rubencart
rubencart
Like in https://github.com/tylin/coco-caption/issues/22#issue-231528122 , I got ``` OSError: [Errno 2] No such file or directory: 'java' ``` When running the evaluation, even with java definitely installed. This SO discusses it:...
`output` gives `tensor([[-1.5800e-01, ... 1.1632e-01]], grad_fn=)` `target` gives `tensor([10, 29, 14, 73, 96, 55, ..., 94])` `target[c]` gives `tensor(10)` So `criterion(output, target[c])` gives `RuntimeError: dimension specified as 0 but tensor...
Results from training an FC model with self-critical RL on 1 single GPU with batch_size 32. Output from training script, before change: ``` iter 50 (epoch 0), avg_reward = 0.001,...
Hi, In your picture [here](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/image_captioning/png/image_captioning.png) the output of the LSTM at the 1st timestep (when the input is the image feature vector) is "\", which is then fed back into...
When I try to debug the following main.cpp in CLion with the platformio.ini listed below, I get the error below, and the debugger stops. main.cpp: ``` #include static int solenoidPin...
Is it possible to specify which configuration file to load in an argument? So instead of: ```python class Args(Tap): arg1: int arg2: str args = Args(config_files=['my_config.txt']).parse_args() ``` Something like this:...
Hi, It is not entirely clear to me how you guys handle elitism. In your paper ([link](https://arxiv.org/abs/1712.06567)) you mention "The Nth individual is an **unmodified** copy of the best individual...
### Current Behavior When I search metrics (that are being logged) in the 'Manage Columns' dialog box in the web app Table view, metrics matching my search query briefly appear,...
**Description** [You documentation](https://docs.wandb.ai/library/log#matplotlib) says "You can pass a matplotlib pyplot or figure object to `wandb.log()`". However, when I do this, at the moment of the commit, I get the following...
## Instructions To Reproduce the Issue We extracted features of the COCO train2017 split with the `detectron2_mscoco_proposal_maxnms.py` script. This completed without errors. Afterwards we try to read in the features...