C3D

C3D copied to clipboard

Low acc using extract_image_features.bin of v1.1

2

Hi, I use v1.0 extract_image_features.bin to extract prob and get the same accuracy (39%) as the test.bin (40%). But I get much lower accuracy (11%) than the test.bin (39%) when...

sherleens

Error while compiling

9

I modified the Makefileconfig file to work with CPU, when i try and run make, I get the following error : .build_release/lib/libcaffe.so: undefined reference to `cv::VideoCapture::set(int, double)' .build_release/lib/libcaffe.so: undefined reference...

kousik97

question about compute volume mean

16

when I run the create_volume_mean.sh ,the following question is: I0217 20:11:32.672004 19663 compute_volume_mean_from_list.cpp:53] using dropping rate 10 I0217 20:11:32.695142 19663 compute_volume_mean_from_list.cpp:80] Starting Iteration F0217 20:11:33.270965 19663 compute_volume_mean_from_list.cpp:92] Check failed: size_in_datum...

sophiazy

Loss is so high when using SIGMOID_CROSS_ENTROPY_LOSS or EUCLIDEAN_LOSS

4

Hi, I want to predict saliency values of a voxel, using V2V. The output and truth have 1 channel, and the truth has labels 0 and 1. The model is...

ltnghia

In voxel_wise_softmax_layer.cpp line 66, I think the index of scale_data `scale_data[bottom[0]->offset(i,0,l,h,w)]` should be `scale_data[scale_.offset(i,0,l,h,w)]`

iannnn

OpenCV versions support

2

Added support to OpenCV v3 to avoid some version conflict when running the scripts calling it

mlakhal

About extracting features on UCF101, by using C3D model fine­tuned on UCF101

2

Question 1: I am confused about the different names of fc layers in the prototxt files, for different models training on different dataset. I follow the user guide to fine­tune...

misunusc

shuffle and batch size option in test process affect classification probability and accuracy

2

I found something weird about testing pre-trained c3d-resnet model(trained on ucf101) while changing the shuffle and batch size option in the test process. when I tested the model with shuffle...

sainisanjay

Does VIDEO_SEGMENTATION_DATA data format still exist for v1.1？

1

Does VIDEO_SEGMENTATION_DATA data format still exist for v1.1？

bityangke

Upgrade Deconv3D for C3D-v.1.1

6

Hi, Thanks for release C3D-v.1.1. Could you please upgrade Deconv3D and VideoWithVoxelTruth_data layers to v-1.1 ? I tried to convert Deconv3D layer from v-1.0 to v-1.1 but it doesn't work....

ltnghia