Connor Lee

CPU memory leak + cuDNN error when using the GPU with preprocess None

3

Two issues I've been running into when attempting to perform inference with the test.py script: 1. When running with GPU, with no preprocessing (i.e. input shape is size of input...

Where in the code should I modify to extract features from the topmost convolution layer of the vgg encoder?

Poly learning rate scheduler not doing anything

1

The poly learning rate doesn't work as intended. The current implementation is as follows: ``` def get_lr(self): if self.last_epoch % self.decay_iter or self.last_epoch % self.max_iter: return [base_lr for base_lr in...

Demo notebook fails at inferenceDetector

1

The demo notebook fails with a cuda error, possibly relating to incorrect matrix shapes during [multiplications](https://discuss.pytorch.org/t/runtimeerror-cuda-error-cublas-status-invalid-value-when-calling-cublassgemm-handle-opa-opb-m-n-k-alpha-a-lda-b-ldb-beta-c-ldc/124544). I'm using the exact same torch/cuda/mmcv/mmdet versions as listed in the README, on a...