-
I have compiled the code & looks like it went smoothly without errors & only warning signs of unused variables. However, when I tried to run the demo.py, I've been given an Import error message of inv…
-
When I run test_net.py, I encounter CUDA memory related …
-
A user reports that container restarts lead to duplicated responses. For example, after a restart, `.weather xxx` responds twice. After another restart, `.weather xxx` responds three times.
Unfortu…
-
I want train the p net with cpu cause I have compiled the mxnet with cpu(unable cuda). but when I run "python -u ./example/train_P_net.py --gpu=-1", ther are lots errors as follow:
`mtcnn_train_12 gt…
-
The new structure for TraktForVLC 2.x includes a Lua VLC module that will take care of following what is happening on the VLC side, while a helper Python script is provided to perform all the tasks th…
-
First of all: this is awesome!
However, the auto-created quotes are usually very short and only provide one camera perspective. It might be a good idea to source IMDB for multi-line quotes, fuzzy-mat…
ge0rg updated
6 years ago
-
```
Moreover, We observe that the tracking performance of saved models in different epochs varies considerably, therefore, you may want to evaluate a few more models instead of just picking the model…
-
Hello , How execute this porjet https://github.com/smallcorgi/Faster-RCNN_TF without GPU ?
ghost updated
7 years ago
-
Hi,when I use ckpt v1 format,the command line as follows,
python ./faster_rcnn/test_net.py --gpu 0 --weights ./models/VGGnet_fast_rcnn_iter_150000.ckpt --imdb voc_2007_test --cfg ./experiments/cfgs/f…
ygren updated
5 years ago
-
Hi,
Batch size cannot be above 22 when I do use fairseq to do fine-tuning. I set the batch size as 64, but the actual batch size is below 22.
Here is the script.
TOTAL_NUM_UPDATES=7812 # 10…