huntkao
huntkao
Matlab returns error when executes the command "mat2obj('%s', '%s', %d);", matfilename, objfilename, isoval) generated in test.lua. How can I find the implementation of the mat2obj function, please? Thanks.
I used the pretrained model. The testing dataset is the default flyingthings3D TEST. After 'outputs = model(imgL, imgR)' I got len(outputs)=2 , which caused the line 'for x in range(stages):...
where and when preprocess_input() in places_utils.py be explicitly called?
examples/torch/classification/main.py outputs multiple times loading libcudart library. Is it possible the load being reduced to only once? Thanks. my log: ``` .... (omitted) to_onnx : compressed_model_accuracy_aware_sample.onnx weights : None workers...
In the test stage, the test dynamic frames are pre-processed using the exposure ratio determined by its corresponding long-exposure frame. The result seems fine. But for arbitrary scene, since we...
in train.py and pretrain_on_small.py, the following codes: ` vgg_fake1=build_vgg19(255*out_small[0:1,:,:,::-1], reuse=True) vgg_fake2=build_vgg19(255*out_small[1:2,:,:,::-1], reuse=True)` take the network's outputs as the RGB image input. Should not `out_small` be clipped or normalized to 0~255...
Could not find testing_fun() and testimage_dataloader() in the whole project when running Script_testing.py.
Thanks for share the implementation. When I use the model which was trained myself following the training step, my output images were quite bright (at ~30th epoch). Do you have...
Does the extrinsic calibration work for two horizontally layout cameras with only about 15% of overlap width?
First, thank you for the great work. I follow the pipeline for the tabletop dataset. Everything seems fine until failure raised at pool.map_async(process_sequence, paths.test_data_.get(9999999). After some check, I realize that...