Closed TapendraBaduwal closed 1 year ago
what's your version of paddlapaddle?
@an1018 PaddlePaddle 2.4.1, compiled with with_avx: ON with_gpu: OFF with_mkl: ON with_mkldnn: ON with_python: ON
You can try install PaddlePaddle 2.3
@an1018 same error with paddle 2.3
--- fused 0 elementwise_mul with hardswish activation
--- fused 0 elementwise_mul with sqrt activation
--- fused 0 elementwise_mul with abs activation
--- fused 0 elementwise_mul with clip activation
--- fused 0 elementwise_mul with gelu activation
--- fused 0 elementwise_mul with relu6 activation
--- fused 0 elementwise_mul with sigmoid activation
Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/tapendra/Desktop/layout/layout_analysis.py", line 71, in Input
contains uninitialized Tensor.
[Hint: Expected t->IsInitialized() == true, but received t->IsInitialized():0 != true:1.] (at /paddle/paddle/fluid/framework/operator.cc:2094)
[operator < conv2d > error]
tapendra@tapendra:~/Desktop/layout$ paddle version
/home/tapendra/.local/bin/paddle: line 150: python: command not found
PaddlePaddle 2.3.2, compiled with
with_avx: ON
with_gpu: OFF
with_mkl: ON
with_mkldnn: ON
with_python: ON
@an1018 my train.json file data for model training {"images":[{"height":1650,"width":1275,"id":1,"file_name":"Tu_page-0003.jpg"},{"height":1754,"width":1240,"id":2,"file_name":"Tu_page-004.jpg"},{"height":1754,"width":1240,"id":3,"file_name":"Tu_page-005.jpg"},{"height":1650,"width":1275,"id":4,"file_name":"Tu_page-0001.jpg"},{"height":1650,"width":1275,"id":5,"file_name":"Tu_page-0002.jpg"}],"annotations":[{"iscrowd":0,"image_id":1,"bbox":[48.205128205128176,128.15384615384616,992.3076923076924,310.2564102564103],"segmentation":[[48,135,55,438,1040,433,1025,128]],"category_id":0,"id":1,"area":298076},{"iscrowd":0,"image_id":1,"bbox":[189.23076923076917,402.5128205128205,641.025641025641,446.15384615384613],"segmentation":[[189,430,199,840,830,848,814,402]],"category_id":1,"id":2,"area":269132},{"iscrowd":0,"image_id":2,"bbox":[112.67567567567573,193.40540540540542,427.027027027027,178.3783783783784],"segmentation":[[112,193,120,369,539,371,531,193]],"category_id":0,"id":3,"area":74149},{"iscrowd":0,"image_id":2,"bbox":[545.1081081081081,185.2972972972973,540.5405405405406,194.59459459459458],"segmentation":[[545,185,553,379,1082,374,1085,188]],"category_id":2,"id":4,"area":101968},{"iscrowd":0,"image_id":2,"bbox":[120.78378378378375,377.1891891891892,1002.7027027027027,475.6756756756757],"segmentation":[[120,390,145,852,1123,850,1099,377]],"category_id":0,"id":5,"area":457655},{"iscrowd":0,"image_id":2,"bbox":[258.62162162162167,793.4054054054054,737.8378378378377,237.83783783783792],"segmentation":[[258,823,266,1031,996,1023,966,793]],"category_id":1,"id":6,"area":157742},{"iscrowd":0,"image_id":2,"bbox":[172.1351351351351,1017.7297297297298,864.8648648648649,83.78378378378375],"segmentation":[[177,1020,172,1101,1037,1093,1034,1017]],"category_id":0,"id":7,"area":67461},{"iscrowd":0,"image_id":2,"bbox":[293.7567567567568,1077.1891891891892,718.9189189189188,224.32432432432438],"segmentation":[[293,1079,299,1301,1012,1293,1004,1077]],"category_id":1,"id":8,"area":155942},{"iscrowd":0,"image_id":2,"bbox":[153.21621621621625,1290.7027027027027,864.8648648648648,67.5675675675675],"segmentation":[[153,1290,158,1358,1018,1358,1018,1306]],"category_id":0,"id":9,"area":51241},{"iscrowd":0,"image_id":2,"bbox":[264.0270270270271,1358.2702702702702,754.054054054054,267.5675675675677],"segmentation":[[264,1360,277,1625,1012,1617,1018,1358]],"category_id":1,"id":10,"area":195226},{"iscrowd":0,"image_id":3,"bbox":[145.10810810810813,163.67567567567568,940.5405405405406,91.89189189189187],"segmentation":[[145,177,147,255,1085,255,1082,163]],"category_id":0,"id":11,"area":79861},{"iscrowd":0,"image_id":3,"bbox":[247.81081081081084,247.45945945945948,686.4864864864865,200.0],"segmentation":[[247,255,261,444,934,447,928,247]],"category_id":1,"id":12,"area":131771},{"iscrowd":0,"image_id":3,"bbox":[104.56756756756761,442.05405405405406,1008.108108108108,337.8378378378378],"segmentation":[[104,442,118,774,1112,779,1096,447]],"category_id":0,"id":13,"area":330105},{"iscrowd":0,"image_id":3,"bbox":[242.40540540540542,744.7567567567568,732.4324324324325,218.91891891891896],"segmentation":[[242,758,253,963,974,955,953,744]],"category_id":1,"id":14,"area":149225},{"iscrowd":0,"image_id":3,"bbox":[104.56756756756761,939.3513513513514,1016.2162162162161,354.05405405405406],"segmentation":[[104,942,109,1285,1120,1293,1112,939]],"category_id":0,"id":15,"area":351928},{"iscrowd":0,"image_id":4,"bbox":[35.38461538461536,105.07692307692307,479.48717948717956,158.97435897435898],"segmentation":[[35,105,35,264,514,261,514,105]],"category_id":0,"id":16,"area":75611},{"iscrowd":0,"image_id":4,"bbox":[514.8717948717949,105.07692307692307,615.3846153846152,179.48717948717947],"segmentation":[[514,105,1130,110,1122,284,520,264]],"category_id":2,"id":17,"area":101512},{"iscrowd":0,"image_id":4,"bbox":[30.256410256410277,294.8205128205128,1084.6153846153848,535.8974358974359],"segmentation":[[35,294,1114,307,1109,830,30,825]],"category_id":0,"id":18,"area":568852},{"iscrowd":0,"image_id":4,"bbox":[258.46153846153845,840.9743589743589,641.025641025641,358.9743589743591],"segmentation":[[258,840,268,1192,894,1199,899,843]],"category_id":1,"id":19,"area":224089},{"iscrowd":0,"image_id":4,"bbox":[86.66666666666663,1207.6410256410256,1002.5641025641027,97.43589743589746],"segmentation":[[86,1207,89,1302,1089,1305,1084,1223]],"category_id":0,"id":20,"area":88313},{"iscrowd":0,"image_id":4,"bbox":[158.46153846153845,1282.0,766.6666666666666,287.17948717948707],"segmentation":[[158,1282,171,1548,925,1569,922,1312]],"category_id":1,"id":21,"area":198303},{"iscrowd":0,"image_id":4,"bbox":[89.23076923076917,1548.6666666666665,1002.5641025641027,82.05128205128221],"segmentation":[[89,1548,89,1620,1091,1630,1089,1553]],"category_id":0,"id":22,"area":74444},{"iscrowd":0,"image_id":5,"bbox":[76.41025641025635,115.33333333333334,966.6666666666667,89.74358974358972],"segmentation":[[76,120,78,197,1043,205,1043,115]],"category_id":0,"id":23,"area":80447},{"iscrowd":0,"image_id":5,"bbox":[237.9487179487179,210.2051282051282,612.8205128205128,271.7948717948718],"segmentation":[[237,220,245,482,850,482,835,210]],"category_id":1,"id":24,"area":160401},{"iscrowd":0,"image_id":5,"bbox":[73.84615384615381,494.8205128205128,946.1538461538462,94.8717948717948],"segmentation":[[76,494,73,582,1020,589,1012,499]],"category_id":1,"id":25,"area":83228},{"iscrowd":0,"image_id":5,"bbox":[199.48717948717945,602.5128205128204,664.1025641025642,258.974358974359],"segmentation":[[199,605,204,851,863,861,861,602]],"category_id":1,"id":26,"area":166742},{"iscrowd":0,"image_id":5,"bbox":[58.46153846153845,879.4358974358975,969.2307692307692,123.07692307692298],"segmentation":[[61,879,58,1002,1025,1002,1027,882]],"category_id":0,"id":27,"area":117738},{"iscrowd":0,"image_id":5,"bbox":[263.58974358974353,1002.5128205128204,551.2820512820514,266.66666666666663],"segmentation":[[263,1005,271,1269,814,1264,814,1002]],"category_id":1,"id":28,"area":143892},{"iscrowd":0,"image_id":5,"bbox":[68.71794871794873,1256.3589743589744,964.102564102564,258.9743589743589],"segmentation":[[68,1276,71,1502,1032,1515,1030,1256]],"category_id":1,"id":29,"area":232998}],"categories":[{"id":0,"name":"text","supercategory":"text"},{"id":1,"name":"figure","supercategory":"figure"},{"id":2,"name":"table","supercategory":"table"}]}
@an1018 my single image json file formate from labelme tool is
{ "version": "3.16.7", "flags": {}, "shapes": [ { "label": "text", "line_color": null, "fill_color": null, "points": [ [ 35.38461538461536, 105.07692307692307 ], [ 35.38461538461536, 264.05128205128204 ], [ 514.8717948717949, 261.4871794871795 ], [ 514.8717948717949, 105.07692307692307 ] ], "shape_type": "polygon", "flags": {} }, { "label": "table", "line_color": null, "fill_color": null, "points": [ [ 514.8717948717949, 105.07692307692307 ], [ 1130.2564102564102, 110.2051282051282 ], [ 1122.5641025641025, 284.56410256410254 ], [ 520.0, 264.05128205128204 ] ], "shape_type": "polygon", "flags": {} }, { "label": "text", "line_color": null, "fill_color": null, "points": [ [ 35.38461538461536, 294.8205128205128 ], [ 1114.871794871795, 307.64102564102564 ], [ 1109.7435897435896, 830.7179487179487 ], [ 30.256410256410277, 825.5897435897435 ] ], "shape_type": "polygon", "flags": {} }, { "label": "figure", "line_color": null, "fill_color": null, "points": [ [ 258.46153846153845, 840.9743589743589 ], [ 268.71794871794873, 1192.2564102564102 ], [ 894.3589743589744, 1199.948717948718 ], [ 899.4871794871794, 843.5384615384615 ] ], "shape_type": "polygon", "flags": {} }, { "label": "text", "line_color": null, "fill_color": null, "points": [ [ 86.66666666666663, 1207.6410256410256 ], [ 89.23076923076917, 1302.5128205128206 ], [ 1089.2307692307693, 1305.076923076923 ], [ 1084.102564102564, 1223.0256410256409 ] ], "shape_type": "polygon", "flags": {} }, { "label": "figure", "line_color": null, "fill_color": null, "points": [ [ 158.46153846153845, 1282.0 ], [ 171.28205128205127, 1548.6666666666665 ], [ 925.1282051282051, 1569.179487179487 ], [ 922.5641025641025, 1312.7692307692307 ] ], "shape_type": "polygon", "flags": {} }, { "label": "text", "line_color": null, "fill_color": null, "points": [ [ 89.23076923076917, 1548.6666666666665 ], [ 89.23076923076917, 1620.4615384615383 ], [ 1091.7948717948718, 1630.7179487179487 ], [ 1089.2307692307693, 1553.7948717948718 ] ], "shape_type": "polygon", "flags": {} } ], "lineColor": [ 0, 255, 0, 128 ], "fillColor": [ 255, 0, 0, 128 ], "imagePath": "Tu_page-0001.jpg", "Someting long key here" "imageHeight": 1650, "imageWidth": 1275 }
Is it normal to train with your own dataset? and did you test your model before export?
@an1018 in output dir below image save while infer
@an1018 while training in last i got
Accumulating evaluation results... DONE (t=0.02s). Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000 [01/16 12:33:12] ppdet.engine INFO: Total sample number: 3, average FPS: 1.5615825421222556 [01/16 12:33:12] ppdet.engine INFO: Best test bbox ap is 0.000. [01/16 12:33:12] ppdet.utils.checkpoint INFO: Save checkpoint: output/picodet_lcnet_x1_0_layout
您可以尝试安装 PaddlePaddle 2.3
我也是报这个错误,版本2.4换成2.3还是不行
用自己的数据集训练正常吗?你在出口前测试过你的模型吗?
#测试版面分析结果
!python3 PaddleDetection/tools/infer.py \
-c ./picodet_lcnet_x1_0_layout.yml \
-o weights='output/picodet_lcnet_x1_0_layout/best_model.pdparams' \
--infer_img='data/images/123.png' \
--output_dir=output_dir/ \
--draw_threshold=0.5
用自己的数据集训练正常吗?你在出门前测试过你的模型吗?
#生成训练集合测试集
!python label_studio.py \
--label_studio_file ./datasets/label.json \
--save_dir ./datasets \
--splits 0.8 0.2 0\
--task_type ext \
--layout_analysis True
我在layout_analysis True用我自己训练版面模型时报了
ValueError: (InvalidArgument) The conv2d Op's Input Variable Input
contains uninitialized Tensor.
[Hint: Expected t->IsInitialized() == true, but received t->IsInitialized():0 != true:1.] (at /paddle/paddle/fluid/framework/operator.cc:2411)
[operator < conv2d > error]
@1061302569 yes the version 2.4 is changed to 2.3 still not solved what is the minimum number of data required to train a layout model currently i am doing finetune on 10 dataset "Is it a problem due to less number of of data? in how many data you train your model?
@1061302569 yes the version 2.4 is changed to 2.3 still not solved what is the minimum number of data required to train a layout model currently i am doing finetune on 10 dataset "Is it a problem due to less number of of data? in how many data you train your model?
It should not be the reason for the small data set. At the beginning, I also used 10 pictures for training. Now I increase the data set to 100 pictures. This error is still the same.
@1061302569 @an1018 "Is it a problem due to image size? my images size is like "imageHeight": 1650, "imageWidth": 1275 ? In .yml file image_shape: [1, 3, 800, 608] is mention. Shall we maintain this size while training?
@1061302569 Did you solve this issue?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.
i am facing this issue when i use inference.pdiparams, inference.pdiparams.info ,inference.pdmodel models for layout analysis.
ValueError: (InvalidArgument) The conv2d Op's Input Variable Input contains uninitialized Tensor. [Hint: Expected t->IsInitialized() == true, but received t->IsInitialized():0 != true:1.] (at /paddle/paddle/fluid/framework/operator.cc:2094) [operator < conv2d > error]