ANet datatools

configs/recognition/tsn/tsn_r50_320p_1x1x8_150e_activitynet_clip_flow.py

@@ -80,6 +80,7 @@
         filename_tmpl='flow_{}_{:05d}.jpg',
         with_offset=True,
         modality='Flow',
+        start_index=0,
         pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
@@ -88,6 +89,7 @@
         filename_tmpl='flow_{}_{:05d}.jpg',
         with_offset=True,
         modality='Flow',
+        start_index=0,
         pipeline=val_pipeline),
     test=dict(
         type=dataset_type,
@@ -96,6 +98,7 @@
         filename_tmpl='flow_{}_{:05d}.jpg',
         with_offset=True,
         modality='Flow',
+        start_index=0,
         pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)

configs/recognition/tsn/tsn_r50_320p_1x1x8_150e_activitynet_video_flow.py

@@ -80,6 +80,7 @@
         filename_tmpl='flow_{}_{:05d}.jpg',
         with_offset=True,
         modality='Flow',
+        start_index=0,
         pipeline=train_pipeline),
     val=dict(
         type=dataset_type,
@@ -88,6 +89,7 @@
         filename_tmpl='flow_{}_{:05d}.jpg',
         with_offset=True,
         modality='Flow',
+        start_index=0,
         pipeline=val_pipeline),
     test=dict(
         type=dataset_type,
@@ -96,6 +98,7 @@
         filename_tmpl='flow_{}_{:05d}.jpg',
         with_offset=True,
         modality='Flow',
+        start_index=0,
         pipeline=test_pipeline))
 # optimizer
 optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)

configs/recognition/tsn/tsn_r50_320p_1x1x8_50e_activitynet_clip_rgb.py

@@ -79,20 +79,23 @@
         data_prefix=data_root,
         pipeline=train_pipeline,
         with_offset=True,
+        start_index=0,
         filename_tmpl='image_{:05d}.jpg'),
     val=dict(
         type=dataset_type,
         ann_file=ann_file_val,
         data_prefix=data_root_val,
         pipeline=val_pipeline,
         with_offset=True,
+        start_index=0,
         filename_tmpl='image_{:05d}.jpg'),
     test=dict(
         type=dataset_type,
         ann_file=ann_file_test,
         data_prefix=data_root_val,
         pipeline=test_pipeline,
         with_offset=True,
+        start_index=0,
         filename_tmpl='image_{:05d}.jpg'))
 # optimizer
 optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)

configs/recognition/tsn/tsn_r50_320p_1x1x8_50e_activitynet_video_rgb.py

@@ -79,20 +79,23 @@
         data_prefix=data_root,
         pipeline=train_pipeline,
         with_offset=True,
+        start_index=0,
         filename_tmpl='image_{:05d}.jpg'),
     val=dict(
         type=dataset_type,
         ann_file=ann_file_val,
         data_prefix=data_root_val,
         pipeline=val_pipeline,
         with_offset=True,
+        start_index=0,
         filename_tmpl='image_{:05d}.jpg'),
     test=dict(
         type=dataset_type,
         ann_file=ann_file_test,
         data_prefix=data_root_val,
         pipeline=test_pipeline,
         with_offset=True,
+        start_index=0,
         filename_tmpl='image_{:05d}.jpg'))
 # optimizer
 optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)

mmaction/datasets/ssn_dataset.py

@@ -455,8 +455,8 @@ def evaluate(self,
         plain_detections = {}
         for class_idx in range(len(detections)):
             detection_list = []
-            for vid, dets in detections[class_idx].items():
-                detection_list.extend([[vid, class_idx] + x[:3]
+            for video, dets in detections[class_idx].items():
+                detection_list.extend([[video, class_idx] + x[:3]
                                        for x in dets.tolist()])
             plain_detections[class_idx] = detection_list
 
@@ -500,15 +500,15 @@ def get_all_gts(self):
         """Fetch groundtruth instances of the entire dataset."""
         gts = {}
         for video_info in self.video_infos:
-            vid = video_info['video_id']
+            video = video_info['video_id']
             for gt in video_info['gts']:
                 class_idx = gt.label - 1
                 # gt_info: [relative_start, relative_end]
                 gt_info = [
                     gt.start_frame / video_info['total_frames'],
                     gt.end_frame / video_info['total_frames']
                 ]
-                gts.setdefault(class_idx, {}).setdefault(vid,
+                gts.setdefault(class_idx, {}).setdefault(video,
                                                          []).append(gt_info)
 
         return gts

tools/data/activitynet/action_name.csv

@@ -0,0 +1,201 @@
+action
+Applying sunscreen
+Arm wrestling
+Assembling bicycle
+BMX
+Baking cookies
+Baton twirling
+Beach soccer
+Beer pong
+Blow-drying hair
+Blowing leaves
+Playing ten pins
+Braiding hair
+Building sandcastles
+Bullfighting
+Calf roping
+Camel ride
+Canoeing
+Capoeira
+Carving jack-o-lanterns
+Changing car wheel
+Cleaning sink
+Clipping cat claws
+Croquet
+Curling
+Cutting the grass
+Decorating the Christmas tree
+Disc dog
+Doing a powerbomb
+Doing crunches
+Drum corps
+Elliptical trainer
+Doing fencing
+Fixing the roof
+Fun sliding down
+Futsal
+Gargling mouthwash
+Grooming dog
+Hand car wash
+Hanging wallpaper
+Having an ice cream
+Hitting a pinata
+Hula hoop
+Hurling
+Ice fishing
+Installing carpet
+Kite flying
+Kneeling
+Knitting
+Laying tile
+Longboarding
+Making a cake
+Making a lemonade
+Making an omelette
+Mooping floor
+Painting fence
+Painting furniture
+Peeling potatoes
+Plastering
+Playing beach volleyball
+Playing blackjack
+Playing congas
+Playing drums
+Playing ice hockey
+Playing pool
+Playing rubik cube
+Powerbocking
+Putting in contact lenses
+Putting on shoes
+Rafting
+Raking leaves
+Removing ice from car
+Riding bumper cars
+River tubing
+Rock-paper-scissors
+Rollerblading
+Roof shingle removal
+Rope skipping
+Running a marathon
+Scuba diving
+Sharpening knives
+Shuffleboard
+Skiing
+Slacklining
+Snow tubing
+Snowboarding
+Spread mulch
+Sumo
+Surfing
+Swimming
+Swinging at the playground
+Table soccer
+Throwing darts
+Trimming branches or hedges
+Tug of war
+Using the monkey bar
+Using the rowing machine
+Wakeboarding
+Waterskiing
+Waxing skis
+Welding
+Drinking coffee
+Zumba
+Doing kickboxing
+Doing karate
+Tango
+Putting on makeup
+High jump
+Playing bagpipes
+Cheerleading
+Wrapping presents
+Cricket
+Clean and jerk
+Preparing pasta
+Bathing dog
+Discus throw
+Playing field hockey
+Grooming horse
+Preparing salad
+Playing harmonica
+Playing saxophone
+Chopping wood
+Washing face
+Using the pommel horse
+Javelin throw
+Spinning
+Ping-pong
+Making a sandwich
+Brushing hair
+Playing guitarra
+Doing step aerobics
+Drinking beer
+Playing polo
+Snatch
+Paintball
+Long jump
+Cleaning windows
+Brushing teeth
+Playing flauta
+Tennis serve with ball bouncing
+Bungee jumping
+Triple jump
+Horseback riding
+Layup drill in basketball
+Vacuuming floor
+Cleaning shoes
+Doing nails
+Shot put
+Fixing bicycle
+Washing hands
+Ironing clothes
+Using the balance beam
+Shoveling snow
+Tumbling
+Using parallel bars
+Getting a tattoo
+Rock climbing
+Smoking hookah
+Shaving
+Getting a piercing
+Springboard diving
+Playing squash
+Playing piano
+Dodgeball
+Smoking a cigarette
+Sailing
+Getting a haircut
+Playing lacrosse
+Cumbia
+Tai chi
+Painting
+Mowing the lawn
+Shaving legs
+Walking the dog
+Hammer throw
+Skateboarding
+Polishing shoes
+Ballet
+Hand washing clothes
+Plataform diving
+Playing violin
+Breakdancing
+Windsurfing
+Hopscotch
+Doing motocross
+Mixing drinks
+Starting a campfire
+Belly dance
+Removing curlers
+Archery
+Volleyball
+Playing water polo
+Playing racquetball
+Kayaking
+Polishing forniture
+Playing kickball
+Using uneven bars
+Washing dishes
+Pole vault
+Playing accordion
+Playing badminton

tools/data/activitynet/activitynet_feature_extraction.py → tools/data/activitynet/activitynet_feature_postprocessing.py

@@ -15,7 +15,7 @@ def parse_args():
     parser.add_argument('--rgb', default='', help='rgb feature root')
     parser.add_argument('--flow', default='', help='flow feature root')
     parser.add_argument('--dest', default='', help='dest root')
-    parser.add_argument('--output-format', default='pkl', help='clip length')
+    parser.add_argument('--output-format', default='csv')
     args = parser.parse_args()
     return args
 
@@ -64,12 +64,13 @@ def pool_feature(data, num_proposals=100, num_sample_bins=3, pool_type='mean'):
 
 def merge_feat(name):
     # concatenate rgb feat and flow feat for a single sample
-    global args
     rgb_feat = load(osp.join(args.rgb, name))
     flow_feat = load(osp.join(args.flow, name))
     rgb_feat = pool_feature(rgb_feat)
     flow_feat = pool_feature(flow_feat)
     feat = np.concatenate([rgb_feat, flow_feat], axis=-1)
+    if not osp.exists(args.dest):
+        os.system(f'mkdir -p {args.dest}')
     if args.output_format == 'pkl':
         dump(feat, osp.join(args.dest, name))
     elif args.output_format == 'csv':