Min
Max
Min
Max
Min
Max
Min
Max
Top Vegetable Computer Vision Models
The models below have been fine-tuned for various vegetable detection tasks. You can try out each model in your browser, or test an edge deployment solution (i.e. to an NVIDIA Jetson). You can use the datasets associated with the models below as a starting point for building your own vegetable detection model.
At the bottom of this page, we have guides on how to count vegetables in images and videos.
6340 images3 models
0--s--unknown1--s--Qingjiang Cuisine100--m--Fried Cod101--s--Sand Tea Mustard Slices102--s--Flax103--s--Xiuzhen Mushroom Fried Chicken104--m--Garlic Grilled Pork Chop105--s--Sauce106--s--Homemade Tofu107--m--Fried Dragon Fish109--s--Corn11--s--Amaranth110--s--Sesame Belt Root111--s--Big Melon Fungus Slices112--m--Frying Muscle112--m--Turou115--s--Emerald Steamed Egg116--s--Shrimp Tofu117--s--Kelp Sprouting Enoki Mushroom118--s--Sauce
6451 images1 model
4800 images1 model
1412 images1 model
9472 images1 model
869 images1 model
cardboard boxplastic cupALDIPlastic BagAfiaAfia Plastic BottleAlliance Lysol Plastic JerrycanAmigos Plastic BagAmplico Dawa Plastic BottleAquaAquaclearAquafrostAriel Plastic SacheAssured Plastic ContainerAzam Energy DrinkAzam Energy Plastic BottleBazuu Energy DrinkBazuu Energy Plastic BottleBella Plastic BagBlueband Plastic sacheBrava
3010 images1 model
aluminum - Non_biodegradable-Recyclablecardboard - Non_Biodegradable-Recyclableegg shell - Biodegradablefacemask - Non_Biodegradablefood wrapper - Non_Biodegradablefruit peels - Biodegradableglass bottle - Non_Biodegradableleft-over food - Biodegradablepaper - Biodegradable-Recyclablepet bottle - Non_Biodegradable-Recyclableplastic bag - Non_Biodegradableplastic bottle - Non_Biodegradableplastic container - Non_Biodegradableplastic sachet - Non_Biodegradableplastic straw - Non_Biodegradablestyrofoam containers - Non_Biodegradabletreeleaves - Biodegradableuht carton - Non_Biodegradable-Recyclablevegetable peels - Biodegradable
3010 images1 model
aluminum - Non_biodegradable-Recyclablecardboard - Non_Biodegradable-Recyclableegg shell - Biodegradablefacemask - Non_Biodegradablefood wrapper - Non_Biodegradablefruit peels - Biodegradableglass bottle - Non_Biodegradableleft-over food - Biodegradablepaper - Biodegradable-Recyclablepet bottle - Non_Biodegradable-Recyclableplastic bag - Non_Biodegradableplastic bottle - Non_Biodegradableplastic container - Non_Biodegradableplastic sachet - Non_Biodegradableplastic straw - Non_Biodegradablestyrofoam containers - Non_Biodegradabletreeleaves - Biodegradableuht carton - Non_Biodegradable-Recyclablevegetable peels - Biodegradable
147 images1 model
Ajab Homebaking FloorAlways PadsAmara Coco ButterArial Washing PowerAvenda Premium Vegetable OilBarakiBiryani RiceBlack Hair ShampooBluebandBucketCerelacChapa Mandashi Baking PowerCloseup ToothpasetCoca ColaColgate ToothpasteCrunchy GingerCurry PowderDaawat SpaghettiDairyBest Whole MilkDairyTop MIlk
783 images1 model
cardboard boxplastic cupALDIPlastic BagAfia Plastic BottleAlliance Lysol Plastic JerrycanAmigos Plastic BagAmplico Dawa Plastic BottleAriel Plastic SacheAssured Plastic ContainerAzam Energy Plastic BottleBazuu Energy Plastic BottleBella Plastic BagBlueband Plastic sacheBrookSide Lala Plastic BottleButterfly Plastic BagCablesCardboard CartonCeramic mugCeramic mugsChandaranaPlastic Shopping Bag
Guide: How to Count Vegetables with Computer Vision
With a model hosted on Roboflow like the ones above and the open source supervision Python package, you can count vegetables in your images and videos.
The following code snippet counts the number of vegetables present in an image.
To use the snippet below, you will need to run pip install roboflow supervision. Replace the project name and model name with any model trained on Universe, such as those listed above.
import supervision as sv
import roboflow
roboflow.login()
rf = roboflow.Roboflow()
# replace with the vegetable project you choose above
project = rf.workspace("ai-nutrient-tracker").project("object-detection-ez3ce")
vegetable_model = project.version(1).model
results = vegetable_model.predict("vegetable.jpg").json()
vegetables = sv.Detections.from_roboflow(results)
# print number of vegetables
print(len(vegetables))Guide: How to Count Vegetables in a Zone
With a bit more code, you can count the number of vegetable present in a specific zone of your image or video.
The following code snippet counts the number of vegetable present in each frame in a video.
To use the snippet below, you will need to run pip install roboflow supervision. Replace the project name and model name with any model trained on Universe, such as those listed above.
Read our blog post on counting objects in a zone
import numpy as np
import supervision as sv
import roboflow
SOURCE_VIDEO_PATH = "vegetable.mp4"
TARGET_VIDEO_PATH = "vegetable_out.mp4"
# use https://roboflow.github.io/polygonzone/ to get the points for your shape
polygon = np.array([
# draw 50x50 box in top left corner
[0, 0],
[50, 0],
[50, 50],
[0, 50]
])
roboflow.login()
rf = roboflow.Roboflow()
# replace with the vegetable project you choose above
project = rf.workspace("ai-nutrient-tracker").project("object-detection-ez3ce")
vegetable_model = project.version(1).model
# create BYTETracker instance
vegetable_tracker = sv.ByteTrack(track_thresh=0.25, track_buffer=30, match_thresh=0.8, frame_rate=30)
# create VideoInfo instance
video_info = sv.VideoInfo.from_video_path(SOURCE_VIDEO_PATH)
# create frame generator
generator = sv.get_video_frames_generator(SOURCE_VIDEO_PATH)
# create PolygonZone instance
zone = sv.PolygonZone(polygon=polygon, frame_resolution_wh=(video_info.width, video_info.height))
# create box annotator
box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2)
colors = sv.ColorPalette.default()
# create instance of BoxAnnotator
zone_annotator = sv.PolygonZoneAnnotator(thickness=4, text_thickness=4, text_scale=2, zone=zone, color=colors.colors[0])
# define call back function to be used in video processing
def callback(frame: np.ndarray, index:int) -> np.ndarray:
# model prediction on single frame and conversion to supervision Detections
results = vegetable_model.predict(frame).json()
vegetables = sv.Detections.from_roboflow(results)
# show vegetable detections in real time
print(vegetables)
# tracking vegetable detections
vegetables = vegetable_tracker.update_with_detections(vegetables)
annotated_frame = box_annotator.annotate(scene=frame, detections=vegetables)
annotated_frame = zone_annotator.annotate(scene=annotated_frame)
# return frame with box and line annotated result
return annotated_frame
# process the whole video
sv.process_video(
source_path = SOURCE_VIDEO_PATH,
target_path = TARGET_VIDEO_PATH,
callback=callback
)Guide: How to Track Vegetables Crossing a Line
You can count how many vegetables have crossed a line using the supervision LineCounter method.
The following code snippet counts the number of vegetables that cross a line in a video.
To use the snippet below, you will need to run pip install roboflow supervision. Replace the project name and model name with any model trained on Universe, such as those listed above.
import numpy as np
import supervision as sv
import roboflow
SOURCE_VIDEO_PATH = "vegetable.mp4"
TARGET_VIDEO_PATH = "vegetable_out.mp4"
# use https://roboflow.github.io/polygonzone/ to get the points for your line
LINE_START = sv.Point(0, 300)
LINE_END = sv.Point(800, 300)
roboflow.login()
rf = roboflow.Roboflow()
# replace with the vegetable project you choose above
project = rf.workspace("ai-nutrient-tracker").project("object-detection-ez3ce")
vegetable_model = project.version(1).model
# create BYTETracker instance
vegetable_tracker = sv.ByteTrack(track_thresh=0.25, track_buffer=30, match_thresh=0.8, frame_rate=30)
# create VideoInfo instance
video_info = sv.VideoInfo.from_video_path(SOURCE_VIDEO_PATH)
# create frame generator
generator = sv.get_video_frames_generator(SOURCE_VIDEO_PATH)
# create LineZone instance, it is previously called LineCounter class
line_zone = sv.LineZone(start=LINE_START, end=LINE_END)
# create instance of BoxAnnotator
box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2)
# create instance of TraceAnnotator
trace_annotator = sv.TraceAnnotator(thickness=4, trace_length=50)
line_zone_annotator = sv.LineZoneAnnotator(thickness=4, text_thickness=4, text_scale=2)
# define call back function to be used in video processing
def callback(frame: np.ndarray, index:int) -> np.ndarray:
# model prediction on single frame and conversion to supervision Detections
results = vegetable_model.predict(frame).json()
vegetables = sv.Detections.from_roboflow(results)
# show vegetable detections in real time
print(vegetables)
# tracking vegetable detections
vegetables = vegetable_tracker.update_with_detections(vegetables)
annotated_frame = trace_annotator.annotate(
scene=frame.copy(),
detections=vegetables
)
annotated_frame=box_annotator.annotate(
scene=annotated_frame,
detections=vegetables
)
# update line counter
line_zone.trigger(vegetables)
# return frame with box and line annotated result
return line_zone_annotator.annotate(annotated_frame, line_counter=line_zone)
# process the whole video
sv.process_video(
source_path = SOURCE_VIDEO_PATH,
target_path = TARGET_VIDEO_PATH,
callback=callback
)