Giri Giribushan
Giribushan
/ decodes, _ = tf.nn.ctc_beam_search_decoder(inputs=net_out, sequence_length=25*np.ones(4), merge_repeated=False)
Created
January 20, 2019 22:08
CTC error for a wrong batch_size (expected - 2 , given - 4)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Caused by op u'CTCBeamSearchDecoder', defined at: | |
| File "tools/export_crnn_model_script.py", line 266, in <module> | |
| recognize(image_path=args.image_path, weights_path=args.weights_path) | |
| File "tools/export_crnn_model_script.py", line 136, in recognize | |
| decodes, _ = tf.nn.ctc_beam_search_decoder(inputs=net_out, sequence_length=25*np.ones(4), merge_repeated=False) | |
| File "/home/sathish/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/ctc_ops.py", line 277, in ctc_beam_search_decoder | |
| merge_repeated=merge_repeated)) | |
| File "/home/sathish/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/gen_ctc_ops.py", line 73, in ctc_beam_search_decoder | |
| top_paths=top_paths, merge_repeated=merge_repeated, name=name) | |
| File "/home/sathish/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper |
Giribushan
/ decodes, _ = tf.nn.ctc_beam_search_decoder(inputs=net_out, sequence_length=25*np.ones(None), merge_repeated=False)
Created
January 20, 2019 22:05
CTC Error
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| File "tools/export_crnn_model_script.py", line 136, in recognize | |
| decodes, _ = tf.nn.ctc_beam_search_decoder(inputs=net_out, sequence_length=25*np.ones(None), merge_repeated=False) | |
| File "/home/sathish/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/ctc_ops.py", line 277, in ctc_beam_search_decoder | |
| merge_repeated=merge_repeated)) | |
| File "/home/sathish/anaconda2/lib/python2.7/site-packages/tensorflow/python/ops/gen_ctc_ops.py", line 73, in ctc_beam_search_decoder | |
| top_paths=top_paths, merge_repeated=merge_repeated, name=name) | |
| File "/home/sathish/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper | |
| op_def=op_def) | |
| File "/home/sathish/anaconda2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3392, in create_op | |
| op_def=op_def) |
Giribushan
/ Crnn Cloud
Created
July 23, 2018 23:51
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| File "C:\Users\gcheru200\git\CRNN_Tensorflow\call_cloud_service.py", line 59, in <module> | |
| predict_json(PROJECT_ID, MODEL_NAME, instances = INPUT_DATA_FILE, version=VERSION_NAME) | |
| File "C:\Users\gcheru200\git\CRNN_Tensorflow\call_cloud_service.py", line 54, in predict_json | |
| raise RuntimeError(response['error']) | |
| RuntimeError: Prediction failed: Error during model execution: AbortionError(code=StatusCode.INVALID_ARGUMENT, details="NodeDef mentions attr 'dilations' not in Op<name=Conv2D; signature=input:T, filter:T -> output:T; attr=T:type,allowed=[DT_HALF, DT_FLOAT, DT_DOUBLE]; attr=strides:list(int); attr=use_cudnn_on_gpu:bool,default=true; attr=padding:string,allowed=["SAME", "VALID"]; attr=data_format:string,default="NHWC",allowed=["NHWC", "NCHW"]>; NodeDef: shadow/conv1/Conv2D = Conv2D[T=DT_FLOAT, _output_shapes=[[1,32,100,64]], data_format="NHWC", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/cpu:0"](Reshape, shadow/co |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| sathish@sathish-linux-deep:~/gitRepos/OCR/CRNN_Tensorflow$ python3 tools/train_shadownet.py --dataset_dir /home/sathish/gitRepos/OCR/datasets/SynthText/SynthText/tfrecords_dir/ | |
| /usr/local/lib/python3.5/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. | |
| from ._conv import register_converters as _register_converters | |
| The dict_path - /home/sathish/gitRepos/OCR/CRNN_Tensorflow/data/char_dict/char_dict.json | |
| The dict_path - /home/sathish/gitRepos/OCR/CRNN_Tensorflow/data/char_dict/char_dict.json | |
| The labels read - SparseTensor(indices=Tensor("ParseSingleExample/ParseSingleExample:0", shape=(?, 1), dtype=int64), values=Tensor("Cast:0", shape=(?,), dtype=int32), dense_shape=Tensor("ParseSingleExample/ParseSingleExample:2", shape=(1,), dtype=int64)) | |
| The image names - Tensor("ParseSingleExample/ParseSingleExample:3", shape=(1,), dtype=string) | |
| 2018-06-29 |
Giribushan
/ This is how FPN is built
Created
December 17, 2017 10:06
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def build_pyramid(net_name, end_points, bilinear=True): | |
| """build pyramid features from a typical network, | |
| assume each stage is 2 time larger than its top feature | |
| Returns: | |
| returns several endpoints | |
| """ | |
| pyramid = {} | |
| if isinstance(net_name, str): | |
| pyramid_map = _networks_map[net_name] | |
| else: |