-
is lxml and libxml2 and libxslt installed in the docker image. I have them installed on my base image but this provider fails to produce results could also be that this needs to be updated since there…
-
Hi, @jshtok ,
When I try to reproduce the VOC experiment, I used the new 'resnet_v1_101_voc0712_trainval_fpn_dcn_oneshot_end2end_ohem_8_orig.yaml' file and I changed the dataset to VOC. I use the 'py…
-
With a series of file index mismatch problems in your code-file "train_faster_rcnn.sh" being debugged.
I successfully got to the following running process:
'"
+ python ./tools/trainval_net.py --wei…
-
Hi all,
Does anyone know how easy it would be to modify the data layer portion of the code to accept images with more than 3 channels? I'm doing some experiments where I have imagery that is composed …
-
There is a few times meeting this error when the train is in 18th or 19th iter.
At the first time, I thought it was maybe caused by a big learning rate.
But when I changed it from 0.01 to 0.001, it…
-
Whenever I modify the config file to add my imgur ID and an IMDB button (straight from the example provided minus me changing it to MY actual imgur ID) and save it, when I start the script again to re…
-
Hi everyone:
I want to train Faster R-CNN on my own dataset. Because Faster R-CNN does not use selective search method, I comment the code about selective. However, there are still some errors ab…
-
Hi yu4u,
I want to train the network with 128 image size. (40k images)
However, the lost reduce stop at 24 (at 20 epochs) and then it doesn't decrease anymore. I've tried with adam, sgd, rmsprop. …
-
Hi,I am trying to implement LIT on a sentiment model based on imdb dataset in classification.py file. I am not get predictions,on running.
`import os
from absl import app
from absl import flags
…
-
### Description of the new feature / enhancement
## Mimicing Alfred
I would like functionality that mimic some of what [Alfred](https://www.alfredapp.com/) can do.
### Feature 1: Separate `find…