gpu3

.gitignore

@@ -114,6 +114,7 @@ data
 *.pkl.json
 *.log.json
 work_dirs/
+results/
 
 # Pytorch
 *.pth

configs/_base_/datasets/voc0712_analyze.py

+# dataset settings
+dataset_type = 'VOCDataset'
+#data_root = 'data/VOCdevkit/'
+data_root = '/opt/Dataset/VOCdevkit/'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1000, 600),
+        flip=False,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ])
+]
+data = dict(
+    samples_per_gpu=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=[
+            data_root + 'VOC2007/ImageSets/Main/trainval.txt',
+            data_root + 'VOC2012/ImageSets/Main/trainval.txt'
+        ],
+        img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
+        img_prefix=data_root + 'VOC2007/',
+        pipeline=test_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
+        img_prefix=data_root + 'VOC2007/',
+        pipeline=test_pipeline))
+evaluation = dict(interval=1, metric='mAP')

configs/pascal_voc/cascade_rcnn_r152_fpn_1x_voc0712.py

+_base_ = './cascade_rcnn_r50_fpn_1x_voc0712.py'
+model = dict(
+    backbone=dict(
+        depth=152,
+        init_cfg=dict(type='Pretrained',
+                      checkpoint='torchvision://resnet152')))
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
\ No newline at end of file

configs/pascal_voc/cascade_rcnn_r50_fpn_1x_voc0712.py

@@ -58,11 +58,16 @@ model = dict(roi_head=dict(bbox_head=[
         ]))
 
 # optimizer
-optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
 optimizer_config = dict(grad_clip=None)
 # learning policy
 # actual epoch = 3 * 3 = 9
-lr_config = dict(policy='step', step=[3])
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=200,
+    warmup_ratio=0.001,
+    step=[3])
 # runtime settings
 runner = dict(
     type='EpochBasedRunner', max_epochs=4)  # actual epoch = 4 * 3 = 12

configs/pascal_voc/faster_rcnn_r152_fpn_1x_voc0712.py

@@ -6,4 +6,10 @@ model = dict(
                       checkpoint='torchvision://resnet152')))
 
 optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=200,
+    warmup_ratio=0.001,
+    step=[3])