4 open source projects by v-iashin

PyTorch/Tensorflow solutions for Stanford's CS231n: "CNNs for Visual Recognition"

✭ 47

Jupyter Notebook machine-learning computer-vision deep-learning neural-network solutions tensorflow numpy jupyter-notebook stanford-university assignment pytorch recurrent-neural-networks lstm generative-adversarial-network style-transfer convolutional-neural-networks backpropagation svm-classifier adam-optimizer sgd-optimizer

2. WebsiteYOLO

The back-end for the YOLOv3 object detector running as a webapp

✭ 26

python shell flask pytorch webapp yolo object-detection yolov3

3. video features

Extract video features from raw videos using multiple GPUs. We support RAFT and PWC flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, ResNet features.

✭ 225

python Dockerfile windows raft audio-features parallel pytorch feature-extraction resnet optical-flow clip multi-gpu i3d s3d video-features vggish pwc-net r2plus1d visual-features ig65m

4. BMT

Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)

✭ 192

python Jupyter Notebook shell audio video pytorch transformer temporal-action-proposals i3d video-features dense-video-captioning multimodal-fusion activitynet-captions bmvc bmt bmvc20 bi-modal-transformer proposal-generator bi-modal-encoder