-
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…
-
I am training a CRNN model in pytorch
max_seq_length=99
number_of_alphabets=96
batch_size=16
output=CRNN(image)
what should be the expected shape of output?
Secondly, should we apply softmax in …
-
在制作lmdb时，tolmdb.py 28行 报错：
TypeError: Won't implicitly convert Unicode to bytes; use .encode()
25 def writeCache(env, cache):
26 with env.begin(write=True) as txn:
27 for k, v in …
-
32核服务器
num_workers为2的时候，cpu占用率1600%，100batch平均21s
num_workers为0的时候，cpu占用率1300%，100batch平均29s
你们的也是如此吗？
-
Hi ,
I'm getting the below error while running the predict function.
(User) C:\Jagadesh\529\CRNN_OCR_lite>python predict.py --G 0 --model_path C:\Jagadesh\529\CRNN_OCR_lite\models\OCR_IAM_v…
-
LXLun updated
5 years ago
-
Hello ,
i tried to re-tain the model using the English dataset (synth90k), after converting the data to the tensorflow records and after launching the training , i got this message :
```
I0701…
-
使用crnn-mxnet的Synthetic Chinese Dataset样本，执行
python ./cnocr-master/scripts/cnocr_train.py --loss ctc --dataset cn_ocr --data_root ./data/images --train_file ./data/train.txt --test_file ./data/test.tx…
-
Hello :+1:
How to speed up inference with batch images input ?
When I use test_shadownet.py to inference image , it only can take one image per time , when the image size changed , I have t…
-
1.ctc模型预测报错：
Traceback (most recent call last):
File "infer.py", line 153, in
main()
File "infer.py", line 149, in main
inference(args)
File "infer.py", line 34, in inference
…