update for inference

configs/AD_mlops/AD_mlops_test18.py

@@ -1,5 +1,5 @@
 _base_ = [
-    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+    '../_base_/schedules/schedule_1x.py', '../_base_/datasets/coco_detection.py', '../_base_/default_runtime.py'
 ]
 norm_cfg = dict(type='BN', requires_grad=True)
 model = dict(
@@ -61,71 +61,71 @@ model = dict(
         nms=dict(type='nms', iou_threshold=0.6),
         max_per_img=100))
 
-dataset_type = 'CocoDataset'
-classes = ('yiwei','loujian','celi','libei','fantie','lianxi','duojian','shunjian','shaoxi','jiahan','yiwu')
+#dataset_type = 'CocoDataset'
+#classes = ('yiwei','loujian','celi','libei','fantie','lianxi','duojian','shunjian','shaoxi','jiahan','yiwu')
 
-img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+#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=[(512, 512), (640, 640)],
-        multiscale_mode='value',
-        keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=[0.2,0.2,0.2], direction=['horizontal', 'vertical', 'diagonal']),
-    dict(type='BrightnessTransform', level=5, prob=0.5),
-    dict(type='ContrastTransform', level=5, prob=0.5),
-    dict(type='RandomShift', shift_ratio=0.5),
-    dict(type='MinIoURandomCrop', min_ious=(0.5, 0.7, 0.9), min_crop_size=0.8),
-    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=[(640, 640)],
-        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']),
-        ])
-]
+#train_pipeline = [
+#    dict(type='LoadImageFromFile'),
+#    dict(type='LoadAnnotations', with_bbox=True),
+#    dict(
+#        type='Resize',
+#        img_scale=[(512, 512), (640, 640)],
+#        multiscale_mode='value',
+#        keep_ratio=True),
+#    dict(type='RandomFlip', flip_ratio=[0.2,0.2,0.2], direction=['horizontal', 'vertical', 'diagonal']),
+#    dict(type='BrightnessTransform', level=5, prob=0.5),
+#    dict(type='ContrastTransform', level=5, prob=0.5),
+#    dict(type='RandomShift', shift_ratio=0.5),
+#    dict(type='MinIoURandomCrop', min_ious=(0.5, 0.7, 0.9), min_crop_size=0.8),
+#    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=[(640, 640)],
+#        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=4,
-    workers_per_gpu=2,
-    train=dict(
-        type='AD_ClassBalancedDataset',
-        dataset=dict(
-            type=dataset_type,
-            img_prefix='data/coco/train2017/',
-            classes=classes,
-            ann_file='data/coco/annotations/instances_train2017.json',
-            pipeline=train_pipeline,
-        ),
-        oversample_thr = 1.0),
-    val=dict(
-        type=dataset_type,
-        img_prefix='data/coco/train2017/',
-        classes=classes,
-        ann_file='data/coco/annotations/instances_train2017.json',
-        pipeline=test_pipeline),
-    test=dict(
-        type=dataset_type,
-        img_prefix='data/coco/train2017/',
-        classes=classes,
-        ann_file='data/coco/annotations/instances_train2017.json',
-        pipeline=test_pipeline))
+#data = dict(
+#    samples_per_gpu=4,
+#    workers_per_gpu=2,
+#    train=dict(
+#        type='AD_ClassBalancedDataset',
+#        dataset=dict(
+#            type=dataset_type,
+#            img_prefix='data/coco/train2017/',
+#            classes=classes,
+#            ann_file='data/coco/annotations/instances_train2017.json',
+#            pipeline=train_pipeline,
+#        ),
+#        oversample_thr = 1.0),
+#    val=dict(
+#        type=dataset_type,
+#        img_prefix='data/coco/train2017/',
+#        classes=classes,
+#        ann_file='data/coco/annotations/instances_train2017.json',
+#        pipeline=test_pipeline),
+#    test=dict(
+#        type=dataset_type,
+#        img_prefix='data/coco/train2017/',
+#        classes=classes,
+#        ann_file='data/coco/annotations/instances_train2017.json',
+#        pipeline=test_pipeline))
 
 # optimizer
 optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
@@ -139,5 +139,5 @@ lr_config = dict(
     min_lr_ratio=1e-5)
 runner = dict(type='EpochBasedRunner', max_epochs=20)
 
-evaluation = dict(interval=1, metric='bbox')
-checkpoint_config = dict(interval=1)
+evaluation = dict(interval=10, metric='bbox')
+checkpoint_config = dict(interval=5)

configs/atss/atss_r101_fpn_1x_coco.py

@@ -1,6 +1,64 @@
-_base_ = './atss_r50_fpn_1x_coco.py'
+_base_ = [
+    '../_base_/datasets/coco_detection.py',
+    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
+]
 model = dict(
+    type='ATSS',
     backbone=dict(
+        type='ResNeXt',
         depth=101,
-        init_cfg=dict(type='Pretrained',
-                      checkpoint='torchvision://resnet101')))
+        groups=64,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        norm_cfg=norm_cfg,
+        style='pytorch',
+        init_cfg=dict(
+            type='Pretrained', checkpoint='/tmp/code/code_test/resnext101_64x4d-ee2c6f71.pth')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs='on_output',
+        num_outs=5),
+    bbox_head=dict(
+        type='ATSSHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='AnchorGenerator',
+            ratios=[1.0],
+            octave_base_scale=8,
+            scales_per_octave=1,
+            strides=[8, 16, 32, 64, 128]),
+        bbox_coder=dict(
+            type='DeltaXYWHBBoxCoder',
+            target_means=[.0, .0, .0, .0],
+            target_stds=[0.1, 0.1, 0.2, 0.2]),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
+        loss_centerness=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
+    # training and testing settings
+    train_cfg=dict(
+        assigner=dict(type='ATSSAssigner', topk=9),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=1000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(type='nms', iou_threshold=0.6),
+        max_per_img=100))
+# optimizer
+optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)

tools/train.py

@@ -399,8 +399,8 @@ def main():
     #if on platform, change the classnum fit the user define dataset
     if args.data_path is not None:
         coco_config=COCO(os.path.join(args.data_path,"annotations/instances_annotations.json"))
-        cfg.data.train.dataset.img_prefix = os.path.join(args.data_path,"images")
-        cfg.data.train.dataset.ann_file =  os.path.join(args.data_path,"annotations/instances_annotations.json")
+        cfg.data.train.img_prefix = os.path.join(args.data_path,"images")
+        cfg.data.train.ann_file =  os.path.join(args.data_path,"annotations/instances_annotations.json")
 
         cfg.data.val.img_prefix = os.path.join(args.data_path,"images")
         cfg.data.val.ann_file =  os.path.join(args.data_path,"annotations/instances_annotations.json")
@@ -411,7 +411,7 @@ def main():
         for cat in coco_config.cats.values():
             cfg.classes = cfg.classes + tuple([cat['name']])
 
-        cfg.data.train.dataset.classes = cfg.classes
+        cfg.data.train.classes = cfg.classes
         cfg.data.val.classes = cfg.classes
         cfg.data.test.classes = cfg.classes
 

transformer/postprocess.py

@@ -81,7 +81,14 @@ class Filter:
     def filter(self, inputs, meta_list):
         results = []
         for dets, labels, feature, det_features, det_lloss, meta in zip(inputs['dets'], inputs['labels'], inputs['feature'], inputs['entropy'], inputs['learning_loss'], meta_list):
+
             pred = Predict()
+            if len(labels) == 0:
+                result = Any()
+                result.Pack(pred, pred.DESCRIPTOR.file.package)
+                results.append([result.SerializeToString()])
+                continue
+
             
             meta['result'] = 'OK'
             meta['score'] = 0
@@ -104,18 +111,18 @@ class Filter:
                             label_id=index)
                         )
             
-            scores = dets[:,4]
-            entropy_nms = get_entropy_by_enms(labels, scores, det_features)
+            #scores = dets[:,4]
+            #entropy_nms = get_entropy_by_enms(labels, scores, det_features)
             
-            learning_loss_nms = get_lloss_by_lnms(labels, det_lloss, det_features)
+            #learning_loss_nms = get_lloss_by_lnms(labels, det_lloss, det_features)
             
-            meta['attributes']={}
+            #meta['attributes']={}
             #meta['attributes']['feature'] = feature.tolist()
-            meta['attributes']['entropy'] = float(entropy)
-            meta['attributes']['learning_loss'] = float(learning_loss)
-            meta['attributes']['entropy_nms'] = float(entropy_nms)
-            meta['attributes']['learning_loss_nms'] = float(learning_loss_nms)
-            meta['attributes']['distance'] = 0
+            #meta['attributes']['entropy'] = float(entropy)
+            #meta['attributes']['learning_loss'] = float(learning_loss)
+            #meta['attributes']['entropy_nms'] = float(entropy_nms)
+            #meta['attributes']['learning_loss_nms'] = float(learning_loss_nms)
+            #meta['attributes']['distance'] = 0
             
             result = Any()
             result.Pack(pred, pred.DESCRIPTOR.file.package)