-
有没有可能做到零样本（ZSL），就是直接通过part的state然后推到出新的action，不在这600类中。也就是说比如我手里有新的数据不属于这600类，而且没有标注训练集。
-
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1844: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`…
-
$ python preprocessing/crawl_descriptions.py
person 1000
0 []
bicycle 1000
0 []
car 1000
0 []
motorbike 1000
0 []
aeroplane 1000
0 []
...
Is this result normal? How to solve it?Looking for…
-
Hi, I just want to test the captioning result on some raw images. I have read the **vlp/decode_img2txt.py**, but the settings are a little bit complicated for me, for example, the standard size of an …
-
A sophisticated alternative to human labor (#1) for syncing new and old episodes would be to use an automated algorithm executed weekly:
1. Download the podcast audio file.
2. Download the YouTube v…
-
When will someone use TimeDistributedDense? Is it only to reduce training data set? Does it have other benefit?
Why is TimeDistributedDense after RNN/LSTM/GRU? Shouldn't it be before? For example, if…
-
Thanks for your released code. The code is well-structured, I replaced the dataloader with my own implemention and it still works well. But I still got some issues.
I've trained the SAT and BUTD m…
-
I am trying to train the model as the per the instructions given on the repo. I am getting below error:
`[gsrivastava@default-home-gsrivastava-weietgweso self-critical.pytorch]$ python tools/train.…
-
Right now it's some stock icon of an input IIRC.
-
Hi. Thanks for your code.
1- May I ask why are you including the start and end token when constructing the caption? Since you want to encode the caption only, there is no need for it. As far as I kno…