omerbrandis

retried, failed again. ...$ git clone https://github.com/an-tao/drogon Cloning into 'drogon'... remote: Enumerating objects: 13861, done. remote: Counting objects: 100% (1118/1118), done. remote: Compressing objects: 100% (658/658), done. remote: Total 13861...

i also tried following trantor's installation instructions to "manually" install it under drogon/trantor. trantors build worked, but drogon's cmake failed with "You have called ADD_LIBRARY for library **trantor** without any...

I've tried git clone https://github.com/an-tao/drogon cd drogon rm -r trantor git clone https://github.com/an-tao/trantor cd trantor cmake -Bbuild -H. cd build make -j cd .. mkdir build cd build cmake -DCMAKE_BUILD_TYPE=Release...

tried the latest suggestion , hasn't solved the problem. still getting got : You have called ADD_LIBRARY for library drogon without any source files. This typically indicates a problem with...

hello , Has there been any progress with this? ( I've encountered same problem, i've created a custom dataset that inherits from coco in a mmdet/datasets/custom.py and refered to it...

hello , Can you please shed some light on how to change the loss function to focal-lossas suggested previously. in the config files I've noticed the following : loss_ins=dict( type='DiceLoss',...

Thank you very much Keisen, I'll try to follow these instructions. Omer.

Hello HungHY I encountered the same problem, have you managed to find a solution ? thanks, Omer

hi value of img_metas in SipMask/SipMask-benchmark/fcos_core/modeling/rpn/sipmask/inference.py", line 197 at runtime (prior to ori_shape = (img_metas[i][1],img_metas[i][0])) is None. omer.

I'm now trying with solver.IMS_PER_BATCH = 2. ( in the past i've seen issues with other maskRcnn_benchmark users , something about batch normalization requiring at least 2 images in order...