brunoasm/Tetraopes_on_flowers

Tetraopes Beetle Flower Detection Model

Model Description

This model detects whether photographs of Tetraopes beetles (Cerambycidae: Tetraopini) contain milkweed flowers or fruits (Asclepias spp.). It is designed to facilitate large-scale analysis of iNaturalist observations to identify beetle-plant associations for ecological and co-phylogenetic studies.

Model Architecture: Vision Transformer Large (ViT-L/14) with CLIP pre-training

Base Model: vit_large_patch14_clip_336.openai_ft_in12k_in1k

• Pre-trained by OpenAI on 400M image-text pairs (CLIP)
• Fine-tuned on ImageNet-12k and ImageNet-1k
• Input resolution: 336×336 pixels

Task: Binary image classification (flower present: yes/no)

Training Framework: FastAI with PyTorch backend

Last Updated: 2025-11-07

Intended Use

Primary Use Case

This model is designed specifically for:

• Identifying Tetraopes beetle observations on iNaturalist that show beetles on milkweed flowers/fruits
• Supporting ecological studies of beetle-plant associations
• Enabling large-scale analysis of host plant usage patterns
• Filtering iNaturalist photos for downstream analysis (e.g., host plant identification)

Intended Users

• Ecologists studying plant-insect interactions
• Entomologists researching Tetraopes biology
• Researchers conducting co-phylogenetic analyses
• Biodiversity scientists working with iNaturalist data

Out-of-Scope Use

This model is NOT intended for:

• General flower detection in arbitrary contexts
• Detection of beetles other than Tetraopes
• High-stakes decision making
• Any application where misclassification could cause harm

Limitations

1. Taxonomic Scope: Trained specifically on Tetraopes beetles; may not generalize to other beetle genera
2. Plant Scope: Optimized for milkweed (Asclepias) flowers/fruits; performance on other plants not evaluated
3. Image Quality: Performance depends on image quality typical of iNaturalist photos
4. Confidence Calibration: Based on validation analysis, only predictions with >80% confidence are recommended for use
5. Small Training Set: Trained on only 121 manually labeled images; may not capture all variation
6. Class Imbalance: Training data is approximately balanced, but real-world distribution is unknown

Training Data

Dataset Summary

• Source: Manually labeled photos from iNaturalist observations
• Total Images: 119
  • With flowers (yes): 63
  • Without flowers (no): 56
• Train/Val Split: 80/20 stratified by class (seed=42)
  • Training: ~95 images
  • Validation: ~24 images
• Image Source: iNaturalist community observations

Training Images

All training and validation images are from iNaturalist observations and remain under their original licenses. Links to all training/validation photos are provided below.

Notes:

• For observations with multiple photos, the first photo was used for training/validation.
• Original quality images (full resolution) were downloaded from iNaturalist and then resized to 336×336 pixels during training.

Training/Validation Images WITH Flowers (n=63)

Observation ID	Photo ID	Taxon	Location	Date	Photo URL	Observation URL
294117657	529366891	Tetraopes annulatus	Milk River, AB T0K 1M0, Canada	2025-06-29	Photo	Observation
28949859	45154147	Tetraopes femoratus	Wayne, Utah, United States	2019-07-12	Photo	Observation
30268404	47278404	Tetraopes femoratus	Guadalupe County, NM, USA	2019-07-26	Photo	Observation
306632555	552994059	Tetraopes	Colorado, US	2025-07-31	Photo	Observation
129351639	219808833	Tetraopes femoratus	Las Vegas, NM, US	2022-08-03	Photo	Observation
87493186	144223919	Tetraopes quinquemaculatus	Illinois, US	2021-07-17	Photo	Observation
310905379	561176590	Tetraopes femoratus	Colfax, WA, US	2025-08-30	Photo	Observation
169683166	294212111	Tetraopes quinquemaculatus	Rome, WI, USA	2023-06-23	Photo	Observation
290477669	522556815	Tetraopes femoratus	FBP Native Plant Nursery, Eugene, OR 97405, United...	2025-06-12	Photo	Observation
120970674	204659875	Tetraopes discoideus	Fort Worth Botanic Garden, Fort Worth, TX, US	2022-06-09	Photo	Observation
61981004	99245520	Tetraopes tetrophthalmus	Sioux County, NE, USA	2018-07-05	Photo	Observation
168435516	291907451	Tetraopes tetrophthalmus	Dubuque, IA, USA	2023-06-19	Photo	Observation
159767840	276055398	Tetraopes texanus	Niederwald, TX 78640, USA	2023-05-04	Photo	Observation
311178208	561712088	Tetraopes	spook drive	2025-09-02	Photo	Observation
244997587	437112237	Tetraopes thermophilus	County Road 116, Cat Spring, TX, US	2024-09-30	Photo	Observation
10235131	14150871	Tetraopes discoideus	Payne County, OK, USA	2011-05-21	Photo	Observation
258040781	462909370	Tetraopes femoratus	Santa Cruz County, AZ, USA	2019-08-07	Photo	Observation
84877387	139558762	Tetraopes annulatus	Miller Rd, Los Lunas, NM, US	2021-06-28	Photo	Observation
171115142	296888508	Tetraopes annulatus	Minnesota, US	2023-07-04	Photo	Observation
317292226	573326937	Tetraopes tetrophthalmus	Westerville, OH, USA	2023-07-07	Photo	Observation
311617229	562548352	Tetraopes tetrophthalmus	Voss Pkwy, Middleton, WI, US	2025-07-31	Photo	Observation
315730059	570377571	Tetraopes tetrophthalmus	Markham, ON, Canada	2025-06-27	Photo	Observation
9234594	12498299	Tetraopes femoratus	Yécora, Son., Mexico	2014-08-14	Photo	Observation
219086832	387753490	Tetraopes melanurus	Orange County, US-FL, US	2024-05-27	Photo	Observation
317648966	574011273	Tetraopes	Division No. 1, CA-AB, CA	2025-06-29	Photo	Observation
225241442	399325194	Tetraopes quinquemaculatus	Lake Sherwood, WI 54457, USA	2024-06-24	Photo	Observation
41561579	65937223	Tetraopes thermophilus	Sandoval, TX, USA	2020-04-06	Photo	Observation
124172311	210439879	Tetraopes annulatus	164th St S, Glyndon, MN, US	2022-06-30	Photo	Observation
306388471	552528305	Tetraopes femoratus	Vernon, BC V1T 9L7, Canada	2025-08-14	Photo	Observation
294317775	529747990	Tetraopes melanurus	Restricted Access: Camp Edwards, Sandwich, MA, US	2025-06-30	Photo	Observation
173702174	301683822	Tetraopes melanurus	Wright Rd, Federalsburg, MD, US	2023-07-15	Photo	Observation
238889165	425371964	Tetraopes femoratus	Garfield County, UT, USA	2024-07-29	Photo	Observation
278530285	500121798	Tetraopes melanurus	Florida, US	2025-04-29	Photo	Observation
315720911	570373487	Tetraopes tetrophthalmus	Swannanoa, NC 28778, USA	2025-06-12	Photo	Observation
86641310	152048388	Tetraopes femoratus	Brighton Blvd, Denver, CO, US	2021-07-11	Photo	Observation
291618096	524692846	Tetraopes melanurus	Manchester Road and Raefordvass Rd, Aberdeen, NC, ...	2025-06-20	Photo	Observation
297367440	537877641	Tetraopes annulatus	Denver Botanic Gardens, Denver, CO, US	2025-07-12	Photo	Observation
293970457	529095525	Tetraopes texanus	Bandera County, TX, USA	2025-06-29	Photo	Observation
12981500	18877797	Tetraopes quinquemaculatus	Vernon Parish, LA, USA	2003-07-23	Photo	Observation
177126949	308025393	Tetraopes annulatus	Coral Pink Sand Dunes State Park, Kanab, UT, US	2023-07-09	Photo	Observation
316299132	571461156	Tetraopes thermophilus	Clifton, TX 76634, USA	2025-09-23	Photo	Observation
238251109	424136788	Tetraopes femoratus	Garvin County, OK, USA	2024-08-17	Photo	Observation
276769865	496993364	Tetraopes texanus	Fort Worth Nature Center & Refuge	2025-04-26	Photo	Observation
223337419	395713177	Tetraopes tetrophthalmus	L St, Ord, NE, US	2024-06-16	Photo	Observation
171268373	297172942	Tetraopes femoratus	Uinta-Wasatch-Cache National Forest, Farmington, U...	2023-07-04	Photo	Observation
296157175	533236106	Tetraopes tetrophthalmus	Lincoln Township, KS 66901, USA	2025-07-06	Photo	Observation
169426142	293730150	Tetraopes femoratus	E Eighth Ave, Salt Lake City, UT, US	2023-06-25	Photo	Observation
51041245	81074892	Tetraopes quinquemaculatus	Michigan, US	2020-06-26	Photo	Observation
53796540	85575805	Tetraopes femoratus	Grand Staircase - Escalante National Monument, Bou...	2020-07-17	Photo	Observation
126561450	214752198	Tetraopes annulatus	Fort Sumner, NM 88119, USA	2022-07-15	Photo	Observation
237993656	423636017	Tetraopes discoideus	Brewster County, TX, USA	2024-08-25	Photo	Observation
314082824	567259293	Tetraopes tetrophthalmus	N Bell Ave, Chicago, IL, US	2025-07-02	Photo	Observation
168746922	292486304	Tetraopes texanus	Kerr County, TX, USA	2020-06-29	Photo	Observation
233029688	414084830	Tetraopes ineditus	autlan de navarro jalisco	2024-07-31	Photo	Observation
102976398	172249054	Tetraopes femoratus	Peñón Blanco, Dgo., México	2020-07-18	Photo	Observation
124922174	211785052	Tetraopes melanurus	Lake County, FL, USA	2022-07-02	Photo	Observation
313702927	566526797	Tetraopes tetrophthalmus	Nittany View Cir, State College, PA, US	2025-08-15	Photo	Observation
50103733	79554627	Tetraopes sublaevis	29447, 29759 Old Julian Hwy, Ramona, CA 92065, USA	2020-06-18	Photo	Observation
230635772	409538273	Tetraopes batesi	69916 Oax., México	2024-07-20	Photo	Observation
112151787	189418289	Tetraopes annulatus	Dawes County, NE, USA	2015-07-19	Photo	Observation
48489985	1961612	Tetraopes pilosus	Major, Oklahoma, United States	2015-06-04	Photo	Observation
309623123	558738746	Tetraopes texanus	Texas, US	2023-06-06	Photo	Observation
311287532	561921793	Tetraopes tetrophthalmus	Hodges Township, MN, USA	2025-07-14	Photo	Observation

Training/Validation Images WITHOUT Flowers (n=56)

Observation ID	Photo ID	Taxon	Location	Date	Photo URL	Observation URL
310403056	560219856	Tetraopes	Puebla, Pue., México	2025-08-10	Photo	Observation
316781181	572363141	Tetraopes femoratus	Longmont, CO, USA	2025-09-26	Photo	Observation
94075801	156011833	Tetraopes linsleyi	Belton vicinity, Bell County, Texas, USA	2000-05-29	Photo	Observation
168833060	292645197	Tetraopes femoratus	Stanislaus National Forest	2023-06-21	Photo	Observation
307165291	554003735	Tetraopes	34670 Dgo., México	2025-08-17	Photo	Observation
309480058	558469519	Tetraopes discoideus	34670 Dgo., México	2025-08-26	Photo	Observation
312807182	564817043	Tetraopes tetrophthalmus	Fort Washington, MD 20744, USA	2025-09-06	Photo	Observation
317826616	574343081	Tetraopes annulatus	Cheyenne County, CO, USA	2025-06-17	Photo	Observation
178799501	311190794	Tetraopes discoideus	Localización: 14.712488 -90.633943	2023-08-06	Photo	Observation
9364818	12714648	Tetraopes annulatus	San Juan County, UT, USA	2013-06-19	Photo	Observation
33991467	53446241	Tetraopes varicornis	Tolcayuca, Hgo., México	2019-06-27	Photo	Observation
302228753	544665415	Tetraopes discoideus	Parker Rd, Ruidoso Downs, NM, US	2025-07-29	Photo	Observation
314002462	567102203	Tetraopes femoratus	Plains Conservation Center City of Aurora Open Spa...	2025-09-14	Photo	Observation
312933708	565060621	Tetraopes thermophilus	Valley Mills, TX 76689, USA	2025-09-10	Photo	Observation
9935529	13635571	Tetraopes discoideus	Sombrerete, Zacatecas, Mexico	2012-07-24	Photo	Observation
310402358	560200381	Tetraopes discoideus	Santa Cruz County, AZ, USA	2025-08-20	Photo	Observation
309604310	558699556	Tetraopes tetrophthalmus	Rehoboth, MA 02769, USA	2025-05-25	Photo	Observation
309648179	558789581	Tetraopes femoratus	Colorado, US	2025-08-27	Photo	Observation
92643259	153427832	Tetraopes	Santa Lucía Monteverde, Oax., México	2021-08-20	Photo	Observation
313990753	567077940	Tetraopes skillmani	Pima County, US-AZ, US	2025-08-27	Photo	Observation
309342036	558195834	Tetraopes	Downtown, Colorado Springs, CO, USA	2025-08-25	Photo	Observation
14464908	21527043	Tetraopes femoratus	Jerez de García Salinas, Zacatecas, Mexico	2018-07-17	Photo	Observation
125330817	212523233	Tetraopes quinquemaculatus	Jackson County, WI, USA	2022-06-24	Photo	Observation
316660376	572148708	Tetraopes femoratus	Canyonlands National Park, Monticello, UT, US	2025-09-24	Photo	Observation
84122631	138228196	Tetraopes batesi	Fraccionamiento Vista Real, Corregidora, Qro., Méx...	2021-06-22	Photo	Observation
8010205	10600552	Tetraopes femoratus	73460, Tishomingo, OK, US	2017-09-20	Photo	Observation
306599531	552916729	Tetraopes tetrophthalmus	M36/Kelly SE fen (Putnum Twp)	2025-08-15	Photo	Observation
307108230	553892043	Tetraopes tetrophthalmus	Venetian Village, IL 60046, USA	2025-08-17	Photo	Observation
299340155	539282063	Tetraopes	Santa María del Oro, Nay., México	2025-07-19	Photo	Observation
309862975	559199780	Tetraopes tetrophthalmus	Spring St, Alnwick/Haldimand, ON, CA	2022-08-16	Photo	Observation
304750565	549415703	Tetraopes femoratus	W 73rd Ave, Denver, CO, US	2025-08-08	Photo	Observation
304582396	549096605	Tetraopes tetrophthalmus	University of Minnesota, Minneapolis, MN, US	2025-08-07	Photo	Observation
320175989	578851620	Tetraopes discoideus	N 25th St, McAllen, TX, US	2025-10-04	Photo	Observation
316837863	572470432	Tetraopes tetrophthalmus	Boone, NC, US	2025-07-10	Photo	Observation
311563648	562443212	Tetraopes annulatus	Sweetwater County, US-WY, US	2025-09-04	Photo	Observation
14062739	20802869	Tetraopes texanus	Austin, TX, USA	2018-06-24	Photo	Observation
312382271	563719961	Tetraopes discoideus	Adolfo López Mateos, Adolfo Lopez Mateos, Tixtla d...	2025-08-31	Photo	Observation
304399717	548754239	Tetraopes tetrophthalmus	Merrill, WI, US	2025-08-06	Photo	Observation
178100161	309850840	Tetraopes	Acámbaro, Gto., México	2023-08-12	Photo	Observation
317311680	573363691	Tetraopes tetrophthalmus	Lacewood Cres, Brampton, ON, CA	2025-09-26	Photo	Observation
316641597	572110969	Tetraopes tetrophthalmus	Wixom, MI 48393, USA	2025-06-30	Photo	Observation
304300107	548551342	Tetraopes femoratus	N Chaz Ct, Salt Lake City, UT, US	2025-08-06	Photo	Observation
313129616	565435963	Tetraopes tetrophthalmus	Cornell University, Ithaca, NY, US	2025-09-11	Photo	Observation
136616795	233190550	Tetraopes femoratus	Norman, OK 73072, USA	2022-09-26	Photo	Observation
306838837	553381028	Tetraopes femoratus	Foxfield, CO 80016, USA	2025-08-16	Photo	Observation
312382275	563719999	Tetraopes discoideus	Adolfo López Mateos, Adolfo Lopez Mateos, Tixtla d...	2025-08-31	Photo	Observation
124280729	210636366	Tetraopes discoideus	Santa Fe County, US-NM, US	2022-07-01	Photo	Observation
320024424	578552754	Tetraopes femoratus	Okanagan-Similkameen, BC, Canada	2025-07-12	Photo	Observation
310275974	559969471	Tetraopes annulatus	Cherry Hills Village, CO 80121, USA	2025-08-30	Photo	Observation
320208571	578905449	Tetraopes femoratus	Okanagan-Similkameen, BC, Canada	2025-07-13	Photo	Observation
127797733	217001570	Tetraopes umbonatus	Zumpango, Méx., México	2022-07-23	Photo	Observation
304359205	548670157	Tetraopes tetrophthalmus	Iles de Boucherville, QC, Canada	2025-08-05	Photo	Observation
310671360	560730922	Tetraopes	Evanston, IL, US	2025-08-13	Photo	Observation
314627623	568278754	Tetraopes tetrophthalmus	Tawes Dr, Elkton, MD, US	2025-09-17	Photo	Observation
310951667	561267245	Tetraopes femoratus	Garfield County, WA, USA	2025-08-30	Photo	Observation
1557299	1927889	Tetraopes umbonatus	Joquicingo, MX, MX	2015-05-28	Photo	Observation

Training Procedure

Hyperparameters

• Model: Vision Transformer Large (ViT-L/14)

  • Architecture: vit_large_patch14_clip_336.openai_ft_in12k_in1k
  • Patch size: 14×14
  • Input resolution: 336×336 pixels

• Training Strategy: Transfer learning with fine-tuning

  • Frozen epochs: 3 (train only classification head)
  • Fine-tuning epochs: 3 (train all layers)
  • Total epochs: 6

• Optimization:

  • Optimizer: AdamW (fastai default)
  • Learning rate: Determined via lr_find() - valley of loss curve
  • Learning rate schedule: One-cycle policy
  • Batch size: 8 (per GPU)
  • Weight decay: 0.01 (fastai default)

• Hardware:

  • 2× NVIDIA RTX A5000 GPUs (24GB each)
  • DataParallel training for faster convergence

• Data Augmentation:

  • Geometric:
    • Random rotation: ±10°
    • Random zoom: 1.0-1.3×
    • Random scale: 0.8-1.0×
    • Random warp: ±0.2
    • Horizontal flip: 50%
    • Vertical flip: 50%
  • Photometric:
    • Random lighting: ±0.4
  • Advanced:
    • MixUp augmentation (α=0.4) - blends image pairs during training
  • Normalization: ImageNet statistics (mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])

• Class Balancing:

  • Weighted sampling during training
  • Sample weights calculated using normalized inverse frequency
  • Formula: weight = total_samples / (num_classes × class_count)

Training Procedure Details

1. Data Preparation:

   • Original quality images downloaded from iNaturalist (full resolution, typically ~2048px)
   • Images resized to 336×336 using squish method (no cropping)
   • Applied augmentation transforms
   • Normalized with ImageNet statistics

2. Transfer Learning:

   • Phase 1 (3 epochs): Froze all layers except classification head
   • Phase 2 (3 epochs): Unfroze all layers for end-to-end fine-tuning
   • Used MixUp augmentation throughout training

3. Validation:

   • Evaluated on held-out 20% validation set
   • No augmentation applied during validation
   • Metrics: accuracy, error rate

Evaluation

Validation Results

• Validation Accuracy: 100% (25/25 images correct)
• Validation Error Rate: 0%

Confusion Matrix (Validation Set):

          Predicted No  Predicted Yes
Actual No           12              0
Actual Yes           0             13

Note: Perfect validation accuracy on a small dataset (25 images) suggests potential overfitting. Real-world performance is expected to be lower. Based on visual inspection of large-scale predictions, confidence thresholding (>80%) is recommended.

Large-Scale Prediction Results

The model was applied to 75,428 iNaturalist photos from 50,839 Tetraopes observations:

• Predictions:

  • Flower detected (yes): 31,419 (41.7%)
  • No flower (no): 44,009 (58.3%)
  • Mean confidence: 84.0%

• High-Confidence Results (yes prediction with >80% confidence):

  • Photos: 21,307 (28.2%)
  • Unique observations: 15,916
  • Recommendation: Only use predictions with >80% confidence based on manual validation

Performance by Taxon

Taxon	Observations	Total Photos	High-Conf Photos	High-Conf Obs	% High-Conf
Tetraopes tetrophthalmus	42,000.0	60,592.0	18,076	13,663.0	32.5%
Tetraopes femoratus	4,581.0	7,753.0	1,672	1,148.0	25.1%
Tetraopes	1,973.0	2,935.0	770	581.0	29.4%
Tetraopes melanurus	708.0	1,059.0	118	94.0	13.3%
Tetraopes texanus	485.0	912.0	157	106.0	21.9%
Tetraopes annulatus	400.0	691.0	174	124.0	31.0%
Tetraopes basalis	268.0	541.0	189	112.0	41.8%
Tetraopes discoideus	153.0	269.0	41	31.0	20.3%
Tetraopes thermophilus	56.0	162.0	45	20.0	35.7%
Tetraopes quinquemaculatus	54.0	84.0	23	13.0	24.1%
Tetraopes batesi	34.0	90.0	1	1.0	2.9%
Tetraopes pilosus	30.0	59.0	22	12.0	40.0%
Tetraopes sublaevis	23.0	73.0	15	7.0	30.4%
Tetraopes umbonatus	15.0	38.0	0	nan	nan%
Tetraopes mandibularis	15.0	89.0	1	1.0	6.7%

Showing top 15 of 25 taxa

Notes:

• "High-Conf Photos" = predictions with >80% confidence showing flowers
• "High-Conf Obs" = observations with at least one high-confidence flower photo
• Some taxa have limited observations; interpret results with caution

How to Use

Requirements

pip install fastai timm torch torchvision pandas

Loading the Model

from fastai.vision.all import *
import torch

# Download model from Hugging Face
model_path = 'tetraopes_flower_vit_large_patch14_clip_336.openai_ft_in12k_in1k.pth'

# Create a dummy DataLoader with the same structure as training
# (FastAI requires this to load the model)
from fastai.data.all import DataBlock, ColSplitter, ColReader
import pandas as pd

# Create minimal dataframe for loading
dummy_df = pd.DataFrame({'path': ['dummy.jpg'], 'label': ['yes'], 'is_valid': [False]})

dbl = DataBlock(
    blocks=(ImageBlock, CategoryBlock),
    get_x=ColReader('path'),
    get_y=ColReader('label'),
    splitter=ColSplitter('is_valid'),
    item_tfms=Resize(336, method='squish'),
    batch_tfms=Normalize.from_stats(*imagenet_stats)
)

dls = dbl.dataloaders(dummy_df, bs=1)

# Create learner and load weights
learn = vision_learner(
    dls,
    'vit_large_patch14_clip_336.openai_ft_in12k_in1k',
    metrics=[error_rate, accuracy]
)
learn = learn.to_fp16()  # Use mixed precision
learn.load(model_path.replace('.pth', ''))  # Remove .pth extension

print("Model loaded successfully!")

Making Predictions

# Single image prediction
img_path = 'path/to/tetraopes_photo.jpg'
pred_class, pred_idx, probs = learn.predict(img_path)

print(f"Prediction: {pred_class}")
print(f"Confidence: {probs[pred_idx]:.2%}")
print(f"P(no flower): {probs[0]:.2%}")
print(f"P(with flower): {probs[1]:.2%}")

# Recommended: Filter by confidence threshold
confidence = probs[pred_idx]
if pred_class == 'yes' and confidence > 0.80:
    print("High-confidence flower detection!")
else:
    print("Low confidence or no flower detected")

Batch Predictions

from pathlib import Path

# Get all images
image_files = list(Path('images/').glob('*.jpg'))

# Create test DataLoader
test_dl = learn.dls.test_dl(image_files, bs=16)

# Get predictions
preds, _ = learn.get_preds(dl=test_dl)

# Process results
results = []
for idx, img_path in enumerate(image_files):
    pred_idx = preds[idx].argmax().item()
    pred_class = learn.dls.vocab[pred_idx]
    confidence = float(preds[idx][pred_idx])
    prob_no = float(preds[idx][0])
    prob_yes = float(preds[idx][1])

    results.append({
        'image': img_path.name,
        'prediction': pred_class,
        'confidence': confidence,
        'prob_no': prob_no,
        'prob_yes': prob_yes,
        'high_confidence_flower': pred_class == 'yes' and confidence > 0.80
    })

results_df = pd.DataFrame(results)
print(results_df)

Model Card Authors

Bruno A. S. de Medeiros

Citation

If you use this model in your research, please cite:

@misc{tetraopes_flower_detector_2025,
  author = {de Medeiros, Bruno A. S.},
  title = {Tetraopes Beetle Flower Detection Model},
  year = {2025},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/brunoasm/Tetraopes_on_flowers}},
  note = {Vision Transformer model for detecting Tetraopes beetles on milkweed flowers}
}

Related Repository: The full code for training this model and conducting co-phylogenetic analyses is available at: https://github.com/de-Medeiros-insect-lab/Tetraopes_cophylogeny_analyses

Additional Information

Framework Versions

• Python: 3.13.9
• PyTorch: 2.6.0
• FastAI: 2.8.5
• timm: 1.0.21

Model Size

• Parameters: ~304M (ViT-Large)
• Model file size: ~3.4 GB

Computational Requirements

• Training: 2× NVIDIA RTX A5000 (24GB) - ~30 minutes total
• Inference:
  • GPU recommended (any CUDA-capable GPU with 8GB+ VRAM)
  • CPU inference possible but slow (~1-2 seconds per image)
  • FP16 recommended for faster inference

License

This model is released under the Apache 2.0 license.

Important: The training images remain under their original iNaturalist licenses (typically CC-BY, CC-BY-NC, or CC0). Links to all training images with their original licenses are provided in the "Training Images" section above.

Contact

For questions or issues, please open an issue on the GitHub repository: https://github.com/de-Medeiros-insect-lab/Tetraopes_cophylogeny_analyses

Acknowledgments

• Training data from the iNaturalist community
• Pre-trained weights from OpenAI (CLIP) and timm library
• Training framework: FastAI