-
报错信息是：NaN or Inf found in input tensor
此时的学习率已经调到0.0001，训练很慢了，但是还会出现NaN，请问该怎么处理这个问题？
-
I want to train the model on my own data for a specific use case. I have my dataset in ICDAR-FST2015 dataset format, but the thing is, the InputGenerator in crnn_data which is used for training the CR…
ghost updated
5 years ago
-
Start val
U => U , gt: MNOPQRSTUV
And all test accuracies are 0.
-
我在infer.py里加了
path = "./infer_model"
fluid.io.save_inference_model(dirname=path, feeded_var_names=['pixel'],target_vars=[ids])
load运行后报错如下
 kspook@MLNC6:/usr/local/cuda/samples/bin/x86_64/linux/release$ nvidia-smi
Thu Jul 4 11:00:00 2019
+--------------------…
-
attention ocr 采用train.py训练和保存模型, 运行infer.py时不能顺利加载模型; 控制台打印的信息如下:
/usr/bin/python3.5 /home/liusong/program_install/pycharm-2018.3.4/helpers/pydev/pydevd.py --multiproc --qt-support=auto --client 12…
-
我运行了OCR模型，有如下错误信息，请问如何修改。说明一下，train.py改名为testtx3.py, 放到了E:\paddletest目录下，其他文件也复制过来，运行python testtx3.py,以下就是错误信息，文件train.py中只把use_cube改为False,其他没改。我的paddlepaddle是1.4.1版本，python是3.7.1版本。
--------------…
-
I want to train with my own dataset. First I used the create_dataset.py and it created two files- data.mdb and lock.mdb.
Now i gave the same path of data.mdb to train and validate. If this is not rig…
-
RuntimeError: Error(s) in loading state_dict for CRNN:
size mismatch for rnn.1.embedding.bias: copying a param of torch.Size([19997]) from checkpoint, where the shape is torch.Size([6736]) in curren…