wendell_yi

three is some errors on the below: please input file name:1755.jpg text_recs: [((16.0, 768.6111), (159.0, 790.30804)), ((48.0, 579.4411), (511.0, 690.03076)), ((528.0, 790.0657), (591.0, 800.4505))] rec: ((16.0, 768.6111), (159.0, 790.30804)) pt1:...

the result is change when i freezed the ckpt?why?

3

@eragonruan @banjin-xjy @liuheng92 @skye hai,when i use :python3 freeze_graph.py --input_meta_graph=ctpn_50000.ckpt.meta --input_checkpoint=ctpn_50000.ckpt --output_node_names=model_0/cls_prob,model_0/Reshape_5 --output_graph=CT_Original.pb --clear_devices=True --input_binary=True And,i run this model ,some thing have changed like below: the same model(ckpt && frozen.pb)...

the output from feeezed model have changed?why?

3

**i freezed like this**: if __name__ == '__main__': checkpoints_path=r'/home/luwei/ML/model_sdk/opencvTest/temp/text-detection-ctpn-banjin-dev/model/checkpoints_mlt' meta_path =r'/home/luwei/ML/model_sdk/opencvTest/temp/text-detection-ctpn-banjin-dev/model/checkpoints_mlt/ctpn_50000.ckpt.meta' # init session config = tf.ConfigProto(allow_soft_placement=True) sess = tf.Session(config=config) saver = tf.train.import_meta_graph(meta_path) try: ckpt = tf.train.get_checkpoint_state(checkpoints_path) #ckpt=tf.train.get_checkpoint_state("output/ctpn_end2end/voc_2007_trainval/") print('Restoring from...

Not find the "from shapely.geometry import box, Polygon",in eval_multiscale.py and eval_all.py？

2

from shapely.geometry import box, Polygon isn't exist?

ERROR in D:\CV\tool\PaddleJs2.1.0\PaddleJs2.1.0\packages\paddlejs-models\humanseg\src\index.ts 5:28-53 [tsl] ERROR in D:\CV\tool\PaddleJs2.1.0\PaddleJs2.1.0\packages\paddlejs-models\humanseg\src\index.ts(5,29) TS2307: Cannot find module '@paddlejs/paddlejs-core' or its corresponding type declarations. 

系统：windwos nodejs版本：v12.22.12 32位 错误详细信息： [webpack-cli] Invalid configuration object. Webpack has been initialized using a configuration object that does not match the API schema. - configuration.node has an unknown property 'fs'....

ERROR：0xC00000FD: Stack overflow

2

python out: Loaded speechmetrics.relative.nb_pesq Loaded speechmetrics.relative.pesq Loaded speechmetrics.relative.sisdr Loaded speechmetrics.relative.stoi vs dubeg it: 0x00007FFD86C9FA07 (pesq_core.cp38-win_amd64.pyd) (python.exe 中)处有未经处理的异常: 0xC00000FD: Stack overflow (参数: 0x0000000000000001, 0x000000C2BF203000)。

there is some error on the bellow: python3 reco_chars.py [libprotobuf ERROR google/protobuf/text_format.cc:274] Error parsing text-format caffe.NetParameter: 6:15: Message type "caffe.LayerParameter" has no field named "input_param". WARNING: Logging before InitGoogleLogging() is...

IOS中flycv读取图片时报错：Rebuild fcv with libjpeg-turbo! 和Input Mat of resize is empty!

2

IOS中使用flycv和opencv的静态库,flycv读取图片时报错：Rebuild fcv with libjpeg-turbo! 和Input Mat of resize is empty! flycv的版本：IOS flycv-v1.1.0-ios.tar 在flycv的库里查到了jpg的支持符号如下：