AlexTS1980 issues

Results 26 issues of


AlexTS1980

Image classification

Did you try extending instance segmentation to global (image/video) classification, i.e. predict the class of the image from segmented instances?

IncompatibleKeys(missing_keys=[], unexpected_keys=[]) for FCN32

I loaded FCN32s, downloaded the pre-trained weights and tried to load them into the model: ``` from model = FCN32s() import FCN32s model.load_state_dict(torch.load('fcn32s_from_caffe.pth')) output = model(input) ``` Keep getting this...

help wanted

Mean vector

In the code ``` #PIL reads image in the form of RGB, while cv2 reads image in the form of BGR, mean_vec = [R,G,B] mean_vec = np.array([123.68, 116.779, 103.939], dtype=np.float32)...

CRFasRNN output vs score_final (FCN)

I'm training CRFasRNN layer on top of upsampled score_final layer similar to that in FCN8s on my data, and I quickly noticed that the output from CRF-RNN is not very...

Feature extraction from CRF-RNN vs FCN8s

I've been extracting features from CRF-RNN and FCN8s, and I noticed one weird thing: When I extract features: ``` feats = net.forward(end='fc7', **{'data': caffe_in}) feats = feats['fc7'][0] ``` Features from...

crf-rn demo vs trained algorithm

I've processed the same image through the demo (http://www.robots.ox.ac.uk/~szheng/crfasrnndemo/classify_upload) and the installed trained classifier (TVG_CRFRNN_COCO_VOC.prototxt), and I get very different results (the ones on he website are way better). An...

Is CuDNN 5 supported?

Is CuDNN 5 supported? I installed vanilla caffe w/out any problem, but crf-rnn caffe keeps telling me ./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::createPoolingDesc(cudnnPoolingStruct**, caffe::PoolingParameter_PoolMethod, cudnnPoolingMode_t*, int, int, int, int, int, int)’:...

AlexTS1980