litingfeng
litingfeng
@michaelku1 Are you implying that only registering functions (in datasets.builtin.py and cityscapes_foggy.py) need to be changed? If not, which else need to be modified? Sorry I'm not that familiar with...
@michaelku1 Thank you so much for the detailed answer! This is very helpful! 👍
Install previous version solved this problem for me: `python -m pip install 'git+https://github.com/facebookresearch/[email protected]'`
@abhineet123 Did you mean that [](url) is the input of target RNN(O) and score is the output? But in Figure 2. , [](url) is the output of fc layer following...
@abhineet123 I think I can understand it now. Thank you very much for your elaborate explanation.
Hi, I have another question here about Figure 3. In the second paragraph on page 4( section 3.2), [](url) is a 500-D vector, [](url) is a H-D vector, which is...
In summary, you mean that the 500-D vector of [](url) is the output of the feature extractor CNN with a 500 units of fc layer following a 128 units of...
@abhineet123 I am really grateful for your reply. Later I will ask the author for more details.
Hi, I asked the author but haven't received response yet. Here I have another question： do you know how to train the LSTM in this appearance model？ Is LSTM included...
I have a concern too. Here should we understand RECEPTIVE FIELD as the input size, rather than the real 'receptive field'? I think the default padding=1 in this case. Here...