Goutham

Hi, I am getting the following error while importing caffe in the demo.ipynb. ImportError: libcudart.so.10.0: cannot open shared object file: No such file or directory. I am using cuda-10.0 and...

How can i get a sentence representation

4

Hi, Can you please tell me, how can I extract a single feature vector given a sentence in textual form or a list of word2vec vectors. Thanks

Hi, Can you please tell me how to get the test set question ids? Thanks

Hi, What are the 4 values in the bboxes represents?. Is it (x_c,y_c,w,h) or (x1,y1,x2,y2)?. Thanks

Hi, How can I get the split-wise (yes/no, number and others) accuracy during each epoch while fine-tuning for VQA.? Thanks

AttributeError: module 'model_zoo' has no attribute 'InceptionV3'

3

Hi, I am getting module model_zoo has no attribute InceptionV3 when I am running the test_video.py as mentioned. How can I resolve this? Thanks

Hi, How can I extract the mask attributes (such as color) along with the class label (e.g brown dog)? Thanks

Answer vocabulary

3

Hi, How the answer vocabulary is selected (for VQAv2, VQA-CPv2 and TDIUC)? Thanks

Feature Extraction

1

Hi, _p3d = P3D199(pretrained=True,num_classes=400,modality='RGB') modules=list(p3d.children())[:-2] nw_p3d=nn.Sequential(*modules) data=torch.autograd.Variable(torch.rand(10,3,16,224,224)) p3d_out=nw_p3d(data)_ I wrote the above code to extract video features. But it gave the error, **ValueError: Expected 4D tensor as input, got 5D...

Hi, The given segmentation data is a list of numbers. How can I visualize them? Thanks