Jessespace
Jessespace
When I run "**python experiments/dff_rfcn/dff_rfcn_end2end_train_test.py --cfg experiments/dff_rfcn/cfgs/resnet_v1_101_flownet_imagenet_vid_rfcn_end2end_ohem.yaml**", it generator **xxx.log** in **output/**,It was been running for a while, but occurred this problem: `by cudnn, MXNET convolution is applied. Traceback (most...
After i read the codes,I found that Train Deep Feature Flow trained on DET and VID (30 classes). Now,I want to train the net on dataset of 2 classes. I...
I run the **demo.py**. It generates the result.But When I combined all frames into video.It is out of order.Why? Thanks for your help.
Can you provide some advice about how to adjusting **hyper-parameters** in **object detection**? 1) I have tried the ssd algorithm ,and got 90% mAP,but it's difficult to further improve. 2)...
How to output the accuracy of a single input video??
When I run "**cnn_ucf101_spatial.m**",I got this: `**error dagnn.Layer/load (line 191) obj.(f) = s.(f) error dagnn.DagNN.loadobj (line 27) block.load(struct(s.layers(l).block)) ; error cnn_ucf101_spatial (line 112) net = dagnn.DagNN.loadobj(net);** ` How can i...
I have questions about the input of images.I have researched the code, found that just random crop 16 images from a video as input. And the other frames just throw...
**I have changed test_segments and test_crops to 2,but I still get the error "out of memory".Hope you can help me,thx!** Hardware Configuration: GPU: GTX1080TI 11G CPU: 16G `Initializing TSN with...
I have run through the program and replaced it with my own data set. But I can only output the accuracy of the training set and the test set. if...
I tryied the **GAN** network following "gan-intro.ipynb".About 100epochs,the accuracy is around **50%**. I can understand that,because the **GENERATOR** network can't devide the true data and the fake one. But when...