reverting

app.py

@@ -1,8 +1,6 @@
 
-
 import subprocess
 import os  
-import os  
 if os.getenv('SYSTEM') == 'spaces':
 
     subprocess.call('pip install -U openmim'.split())
@@ -16,9 +14,6 @@ if os.getenv('SYSTEM') == 'spaces':
 
 import gradio as gr
 
-import gradio as gr
-
-from huggingface_hub import snapshot_download
 from huggingface_hub import snapshot_download
 import cv2 
 import dotenv 
@@ -33,16 +28,12 @@ from inference import classes
 from inference import class_sizes_lower
 from metrics import process_results_for_plot
 from metrics import prediction_dashboard
-from inference import classes
-from inference import class_sizes_lower
-from metrics import process_results_for_plot
-from metrics import prediction_dashboard
 import os
 import pathlib
 import multiprocessing as mp
 from time import time
 
-if not os.path.exists('videos_example') and not os.getenv('SYSTEM') == 'spaces':
+if not os.path.exists('videos_example'):
     REPO_ID='SharkSpace/videos_examples'
     snapshot_download(repo_id=REPO_ID, token=os.environ.get('SHARK_MODEL'),repo_type='dataset',local_dir='videos_example')
 
@@ -143,7 +134,7 @@ def draw_cockpit(frame, top_pred,cnt):
     
     
 
-def process_video(input_video,out_fps = 'auto', skip_frames = 7):
+def process_video(input_video, out_fps = 'auto', skip_frames = 7):
     cap = cv2.VideoCapture(input_video)
 
     output_path = "output.mp4"
@@ -205,9 +196,8 @@ def process_video(input_video,out_fps = 'auto', skip_frames = 7):
     yield None,  output_path
 
 with gr.Blocks(theme=theme) as demo:
-    with gr.Row().style(equal_height=True):
+    with gr.Row().style(equal_height=True,height='25%'):
         input_video = gr.Video(label="Input")
-        
         original_frames = gr.Image(label="Processed Frame").style( height=650)
         #processed_frames = gr.Image(label="Shark Engine")
         output_video = gr.Video(label="Output Video")

inference.py

@@ -15,7 +15,6 @@ from huggingface_hub import hf_hub_download
 from huggingface_hub import snapshot_download
 from time import time
 
-classes = ['Beach',
 classes = ['Beach',
  'Sea',
  'Wave',
@@ -25,19 +24,13 @@ classes = ['Beach',
  'Foam',
  'Algae',
  'Vegetation',
- 'Algae',
- 'Vegetation',
  'Watermark',
  'Bird',
  'Ship',
  'Boat',
  'Car',
- 'Ship',
- 'Boat',
- 'Car',
  'Kayak',
  "Shark's line",
- "Shark's line",
  'Dock',
  'Dog',
  'Unidentifiable shade',
@@ -53,15 +46,13 @@ classes = ['Beach',
  'Person',
  'ocean',
  'Surfer',
- 'ocean',
- 'Surfer',
  'Surfer',
  'Fish',
  'Killer whale',
  'Whale',
  'Dolphin',
  'Miscellaneous',
- 'Shadow',
+ 'Unidentifiable shark',
  'C Shark',
  'Dusty shark',
  'Blue shark',
@@ -76,16 +67,6 @@ classes = ['Beach',
  'Blacktip shark',
  'Tiger shark',
  'Bull shark']*3
- '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,
@@ -124,7 +105,7 @@ class_sizes = {'Beach': None,
                '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,
-               'Shadow': {'feet': [2, 15], 'meter': [0.6, 4.5], 'kg': [50, 1000], 'pounds': [110, 2200]},
+               'Unidentifiable shark': {'feet': [2, 15], 'meter': [0.6, 4.5], 'kg': [50, 1000], 'pounds': [110, 2200]},
                'C 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]}, 
@@ -143,11 +124,6 @@ class_sizes = {'Beach': None,
 
 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]
-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]
@@ -155,15 +131,8 @@ 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]
-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]
 
 
-if not os.path.exists('model'):
-    REPO_ID = "SharkSpace/maskformer_model"
-    FILENAME = "mask2former"
-    snapshot_download(repo_id=REPO_ID, token= os.environ.get('SHARK_MODEL'),local_dir='model/')
 if not os.path.exists('model'):
     REPO_ID = "SharkSpace/maskformer_model"
     FILENAME = "mask2former"
@@ -182,7 +151,6 @@ 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['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)
@@ -194,20 +162,12 @@ 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()
-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}')
-    #print(f'inference time: {time()-start}')
     # show the results
     if visualize:
         visualizer.add_datasample(
@@ -221,18 +181,6 @@ def inference_frame_serial(image, visualize = True):
     else:
         frame = None
     return frame, result
-    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)