vision


About the vision category (1)
Making a custom dataset (4)
Data Preprocessing for Tiny ImageNet (1)
Enforcing zeros values in CNN weights (1)
Using Cadene's pretrained model (10)
Object detection: how to pass the proposals of selective search to Detectron project? (2)
Multiplication of 4D and 3D creating linear comibnation (4)
Unable to install Pytorch or torchvision using conda (3)
What is the corresponding part of resnet101's "res4b22" in torchvision's pretrained model (2)
Need to create bounding box only when person is looking towards the camera (1)
RAM use monotonically increases (6)
AttributeError: 'str' object has no attribute 'size' (2)
Check pytorch version in google Colaboratory (2)
Batch norm behavior during test (4)
AttributeError: module 'torch.nn.init' has no attribute 'kaiming_normal_' (2)
Introduce a tool of PyTorch (6)
What does the star mark before list mean? (3)
Visualize live graph of lose and accuracy (8)
Concatenate layer output with additional input data (11)
Any PyTorch function can work as Keras' Timedistributed? (12)
Initialise weight for each layer using random values (7)
RunTime Error: RuntimeError: Given groups=1, weight of size [32, 1, 7, 7], expected input[1, 4, 110, 84] to have 1 channels, but got 4 channels instead (4)
TypeError: max_pool2d_with_indices(): argument 'input' (position 1) must be Tensor, not Sequential (3)
Will ‘torch.utils.data.DataLoader’ do normalization? (2)
Question about transposed convolution (2)
Apply transformations on a set of points (boundary box) (3)
RuntimeError: all tensors must be on devices[0] (1)
Training with Half Precision (12)
Weights copy code (3)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1. Got 8 and 4 in dimension 2 at /Users/soumith/code/builder/wheel/pytorch-src/aten/src/TH/generic/THTensorMath.cpp:3616 (4)