Update app and weights

main.py

@@ -4,6 +4,10 @@ import cv2
 import sys
 import torch
 import numpy as np
+import logging
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
 print('Loading model...')
 device = 'gpu' if torch.cuda.is_available() else 'cpu'
@@ -81,12 +85,16 @@ def get_bbox(mask_array):
 
 
 def predict(image_input):
+    logger.info(f"Image input: {image_input}")
+    
     # Inference the tables in the image.
     result = inference_detector(table_det, image_input)
 
     # Get the masks of the tables.
     mask_images = result.pred_instances.masks.cpu().numpy()
     scores = result.pred_instances.scores.cpu().numpy()
+    
+    logger.info(f"Result: {result}")
 
     bbox_list = []
 

model/table-det/config.py

@@ -2,9 +2,9 @@ model = dict(
     type='MaskRCNN',
     data_preprocessor=dict(
         type='DetDataPreprocessor',
-        mean=[123.675, 116.28, 103.53],
-        std=[58.395, 57.12, 57.375],
-        bgr_to_rgb=True,
+        mean=[103.53, 116.28, 123.675],
+        std=[1.0, 1.0, 1.0],
+        bgr_to_rgb=False,
         pad_mask=True,
         pad_size_divisor=32),
     backbone=dict(
@@ -13,10 +13,12 @@ model = dict(
         num_stages=4,
         out_indices=(0, 1, 2, 3),
         frozen_stages=1,
-        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_cfg=dict(type='BN', requires_grad=False),
         norm_eval=True,
-        style='pytorch',
-        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+        style='caffe',
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
     neck=dict(
         type='FPN',
         in_channels=[256, 512, 1024, 2048],
@@ -123,12 +125,21 @@ model = dict(
             nms=dict(type='nms', iou_threshold=0.5),
             max_per_img=100,
             mask_thr_binary=0.5)))
+dataset_type = 'CocoDataset'
+data_root = 'data/table-det-elect66/'
 backend_args = None
 train_pipeline = [
     dict(type='LoadImageFromFile', backend_args=None),
-    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
-    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
-    dict(type='Rotate', level=10),
+    dict(
+        type='LoadAnnotations',
+        with_bbox=True,
+        with_mask=True,
+        poly2mask=False),
+    dict(
+        type='RandomChoiceResize',
+        scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                (1333, 768), (1333, 800)],
+        keep_ratio=True),
     dict(type='RandomFlip', prob=0.5),
     dict(type='PackDetInputs')
 ]
@@ -141,82 +152,35 @@ test_pipeline = [
         meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                    'scale_factor'))
 ]
-data_root = 'data/table-det-elect66/'
-metainfo = dict(classes=('Table', ), palette=[(220, 20, 60)])
-dataset_elect66 = dict(
-    type='CocoDataset',
-    data_root='data/table-det-elect66/',
-    ann_file='result.json',
-    data_prefix=dict(img=''),
-    metainfo=dict(classes=('Table', ), palette=[(220, 20, 60)]),
-    filter_cfg=dict(filter_empty_gt=True, min_size=32),
-    pipeline=[
-        dict(type='LoadImageFromFile', backend_args=None),
-        dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
-        dict(type='Resize', scale=(1333, 800), keep_ratio=True),
-        dict(type='Rotate', level=10),
-        dict(type='RandomFlip', prob=0.5),
-        dict(type='PackDetInputs')
-    ])
-dataset_vote62 = dict(
-    type='CocoDataset',
-    data_root='data/table-det-740/',
-    ann_file='train_coco.json',
-    data_prefix=dict(img=''),
-    metainfo=dict(classes=('Table', ), palette=[(220, 20, 60)]),
-    filter_cfg=dict(filter_empty_gt=True, min_size=32),
-    pipeline=[
-        dict(type='LoadImageFromFile', backend_args=None),
-        dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
-        dict(type='Resize', scale=(1333, 800), keep_ratio=True),
-        dict(type='Rotate', level=10),
-        dict(type='RandomFlip', prob=0.5),
-        dict(type='PackDetInputs')
-    ])
 train_dataloader = dict(
-    batch_size=2,
+    batch_size=8,
     num_workers=2,
     persistent_workers=True,
     sampler=dict(type='DefaultSampler', shuffle=True),
     batch_sampler=dict(type='AspectRatioBatchSampler'),
     dataset=dict(
-        type='ConcatDataset',
-        datasets=[
+        type='CocoDataset',
+        data_root='data/table-det-elect66/',
+        ann_file='result.json',
+        data_prefix=dict(img=''),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=[
+            dict(type='LoadImageFromFile', backend_args=None),
             dict(
-                type='CocoDataset',
-                data_root='data/table-det-elect66/',
-                ann_file='result.json',
-                data_prefix=dict(img=''),
-                metainfo=dict(classes=('Table', ), palette=[(220, 20, 60)]),
-                filter_cfg=dict(filter_empty_gt=True, min_size=32),
-                pipeline=[
-                    dict(type='LoadImageFromFile', backend_args=None),
-                    dict(
-                        type='LoadAnnotations', with_bbox=True,
-                        with_mask=True),
-                    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
-                    dict(type='Rotate', level=10),
-                    dict(type='RandomFlip', prob=0.5),
-                    dict(type='PackDetInputs')
-                ]),
+                type='LoadAnnotations',
+                with_bbox=True,
+                with_mask=True,
+                poly2mask=False),
             dict(
-                type='CocoDataset',
-                data_root='data/table-det-740/',
-                ann_file='train_coco.json',
-                data_prefix=dict(img=''),
-                metainfo=dict(classes=('Table', ), palette=[(220, 20, 60)]),
-                filter_cfg=dict(filter_empty_gt=True, min_size=32),
-                pipeline=[
-                    dict(type='LoadImageFromFile', backend_args=None),
-                    dict(
-                        type='LoadAnnotations', with_bbox=True,
-                        with_mask=True),
-                    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
-                    dict(type='Rotate', level=10),
-                    dict(type='RandomFlip', prob=0.5),
-                    dict(type='PackDetInputs')
-                ])
-        ]))
+                type='RandomChoiceResize',
+                scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                        (1333, 768), (1333, 800)],
+                keep_ratio=True),
+            dict(type='RandomFlip', prob=0.5),
+            dict(type='PackDetInputs')
+        ],
+        backend_args=None,
+        metainfo=dict(classes=('Table', ), palette=[(220, 20, 60)])))
 val_dataloader = dict(
     batch_size=1,
     num_workers=2,
@@ -275,7 +239,7 @@ test_evaluator = dict(
     metric=['bbox', 'segm'],
     format_only=False,
     backend_args=None)
-train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=10, val_interval=5)
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=70, val_interval=5)
 val_cfg = dict(type='ValLoop')
 test_cfg = dict(type='TestLoop')
 param_scheduler = [
@@ -296,7 +260,7 @@ auto_scale_lr = dict(enable=False, base_batch_size=16)
 default_scope = 'mmdet'
 default_hooks = dict(
     timer=dict(type='IterTimerHook'),
-    logger=dict(type='LoggerHook', interval=100),
+    logger=dict(type='LoggerHook', interval=50),
     param_scheduler=dict(type='ParamSchedulerHook'),
     checkpoint=dict(type='CheckpointHook', interval=5),
     sampler_seed=dict(type='DistSamplerSeedHook'),
@@ -314,5 +278,6 @@ log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
 log_level = 'INFO'
 load_from = None
 resume = True
+metainfo = dict(classes=('Table', ), palette=[(220, 20, 60)])
 launcher = 'none'
 work_dir = './work_dirs/vote-config'

model/table-det/model.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b7b83ed9cb684490569ace380f9df596f324e9ff43f847a91b010a86d220c94
-size 351412361
+oid sha256:e84722e31515bf2415bec7fafbb3f2d9ebbf058e7003b91d798e4cdb9219a58e
+size 351647241