inference.py

# Check Pytorch installation
import torch, torchvision
print("torch version:",torch.__version__, "cuda:",torch.cuda.is_available())

# Check MMDetection installation
import mmdet
import os
import mmcv
import mmengine
from mmdet.apis import init_detector, inference_detector
from mmdet.utils import register_all_modules
from mmdet.registry import VISUALIZERS

from huggingface_hub import hf_hub_download
from huggingface_hub import snapshot_download
from time import time

classes = ['Beach',
 'Sea',
 'Wave',
 'Rock',
 'Breaking wave',
 'Reflection of the sea',
 'Foam',
 'Algae',
 'Vegetation',
 'Watermark',
 'Bird',
 'Ship',
 'Boat',
 'Car',
 'Kayak',
 "Shark's line",
 'Dock',
 'Dog',
 'Unidentifiable shade',
 'Bird shadow',
 'Boat shadow',
 'Kayal shade',
 'Surfer shadow',
 'Shark shadow',
 'Surfboard shadow',
 'Crocodile',
 'Sea cow',
 'Stingray',
 'Person',
 'ocean',
 'Surfer',
 'Surfer',
 'Fish',
 'Killer whale',
 'Whale',
 'Dolphin',
 'Miscellaneous',
 'Unidentifiable shark',
 'Carpet shark',
 'Dusty shark',
 'Blue shark',
 'Great white shark',
 'Copper shark',
 'Nurse shark',
 'Silky shark',
 'Leopard shark',
 'Shortfin mako shark',
 'Hammerhead shark',
 'Oceanic whitetip shark',
 'Blacktip shark',
 'Tiger shark',
 'Bull shark']*3

class_sizes = {'Beach': None,
               'Sea': None,
               'Wave': None,
               'Rock': None,
               'Breaking wave': None,
               'Reflection of the sea': None,
               'Foam': None,
               'Algae': None,
               'Vegetation': None,
               'Watermark': None,
               'Bird': {'feet':[1, 3], 'meter': [0.3, 0.9], 'kg': [0.5, 1.5], 'pounds': [1, 3]},
               'Ship': {'feet':[10, 100], 'meter': [3, 30], 'kg': [1000, 100000], 'pounds': [2200, 220000]},
               'Boat': {'feet':[10, 45], 'meter': [3, 15], 'kg': [750, 80000], 'pounds': [1500, 160000]},
               'Car': {'feet':[10, 20], 'meter': [3, 6], 'kg': [1000, 2000], 'pounds': [2200, 4400]},
               'Kayak': {'feet':[10, 20], 'meter': [3, 6], 'kg': [50, 300], 'pounds': [100, 600]},
               "Shark's line": None,
               'Dock': None,
               'Dog': {'feet':[1, 3], 'meter': [0.3, 0.9], 'kg': [10, 50], 'pounds': [20, 100]},
               'Unidentifiable shade': None,
               'Bird shadow': None,
               'Boat shadow': None,
               'Kayal shade': None,
               'Surfer shadow': None,
               'Shark shadow': None,
               'Surfboard shadow': None,
               'Crocodile': {'feet':[10, 20], 'meter': [3, 6], 'kg': [410, 1000], 'pounds': [900, 2200]},
               'Sea cow':  {'feet':[9,12], 'meter': [3, 4], 'kg': [400, 590], 'pounds': [900, 1300]},
               'Stingray': {'feet':[2, 7.5], 'meter': [0.6, 2.5], 'kg': [100, 300], 'pounds': [220, 770]},
               'Person': {'feet':[5, 7], 'meter': [1.5, 2.1], 'kg': [50, 150], 'pounds': [110, 300]},
               'Ocean': None,
               'Surfer': {'feet':[5, 7], 'meter': [1.5, 2.1], 'kg': [50, 150], 'pounds': [110, 300]},
               'Surfer': {'feet':[5, 7], 'meter': [1.5, 2.1], 'kg': [50, 150], 'pounds': [110, 300]},
               'Fish':  {'feet':[1, 3], 'meter': [0.3, 0.9], 'kg': [20, 150], 'pounds': [40, 300]},
               'Killer whale': {'feet':[10, 20], 'meter': [3, 6], 'kg': [3600, 5400], 'pounds': [8000, 12000]},
               'Whale': {'feet':[15, 30], 'meter': [4.5, 10], 'kg': [2500, 80000], 'pounds': [55000, 176000]},
               'Dolphin': {'feet':[6.6, 13.1], 'meter': [2, 4], 'kg': [150, 650], 'pounds': [330, 1430]},
               'Miscellaneous': None,
               'Unidentifiable shark': {'feet': [2, 15], 'meter': [0.6, 4.5], 'kg': [50, 1000], 'pounds': [110, 2200]},
               'Carpet shark': {'feet': [4, 10], 'meter': [1.25, 3], 'kg': [50, 1000], 'pounds': [110, 2200]}, # Prob incorrect
               'Dusty shark': {'feet': [9, 14], 'meter': [3, 4.25], 'kg': [160, 180], 'pounds': [350, 400]},
               'Blue shark': {'feet': [7.9, 12.5], 'meter': [2.4, 3], 'kg': [60, 120], 'pounds': [130, 260]}, 
               'Great white shark': {'feet': [13.1, 20], 'meter': [4, 6], 'kg': [680, 1800], 'pounds': [1500, 4000]},
               'Copper shark': {'feet': [7.2, 10.8], 'meter': [2.2, 3.3], 'kg': [130, 300], 'pounds': [290, 660]},
               'Nurse shark': {'feet': [7.9, 9.8], 'meter': [2.4, 3], 'kg': [90, 115], 'pounds': [200, 250]},
               'Silky shark': {'feet': [6.6, 8.2], 'meter': [2, 2.5], 'kg': [300, 380], 'pounds': [660, 840]},
               'Leopard shark': {'feet': [3.9, 4.9], 'meter': [1.2, 1.5], 'kg': [11, 20], 'pounds': [22, 44]},
               'Shortfin mako shark': {'feet': [10.5, 12], 'meter': [3.2, 3.6], 'kg': [60, 135], 'pounds': [130, 300]},
               'Hammerhead shark': {'feet': [4.9, 20], 'meter': [1.5, 6.1], 'kg': [230, 450], 'pounds': [500, 1000]},
               'Oceanic whitetip shark': {'feet': [5.9, 9.8], 'meter': [1.8, 3], 'kg': [36, 170], 'pounds': [80, 375]},
               'Blacktip shark': {'feet': [4.9, 6.6], 'meter': [1.5, 2], 'kg': [40, 100], 'pounds': [90, 220]},
               'Tiger shark': {'feet': [9.8, 18], 'meter': [3, 5.5], 'kg': [385, 635], 'pounds': [850, 1400]},
               'Bull shark': {'feet': [7.9, 11.2], 'meter': [2.4, 3.4], 'kg': [200, 315], 'pounds': [440, 690]},
}

class_sizes_lower = {k.lower(): v for k, v in class_sizes.items()}
   
classes_is_shark = [1 if 'shark' in x.lower() else 0 for x in classes]
classes_is_human = [1 if 'person' or 'surfer' in x.lower() else 0 for x in classes]
classes_is_unknown = [1 if 'unidentifiable' in x.lower() else 0 for x in classes]

classes_is_shark_id = [i for i, x in enumerate(classes_is_shark) if x == 1]
classes_is_human_id = [i for i, x in enumerate(classes_is_human) if x == 1]
classes_is_unknown_id = [i for i, x in enumerate(classes_is_unknown) if x == 1]

REPO_ID = "SharkSpace/maskformer_model"
FILENAME = "mask2former"

snapshot_download(repo_id=REPO_ID, token= os.environ.get('SHARK_MODEL'),local_dir='model/')

# Choose to use a config and initialize the detector
config_file ='model/mask2former_swin-t-p4-w7-224_8xb2-lsj-50e_coco-panoptic/mask2former_swin-t-p4-w7-224_8xb2-lsj-50e_coco-panoptic.py'
#'/content/mmdetection/configs/panoptic_fpn/panoptic-fpn_r50_fpn_ms-3x_coco.py'
# Setup a checkpoint file to load
checkpoint_file ='model/mask2former_swin-t-p4-w7-224_8xb2-lsj-50e_coco-panoptic/checkpoint_v2.pth'
# '/content/drive/MyDrive/Algorithms/weights/shark_panoptic_weights_16_4_23/panoptic-fpn_r50_fpn_ms-3x_coco/epoch_36.pth'

# register all modules in mmdet into the registries
register_all_modules()

# build the model from a config file and a checkpoint file
model = init_detector(config_file, checkpoint_file, device='cuda:0')  # or device='cuda:0'
model.dataset_meta['palette'] = model.dataset_meta['palette'] + model.dataset_meta['palette'][-23:]
model.dataset_meta['classes'] = classes
print(model.cfg.visualizer)
# init visualizer(run the block only once in jupyter notebook)
visualizer = VISUALIZERS.build(model.cfg.visualizer)
print(dir(visualizer))
# the dataset_meta is loaded from the checkpoint and
# then pass to the model in init_detector
visualizer.dataset_meta = model.dataset_meta
classes = visualizer.dataset_meta.get('classes', None)
palette = visualizer.dataset_meta.get('palette', None)

print(len(classes))
print(len(palette))
def inference_frame_serial(image, visualize = True):
    #start = time()
    result = inference_detector(model, image)
    #print(f'inference time: {time()-start}')
    # show the results
    if visualize:
        visualizer.add_datasample(
        'result',
        image,
        data_sample=result,
        draw_gt = None,
        show=False
        )
        frame = visualizer.get_image()
    else:
        frame = None
    return frame, result

def inference_frame(image):
    result = inference_detector(model, image)
    # show the results
    frames = []
    cnt=0
    
    for res in result:
        visualizer.add_datasample(
        'result',
        image[cnt],
        data_sample=res.numpy(),
        draw_gt = None,
        show=False
        )
        frame = visualizer.get_image()
        frames.append(frame)
        cnt+=1

    #frames = process_frames(result, image, visualizer)
    return frames

def inference_frame_par_ready(image):
    result = inference_detector(model, image)
    return [result[i].numpy() for i in range(len(result))]

def process_frame(in_tuple = (None, None, None)):
    visualizer.add_datasample(
        'result',
        in_tuple[1], #image,
        data_sample=in_tuple[0], #result
        draw_gt = None,
        show=False
        )
    
    #frame = visualizer.get_image()
    #print(in_tuple[2])
    return visualizer.get_image()

#def process_frame(frame):

# def process_frames(result, image, visualizer):
#     frames = []
#     lock = threading.Lock()

#     def process_data(cnt, res, img):
#         visualizer.add_datasample('result', img, data_sample=res, draw_gt=None, show=False)
#         frame = visualizer.get_image()
#         with lock:
#             frames.append(frame)

#     threads = []
#     for cnt, res in enumerate(result):
#         t = threading.Thread(target=process_data, args=(cnt, res, image[cnt]))
#         threads.append(t)
#         t.start()

#     for t in threads:
#         t.join()

#     return frames