename explicitly, or set the $MDV5A
-# environment variable to point to the model file.
+# This will automatically download MDv5a; you can also specify a filename.
 results = load_and_run_detector_batch('MDV5A', image_file_names)
 
-# Write results as relative filenames, this is what Timelapse
-# and other downstream tools expect.
-write_results_to_file(results,output_file,relative_path_base=image_folder)
+# Write results to a format that Timelapse and other downstream tools like.
+write_results_to_file(results,
+                      output_file,
+                      relative_path_base=image_folder,
+                      detector_file=detector_filename)
 ```
 
 ## Contact

{megadetector-5.0.7 → megadetector-5.0.8}/README-package.md

@@ -9,7 +9,7 @@ If you want to learn more about what MegaDetector is all about, head over to the
 
 ### If you are an ecologist...
 
-If you are an ecologist looking to use MegaDetector to help you get through your camera trap images, you probably don't want this package.  We recommend starting with our "[Getting started with MegaDetector](https://github.com/agentmorris/MegaDetector/blob/main/collaborations.md)" page, then digging in to the [MegaDetector User Guide](https://github.com/agentmorris/MegaDetector/blob/main/megadetector.md), which will walk you through the process of using MegaDetector.  That journey will <i>not</i> involve this package.
+If you are an ecologist looking to use MegaDetector to help you get through your camera trap images, you probably don't want this package.  We recommend starting with our "[Getting started with MegaDetector](https://github.com/agentmorris/MegaDetector/blob/main/collaborations.md)" page, then digging in to the [MegaDetector User Guide](https://github.com/agentmorris/MegaDetector/blob/main/megadetector.md), which will walk you through the process of using MegaDetector.  That journey will <i>not</i> involve this Python package.
 
 ### If you are a computer-vision-y type...
 
@@ -44,15 +44,13 @@ temporary_filename = url_utils.download_url(image_url)
 
 image = vis_utils.load_image(temporary_filename)
 
-# This will automatically download MDv5a to the system temp folder;
-# you can also specify a filename explicitly, or set the $MDV5A
-# environment variable to point to the model file.
+# This will automatically download MDv5a; you can also specify a filename.
 model = run_detector.load_detector('MDV5A')
 
 result = model.generate_detections_one_image(image)
 
 detections_above_threshold = [d for d in result['detections'] if d['conf'] > 0.2]
-print('Found {} detection above threshold'.format(len(detections_above_threshold)))
+print('Found {} detections above threshold'.format(len(detections_above_threshold)))
 ```
 
 #### Run MegaDetector on a folder of images
@@ -69,14 +67,14 @@ output_file = os.path.expanduser('~/megadetector_output_test.json')
 # Recursively find images
 image_file_names = path_utils.find_images(image_folder,recursive=True)
 
-# This will automatically download MDv5a to the system temp folder;
-# you can also specify a filename explicitly, or set the $MDV5A
-# environment variable to point to the model file.
+# This will automatically download MDv5a; you can also specify a filename.
 results = load_and_run_detector_batch('MDV5A', image_file_names)
 
-# Write results as relative filenames, this is what Timelapse
-# and other downstream tools expect.
-write_results_to_file(results,output_file,relative_path_base=image_folder)
+# Write results to a format that Timelapse and other downstream tools like.
+write_results_to_file(results,
+                      output_file,
+                      relative_path_base=image_folder,
+                      detector_file=detector_filename)
 ```
 
 ## Contact

{megadetector-5.0.7 → megadetector-5.0.8}/README.md

@@ -4,35 +4,16 @@
 
 ## Table of contents
 
-1. [Repo overview](#repo-overview)
-2. [What's MegaDetector all about?](#whats-megadetector-all-about)
+1. [What's MegaDetector all about?](#whats-megadetector-all-about)
 3. [How do I get started with MegaDetector?](#how-do-i-get-started-with-megadetector)
 4. [Who is using MegaDetector?](#who-is-using-megadetector)
 5. [Repo contents](#repo-contents)
 6. [Contact](#contact)
 7. [Gratuitous camera trap picture](#gratuitous-camera-trap-picture)
 
-
-## Repo overview
-
-This repo contains the tools for training and running [MegaDetector](megadetector.md), an object detection model that does a pretty good job finding animals, people, and vehicles (and therefore is pretty good at finding empty images) in camera trap images in a variety of terrestrial ecosystems.
-
-The core functionality provided is:
-
-- Training and running [MegaDetector](megadetector.md).
-- Training and running some [species classifiers](classification) that are used in conjunction with MegaDetector.
-- Tools to [convert](data_management) frequently-used camera trap metadata formats into a common format.
-- A [batch processing API](https://github.com/agentmorris/MegaDetector/tree/main/api/batch_processing) that runs MegaDetector on large image collections, to accelerate population surveys.
-- A [real-time API](https://github.com/agentmorris/MegaDetector/tree/main/api/synchronous) that runs MegaDetector (and some species classifiers) synchronously, primarily to support biosecurity applications.
-
-MegaDetector was initially developed by the [Microsoft AI for Earth program](https://www.microsoft.com/en-us/ai/ai-for-earth); this repo was forked from the microsoft/cameratraps repo and is maintained by the original MegaDetector developers (who are no longer at Microsoft, but are absolutely fantastically eternally grateful to Microsoft for the investment and commitment that made MegaDetector happen).
-
-
 ## What's MegaDetector all about?
 
-[MegaDetector](megadetector.md) is an object detection model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images).  This model is trained on several hundred thousand bounding boxes from a variety of ecosystems.  Lots more information – including download links and instructions for running the model – is available in the [MegaDetector User Guide](megadetector.md).
-
-This repo does not host the data used to train MegaDetector, but we work with our collaborators to make data and annotations available whenever possible on [lila.science](http://lila.science).  See the [MegaDetector training data](megadetector.md#can-you-share-the-training-data) section to learn more about the data used to train MegaDetector.
+[MegaDetector](megadetector.md) is an AI model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images).  This model is trained on several million images from a variety of ecosystems.
 
 Here's a “teaser” image of what MegaDetector output looks like:
 
@@ -41,11 +22,11 @@ Here's a “teaser” image of what MegaDetector output looks like:
 
 ## How do I get started with MegaDetector?
 
-If you're just considering the use of AI in your workflow, and you aren't even sure yet whether MegaDetector would be useful to you, we recommend reading the "[getting started with MegaDetector](collaborations.md)" page.
-
-If you're already familiar with MegaDetector and you're ready to run it on your data (and you have some familiarity with running Python code), see the [MegaDetector User Guide](megadetector.md) for instructions on downloading and running MegaDetector.
-
-If you're a programmer-type looking to use tools from this repo, we generally recommend cloning the repo, but there is also a [Python package](https://pypi.org/project/megadetector/) that provides access to everything in this repo (yes, you guessed it, "pip install megadetector").
+* If you are looking for a convenient tool to run MegaDetector, you don't need anything from this repository: check out [EcoAssist](https://github.com/PetervanLunteren/EcoAssist?tab=readme-ov-file).
+* If you're just <i>considering</i> the use of AI in your workflow, and you aren't even sure yet whether MegaDetector would be useful to you, we recommend reading the "[getting started with MegaDetector](collaborations.md)" page.
+* If you're already familiar with MegaDetector and you're ready to run it on your data, see the [MegaDetector User Guide](megadetector.md) for instructions on running MegaDetector.
+* If you're a programmer-type looking to use tools from this repo, check out the [Python package](https://pypi.org/project/megadetector/) that provides access to everything in this repo (yes, you guessed it, "pip install megadetector").
+* If you have any questions, or you want to tell us that MegaDetector was amazing/terrible on your images, <a href="mailto:cameratraps@lila.science">email us</a>!
 
 MegaDetector is just one of many tools that aims to make conservation biologists more efficient with AI.  If you want to learn about other ways to use AI to accelerate camera trap workflows, check out our of the field, affectionately titled &ldquo;[Everything I know about machine learning and camera traps](https://agentmorris.github.io/camera-trap-ml-survey/)&rdquo;.
 
@@ -57,6 +38,7 @@ We work with ecologists all over the world to help them spend less time annotati
 Here are a few of the organizations that have used MegaDetector... we're only listing organizations who (a) we know about and (b) have given us permission to refer to them here (or have posted publicly about their use of MegaDetector), so if you're using MegaDetector or other tools from this repo and would like to be added to this list, <a href="mailto:cameratraps@lila.science">email us</a>!
 
 * [Arizona Department of Environmental Quality](http://azdeq.gov/)
+* [Biometrio.earth](https://biometrio.earth/)
 * [Blackbird Environmental](https://blackbirdenv.com/)
 * [Camelot](https://camelotproject.org/)
 * [Canadian Parks and Wilderness Society (CPAWS) Northern Alberta Chapter](https://cpawsnab.org/)
@@ -65,10 +47,10 @@ Here are a few of the organizations that have used MegaDetector... we're only li
 * [Dudek Camera Trap AI Image Toolkit (AIT)](https://dudek.com/services/wildlife-camera-trap-ai-image-processing-and-management/)
 * [EcoLogic Consultants Ltd.](https://www.consult-ecologic.com/)
 * [Estación Biológica de Doñana](http://www.ebd.csic.es/inicio)
-* [Idaho Department of Fish and Game](https://idfg.idaho.gov/)
-* [Island Conservation](https://www.islandconservation.org/)
+* [Indigenous Desert Alliance](https://www.indigenousdesertalliance.com/)
 * [Myall Lakes Dingo Project](https://carnivorecoexistence.info/myall-lakes-dingo-project/)
 * [Norwegian Institute for Nature Research](https://www.nina.no/english/Home)
+* [Okala](https://www.okala.io/)
 * [Point No Point Treaty Council](https://pnptc.org/)
 * [Ramat Hanadiv Nature Park](https://www.ramat-hanadiv.org.il/en/)
 * [SPEA (Portuguese Society for the Study of Birds)](https://spea.pt/en/)
@@ -94,10 +76,12 @@ Here are a few of the organizations that have used MegaDetector... we're only li
 * [Cross-Cultural Ecology Lab](https://crossculturalecology.net/), Macquarie University
 * [DC Cat Count](https://hub.dccatcount.org/), led by the Humane Rescue Alliance
 * [Department of Fish and Wildlife Sciences](https://www.uidaho.edu/cnr/departments/fish-and-wildlife-sciences), University of Idaho
+* [Department of Society & Conservation](https://www.umt.edu/environment/about/departments/socon/), W.A. Franke College of Forestry & Conservation, University of Montana
 * [Department of Wildlife Ecology and Conservation](https://wec.ifas.ufl.edu/), University of Florida
 * [Ecology and Conservation of Amazonian Vertebrates Research Group](https://www.researchgate.net/lab/Fernanda-Michalski-Lab-4), Federal University of Amapá
 * [Gola Forest Programma](https://www.rspb.org.uk/our-work/conservation/projects/scientific-support-for-the-gola-forest-programme/), Royal Society for the Protection of Birds (RSPB)
 * [Graeme Shannon's Research Group](https://wildliferesearch.co.uk/group-1), Bangor University 
+* [Grizzly Bear Recovery Program](https://www.fws.gov/office/grizzly-bear-recovery-program), U.S. Fish & Wildlife Service
 * [Hamaarag](https://hamaarag.org.il/), The Steinhardt Museum of Natural History, Tel Aviv University
 * [Institut des Science de la Forêt Tempérée](https://isfort.uqo.ca/) (ISFORT), Université du Québec en Outaouais
 * [Lab of Dr. Bilal Habib](https://bhlab.in/about), the Wildlife Institute of India
@@ -111,6 +95,7 @@ Here are a few of the organizations that have used MegaDetector... we're only li
 * [Seattle Urban Carnivore Project](https://www.zoo.org/seattlecarnivores), Woodland Park Zoo
 * [Serra dos Órgãos National Park](https://www.icmbio.gov.br/parnaserradosorgaos/), ICMBio
 * [Snapshot USA](https://emammal.si.edu/snapshot-usa), Smithsonian
+* [TROPECOLNET project](https://www.anabenitezlopez.com/research/global-change-biology/tropecolnet/), Museo Nacional de Ciencias Naturales
 * [Wildlife Coexistence Lab](https://wildlife.forestry.ubc.ca/), University of British Columbia
 * [Wildlife Research](https://www.dfw.state.or.us/wildlife/research/index.asp), Oregon Department of Fish and Wildlife
 * [Wildlife Division](https://www.michigan.gov/dnr/about/contact/wildlife), Michigan Department of Natural Resources
@@ -122,9 +107,12 @@ Here are a few of the organizations that have used MegaDetector... we're only li
 * [School of Natural Sciences](https://www.utas.edu.au/natural-sciences), University of Tasmania ([story](https://www.utas.edu.au/about/news-and-stories/articles/2022/1204-innovative-camera-network-keeps-close-eye-on-tassie-wildlife))
 * [Kenai National Wildlife Refuge](https://www.fws.gov/refuge/kenai), U.S. Fish & Wildlife Service ([story](https://www.peninsulaclarion.com/sports/refuge-notebook-new-technology-increases-efficiency-of-refuge-cameras/))
 
-* [Australian Wildlife Conservancy](https://www.australianwildlife.org/) (blog posts [1](https://www.australianwildlife.org/cutting-edge-technology-delivering-efficiency-gains-in-conservation/), [2](https://www.australianwildlife.org/efficiency-gains-at-the-cutting-edge-of-technology/))
+* [Idaho Department of Fish and Game](https://idfg.idaho.gov/) ([fancy PBS video](https://www.youtube.com/watch?v=uEsL8EZKpbA&t=261s&ab_channel=OutdoorIdaho))
+* [Australian Wildlife Conservancy](https://www.australianwildlife.org/) (blog posts [1](https://www.australianwildlife.org/cutting-edge-technology-delivering-efficiency-gains-in-conservation/), [2](https://www.australianwildlife.org/efficiency-gains-at-the-cutting-edge-of-technology/), [3](https://www.australianwildlife.org/federal-grant-to-fund-ai-supported-wildlife-recognisers))
 * [Bavarian Forest National Park](https://www.nationalpark-bayerischer-wald.bayern.de/english/index.htm) ([story](https://customers.microsoft.com/en-au/story/1667539539271247797-nationalparkbayerischerwald-azure-en))
+* [Environs Kimberley](https://www.environskimberley.org.au) ([blog post](https://www.environskimberley.org.au/ai_megadetector))
 * [Felidae Conservation Fund](https://felidaefund.org/) ([WildePod platform](https://wildepod.org/)) ([blog post](https://abhaykashyap.com/blog/ai-powered-camera-trap-image-annotation-system/))
+* [Island Conservation](https://www.islandconservation.org/) (blog posts [1](https://www.islandconservation.org/conservation-machine-learning/),[2](https://news.lenovo.com/island-conservation-machine-learning-solutions-nvidia-island-ecosystems/?sprinklrid=12869857824&linkId=356951919)) ([video](https://www.lenovo.com/content/dam/lenovo/iso/customer-references-coe/one-lenovo-customer-stories/wfh/videos/WFH-One-Lenovo-ENG-subtitles.mp4))
 * [Alberta Biodiversity Monitoring Institute (ABMI)](https://www.abmi.ca/home.html) ([WildTrax platform](https://www.wildtrax.ca/)) (blog posts [1](https://wildcams.ca/blog/the-abmi-visits-the-zoo/),[2](http://blog.abmi.ca/2023/06/14/making-wildtrax-its-not-a-kind-of-magic-behind-the-screen/))
 * [Shan Shui Conservation Center](http://en.shanshui.org/) ([blog post](https://mp.weixin.qq.com/s/iOIQF3ckj0-rEG4yJgerYw?fbclid=IwAR0alwiWbe3udIcFvqqwm7y5qgr9hZpjr871FZIa-ErGUukZ7yJ3ZhgCevs)) ([translated blog post](https://mp-weixin-qq-com.translate.goog/s/iOIQF3ckj0-rEG4yJgerYw?fbclid=IwAR0alwiWbe3udIcFvqqwm7y5qgr9hZpjr871FZIa-ErGUukZ7yJ3ZhgCevs&_x_tr_sl=auto&_x_tr_tl=en&_x_tr_hl=en&_x_tr_pto=wapp)) ([Web demo](https://cameratrap-ai.hinature.cn/home))
 * [Irvine Ranch Conservancy](http://www.irconservancy.org/) ([story](https://www.ocregister.com/2022/03/30/ai-software-is-helping-researchers-focus-on-learning-about-ocs-wild-animals/))
@@ -134,8 +122,9 @@ Here are a few of the organizations that have used MegaDetector... we're only li
 * [Trapper](https://trapper-project.readthedocs.io/en/latest/overview.html) ([tutorial](https://trapper-project.readthedocs.io/en/latest/tutorial.html))
 
 * [Road Ecology Center](https://roadecology.ucdavis.edu/), University of California, Davis ([Wildlife Observer Network platform](https://wildlifeobserver.net/))
-* [The Nature Conservancy in California](https://www.nature.org/en-us/about-us/where-we-work/united-states/california/) ([Animl platform](https://github.com/tnc-ca-geo/animl-frontend))
+* [The Nature Conservancy in California](https://www.nature.org/en-us/about-us/where-we-work/united-states/california/) ([Animl platform](https://github.com/tnc-ca-geo/animl-frontend)) ([story](https://www.vision-systems.com/non-factory/environment-agriculture/article/14304433/the-nature-conservancy-brings-cameras-ai-to-invasive-species-prevention))
 * [San Diego Zoo Wildlife Alliance](https://science.sandiegozoo.org/)  ([Animl R package](https://github.com/conservationtechlab/animl))
+* [TerrOïko](https://www.terroiko.fr/) ([OCAPI platform](https://www.terroiko.fr/ocapi))
 
 Also see:
 
@@ -145,10 +134,25 @@ Also see:
 
 * The list of papers tagged "MegaDetector" on our [list of papers about ML and camera traps](https://agentmorris.github.io/camera-trap-ml-survey/#camera-trap-ml-papers)
 
+
 ## Repo contents
 
 This repo is organized into the following folders...
 
+This repo contains the tools for training and running [MegaDetector](megadetector.md), an object detection model that does a pretty good job finding animals, people, and vehicles (and therefore is pretty good at finding empty images) in camera trap images in a variety of terrestrial ecosystems.
+
+The core functionality provided is:
+
+- Training and running [MegaDetector](megadetector.md).
+- Training and running some [species classifiers](classification) that are used in conjunction with MegaDetector.
+- Tools to [convert](data_management) frequently-used camera trap metadata formats into a common format.
+- A [batch processing API](https://github.com/agentmorris/MegaDetector/tree/main/api/batch_processing) that runs MegaDetector on large image collections, to accelerate population surveys.
+- A [real-time API](https://github.com/agentmorris/MegaDetector/tree/main/api/synchronous) that runs MegaDetector (and some species classifiers) synchronously, primarily to support biosecurity applications.
+
+This repo does not host the data used to train MegaDetector, but we work with our collaborators to make data and annotations available whenever possible on [lila.science](http://lila.science).  See the [MegaDetector training data](megadetector.md#can-you-share-the-training-data) section to learn more about the data used to train MegaDetector.
+
+MegaDetector was initially developed by the [Microsoft AI for Earth program](https://www.microsoft.com/en-us/ai/ai-for-earth); this repo was forked from the microsoft/cameratraps repo and is maintained by the original MegaDetector developers (who are no longer at Microsoft, but are absolutely fantastically eternally grateful to Microsoft for the investment and commitment that made MegaDetector happen).
+
 
 ### api
 

{megadetector-5.0.7 → megadetector-5.0.8}/api/batch_processing/data_preparation/manage_local_batch.py

@@ -86,6 +86,8 @@ from api.batch_processing.postprocessing.postprocess_batch_results import (
 from detection.run_detector import get_detector_version_from_filename
 from md_utils.ct_utils import image_file_to_camera_folder
 
+## Inference options
+
 # To specify a non-default confidence threshold for including detections in the .json file
 json_threshold = None
 
@@ -109,6 +111,11 @@ quiet_mode = True
 # will use its default size, which is 1280 * 1.3, which is almost always what you want.
 image_size = None
 
+# Should we include image size, timestamp, and/or EXIF data in MD output?
+include_image_size = False
+include_image_timestamp = False
+include_exif_data = False
+
 # Only relevant when running on CPU
 ncores = 1
 
@@ -187,7 +194,7 @@ augment = False
 
 ## Constants related to tiled inference
 
-use_tiled_inference = True
+use_tiled_inference = False
 
 # Should we delete tiles after each job?  Only set this to False for debugging;
 # large jobs will take up a lot of space if you keep tiles around after each task.
@@ -234,7 +241,7 @@ checkpoint_frequency = 10000
 approx_images_per_second = estimate_md_images_per_second(model_file) 
     
 # Rough estimate for the inference time cost of augmentation    
-if augment:
+if augment and (approx_images_per_second is not None):
     approx_images_per_second = approx_images_per_second * 0.7
     
 base_task_name = organization_name_short + '-' + job_date + job_description_string + '-' + \
@@ -268,6 +275,10 @@ filename_base = os.path.join(base_output_folder_name, base_task_name)
 combined_api_output_folder = os.path.join(filename_base, 'combined_api_outputs')
 postprocessing_output_folder = os.path.join(filename_base, 'preview')
 
+combined_api_output_file = os.path.join(
+    combined_api_output_folder,
+    '{}_detections.json'.format(base_task_name))
+
 os.makedirs(filename_base, exist_ok=True)
 os.makedirs(combined_api_output_folder, exist_ok=True)
 os.makedirs(postprocessing_output_folder, exist_ok=True)
@@ -494,7 +505,14 @@ for i_task,task in enumerate(task_info):
         
         overwrite_handling_string = '--overwrite_handling {}'.format(overwrite_handling)        
         cmd = f'{cuda_string} python run_detector_batch.py "{model_file}" "{chunk_file}" "{output_fn}" {checkpoint_frequency_string} {checkpoint_path_string} {use_image_queue_string} {ncores_string} {quiet_string} {image_size_string} {confidence_threshold_string} {overwrite_handling_string}'
-                
+        
+        if include_image_size:
+            cmd += ' --include_image_size'
+        if include_image_timestamp:
+            cmd += ' --include_image_timestamp'
+        if include_exif_data:
+            cmd += ' --include_exif_data'
+        
     cmd_file = os.path.join(filename_base,'run_chunk_{}_gpu_{}{}'.format(str(i_task).zfill(3),
                             str(gpu_number).zfill(2),script_extension))
     
@@ -747,10 +765,6 @@ for im in combined_results['images']:
     else:
         im['file'] = im['file'].replace(input_path + '/','',1)
     
-combined_api_output_file = os.path.join(
-    combined_api_output_folder,
-    '{}_detections.json'.format(base_task_name))
-
 with open(combined_api_output_file,'w') as f:
     json.dump(combined_results,f,indent=1)
 
@@ -793,7 +807,7 @@ options.api_output_file = combined_api_output_file
 options.output_dir = output_base
 ppresults = process_batch_results(options)
 html_output_file = ppresults.output_html_file
-path_utils.open_file(html_output_file,attempt_to_open_in_wsl_host=True)
+path_utils.open_file(html_output_file,attempt_to_open_in_wsl_host=True,browser_name='chrome')
 # import clipboard; clipboard.copy(html_output_file)
 
 
@@ -823,7 +837,7 @@ options.otherDetectionsThreshold = options.confidenceMin
 
 options.bRenderDetectionTiles = True
 options.maxOutputImageWidth = 2000
-options.detectionTilesMaxCrops = 300
+options.detectionTilesMaxCrops = 250
 
 # options.lineThickness = 5
 # options.boxExpansion = 8
@@ -930,7 +944,7 @@ options.output_dir = output_base
 ppresults = process_batch_results(options)
 html_output_file = ppresults.output_html_file
 
-path_utils.open_file(html_output_file,attempt_to_open_in_wsl_host=True)
+path_utils.open_file(html_output_file,attempt_to_open_in_wsl_host=True,browser_name='chrome')
 # import clipboard; clipboard.copy(html_output_file)
 
 
@@ -2003,7 +2017,7 @@ print('Processing {} to {}'.format(base_task_name, output_base))
 options.api_output_file = sequence_smoothed_classification_file
 options.output_dir = output_base
 ppresults = process_batch_results(options)
-path_utils.open_file(ppresults.output_html_file,attempt_to_open_in_wsl_host=True)
+path_utils.open_file(ppresults.output_html_file,attempt_to_open_in_wsl_host=True,browser_name='chrome')
 # import clipboard; clipboard.copy(ppresults.output_html_file)
 
 #% Zip .json files
@@ -2071,7 +2085,7 @@ for i, j in itertools.combinations(list(range(0,len(filenames))),2):
 results = compare_batch_results(options)
 
 from md_utils.path_utils import open_file
-open_file(results.html_output_file,attempt_to_open_in_wsl_host=True)
+open_file(results.html_output_file,attempt_to_open_in_wsl_host=True,browser_name='chrome')
 
 
 #%% Merge in high-confidence detections from another results file
@@ -2125,7 +2139,7 @@ options.output_dir = output_base_large_boxes
 
 ppresults = process_batch_results(options)
 html_output_file = ppresults.output_html_file
-path_utils.open_file(html_output_file,attempt_to_open_in_wsl_host=True)
+path_utils.open_file(html_output_file,attempt_to_open_in_wsl_host=True,browser_name='chrome')
 
 
 #%% .json splitting
@@ -2280,7 +2294,7 @@ import nbformat as nbf
 if os.name == 'nt':
     git_base = r'c:\git'
 else:
-    git_base = os.path.expanduer('~/git')
+    git_base = os.path.expanduser('~/git')
     
 input_py_file = git_base + '/MegaDetector/api/batch_processing/data_preparation/manage_local_batch.py'
 assert os.path.isfile(input_py_file)

{megadetector-5.0.7 → megadetector-5.0.8}/api/batch_processing/postprocessing/combine_api_outputs.py

@@ -48,7 +48,7 @@ def combine_api_output_files(input_files: List[str],
         input_files: list of str, paths to JSON detection files
         output_file: optional str, path to write merged JSON
         require_uniqueness: bool, whether to require that the images in
-            each input_dict be unique
+            each list of images be unique
     """
     
     def print_if_verbose(s):
@@ -84,7 +84,7 @@ def combine_api_output_dictionaries(input_dicts: Iterable[Mapping[str, Any]],
         input_dicts: list of dicts, each dict is the JSON of the detections
             output file from the Batch Processing API
         require_uniqueness: bool, whether to require that the images in
-            each input_dict be unique
+            each input dict be unique
 
     Returns: dict, represents the merged JSON
     """

{megadetector-5.0.7 → megadetector-5.0.8}/api/batch_processing/postprocessing/compare_batch_results.py

@@ -291,7 +291,7 @@ def pairwise_compare_batch_results(options,output_index,pairwise_options):
     filenames_b_set = set([im['file'] for im in images_b])
     
     if len(images_a) != len(images_b):
-        s = 'set A has {} iamges, set B has {}'.format(len(images_a),len(images_b))
+        s = 'set A has {} images, set B has {}'.format(len(images_a),len(images_b))
         if options.error_on_non_matching_lists:
             raise ValueError(s)
         else:

{megadetector-5.0.7 → megadetector-5.0.8}/api/batch_processing/postprocessing/convert_output_format.py

@@ -4,8 +4,8 @@
 #
 # Converts between file formats output by our batch processing API.  Currently
 # supports json <--> csv conversion, but this should be the landing place for any
-# conversion - including between future .json versions - that we support in the 
-# future.
+# conversion - including between hypothetical alternative .json versions - that we support 
+# in the future.
 #
 ########
 
@@ -30,10 +30,13 @@ CONF_DIGITS = 3
 #%% Conversion functions
 
 def convert_json_to_csv(input_path,output_path=None,min_confidence=None,
-                        omit_bounding_boxes=False,output_encoding=None):
+                        omit_bounding_boxes=False,output_encoding=None,
+                        overwrite=True):
     """
     Convert .json to .csv
     
+    If output_path is None, will convert x.json to x.csv.
+    
     TODO: this function should obviously be using Pandas or some other sensible structured
     representation of tabular data.  Even a list of dicts.  This implementation is quite
     brittle and depends on adding fields to every row in exactly the right order.
@@ -42,6 +45,10 @@ def convert_json_to_csv(input_path,output_path=None,min_confidence=None,
     if output_path is None:
         output_path = os.path.splitext(input_path)[0]+'.csv'
         
+    if os.path.isfile(output_path) and (not overwrite):
+        print('File {} exists, skipping json --> csv conversion'.format(output_path))
+        return
+    
     print('Loading json results from {}...'.format(input_path))
     json_output = json.load(open(input_path))
 
@@ -73,7 +80,7 @@ def convert_json_to_csv(input_path,output_path=None,min_confidence=None,
 
         n_classification_categories = len(classification_category_ids)
     
-    # There are several fields for which we add columns, other random bespoke fields
+    # There are several .json fields for which we add .csv columns; other random bespoke fields
     # will be ignored.
     optional_fields = ['width','height','datetime','exif_metadata']
     optional_fields_present = set()
@@ -104,7 +111,7 @@ def convert_json_to_csv(input_path,output_path=None,min_confidence=None,
         if 'failure' in im and im['failure'] is not None:
             row = [image_id, 'failure', im['failure']]
             rows.append(row)
-            print('Skipping failed image {} ({})'.format(im['file'],im['failure']))
+            # print('Skipping failed image {} ({})'.format(im['file'],im['failure']))
             continue
 
         max_conf = ct_utils.get_max_conf(im)
@@ -193,12 +200,21 @@ def convert_json_to_csv(input_path,output_path=None,min_confidence=None,
         writer.writerow(header)
         writer.writerows(rows)
 
+# ...def convert_json_to_csv(...)
+
     
-def convert_csv_to_json(input_path,output_path=None):
+def convert_csv_to_json(input_path,output_path=None,overwrite=True):
+    """
+    Convert .csv to .json.  If output_path is None, will convert x.csv to x.json.
+    """
     
     if output_path is None:
         output_path = os.path.splitext(input_path)[0]+'.json'
         
+    if os.path.isfile(output_path) and (not overwrite):
+        print('File {} exists, skipping csv --> json conversion'.format(output_path))
+        return
+            
     # Format spec:
     #
     # https://github.com/agentmorris/MegaDetector/tree/master/api/batch_processing
@@ -259,6 +275,8 @@ def convert_csv_to_json(input_path,output_path=None):
     json_out['images'] = images
     
     json.dump(json_out,open(output_path,'w'),indent=1)
+    
+# ...def convert_csv_to_json(...)
 
 
 #%% Interactive driver

{megadetector-5.0.7 → megadetector-5.0.8}/api/batch_processing/postprocessing/load_api_results.py

@@ -64,11 +64,9 @@ def load_api_results(api_output_path: str, normalize_paths: bool = True,
         if k != 'images':
             other_fields[k] = v
 
-    # Normalize paths to simplify comparisons later
     if normalize_paths:
         for image in detection_results['images']:
-            image['file'] = os.path.normpath(image['file'])
-            # image['file'] = image['file'].replace('\\','/')
+            image['file'] = os.path.normpath(image['file'])            
 
     if force_forward_slashes:
         for image in detection_results['images']: