-
I0728 17:38:33.145712 108486 train_shadownet.py:577] Use single gpu to train the model
(32, 32, 280, 1) SparseTensor(indices=Tensor("DeserializeSparse:0", shape=(?, 2), dtype=int64), values=Tensor("D…
LXLun updated
5 years ago
-
hey
i want to use this project to create a model for the arabic language so i wonder can these two files be automatically generated? if yes how ?
thanks in advance
-
Hi @novioleo ,
for every validation during training, it keeps saying "target_lengths must be of size batch_size". I am trying to train using batch size of 4 using ICDAR2015 data set. Hope you could h…
ongcj updated
5 years ago
-
@MaybeShewill-CV thank you for your code.
I have error. { "error": "Serving signature name: \"serving_default\" not found in signature def" }
How can I solve?
----- script -----------
```…
-
Hi,
I've read about CRNN net papers for word-spotting, they reported really good result. Does Mlpack support Multi-Dim RNN like Bi-LSTM or MD-LSTM and CTC layers in order to build CRNN ?
I saw tha…
-
@MaybeShewill-CV, I am training Korean, and I got 4 errors. What should I do?
1.AttributeError: module 'tensorflow' has no attribute 'data'
So, I changed to tf.contrib.data.
(I referred to this…
-
I am not clear about how the methods ' labels_to_graph, forward_backward' work and or how they are related to CTC. The doc is too short for a beginner.
I guess the input to 'labels_to_graph' is an …
-
Hi Holmeyoung,
I have 20,000 training samples and 30 characters. I have been trying to train the model but the accuracy does not add up. How should I set the parameters?
-
I am training crnn.pytorch (https://github.com/meijieru/crnn.pytorch) to recognize handwritten characters. The training loss does not decrease and the predictions are all blank characters. The warpctc…
guilk updated
5 years ago
-
你好，我想请问下，论文模型的训练数据集如果是synth90k的话，这个数据只包含字母/数字，不包含标点符号。那么在进行测试时，比如ICDAR15这种带标点符号的数据集，你们是如何测试的呢？
是忽略标点符号来计算准确率，还是说就按照正常的来计算呢，因为这样训练的模型没有标点符号的类，肯定预测不出标点符号。