-
@AlexeyAB Thanks very much for your `darknet.py`. Here, i have a question, how to only output prediction result of `darknet.py`?
For example:
The output of my prediction by invoke `python3 dark…
-
I have trained the SSD7 for my own custom data (same format as udacity dataset including number of same number of class) where prediction results are horrible. The training data size is 8K and validat…
-
hello, how can i achieve same results on your official website? The current training results are not continuous in time. Can you help me? what should I do？ Looking forward to your reply. thx
-
-
I want to know if is possible to know the duration of each char or word in this model's output?
or the alignment of each char or word.
-
Refactor (initially, just add another `mc` service for testing) such that we don't need separate code for CPU and GPU reweighted-MC analysis.
Note that one current issue with the GPU code (and prob…
-
Dear all,
I am wondering how to implement one-shot learning in DeepChem? since I have low amount of data at hand.
In the "Low Data Drug Discovery with One-Shot Learning" paper, if I am correct, …
-
Hello!
I am trying to implement FlowNet network from this paper
FlowNet: Learning Optical Flow with Convolutional Networks, ICCV 2015.
The authors propose to use two different modules in the network…
-
I'm confused about the reshape in these two place. Any suggestion will be appreciated.
-
### Issue summary
There seems something weird when I'm trying to see the output activation from the first conv layer. I'm getting negative values as activations after ReLU.
### Steps to reproduce
…