-
hey，hengruo! I've got a question to consult you~
char_dim = 64 #Embedding dimension for char
In the paper of QANet, the auther stated ' Each character is represented as a trainable vector of dimensi…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### which package/s did you face the problem with?
Dashboard
### What happened?
3 of us tried going th…
-
Thank you for your implementation, it is very helpful for me.
I run this code and can get the similar result when the number of heads equals to 1. But, I cannot get the result of original paper(73.6/…
-
## Description
class ExponentialMovingAverage
in train.py the ema use two position:
if global_step == 1:
for name, param in model.collect_params().items():
ema.add(…
rrjia updated
3 years ago
-
hello，when i ran this code for training，i get the index error.
i convinced the code is right,could you tell me your environment and the version ?
thank u!!
-
while running examples, I tried to deploy on Devnet and Qanet and it showed this strange error
-
## ❓ Questions and Help
$python tools/train_net.py --config-file "configs/caffe2/e2e_mask_rcnn_R_50_FPN_1x_caffe2.yaml"
I checked the image width and height in my annotation file I don't have the…
-
Why I resume the checkpoint to continue training, the loss is normal but the test result of new epoch is very low like the first epoch?
For example, when I have trained the model for 10 epochs. And t…
-
Hello! I've found a performance issue in /MRC: `batch()` should be called before `map()`, which could make your program more efficient. Here is [the tensorflow document](https://tensorflow.google.cn/g…
-
Thank you for sharing your wonderful works.
I wonder whether I could find back translation code for data augmentation!
Does it contain in this repository?
I'm waiting for your reply, thanks.