Gtx titan x

Our CycleGAN with heatmap support models was run using standard CycleGAN settings. Both generators are extended with an additional model to predict Gaussian heatmaps of wheat head locations, both of which share their Adam optimisers and learning rates of $$2\times {10}^{-4}$$ with their respective generator. These models were each trained for 100 epochs, after which GAN training performance began to degrade.
Our experiments were performed with an unmodified Detectron 2 using standard settings, trained on NVIDIA GTX Titan X (Pascal) GPUs for 60 epochs.

The specifications of the development environment were as follows: CPU: AMD EPYC 7452, GPU NVIDIA GTX TITAN X, Python 3.8.10, and PyTorch 1.10.0. To improve predictability, we performed data augmentation on the images extracted from the image server. For data augmentation, the image data were amplified via the application of ColorJitter (random brightness, contrast, saturation, and hue changes), RandomAffine (random geometric deformation), and RandomHorizontalFlip (random left-right flip) to each image. We then decomposed all chest X-rays into four (2 × 2) patches and resized them to 224 × 224 pixels. Each decomposed patch was vectorized and concatenated using ResNet50 [28 ]. These were then combined with the age and sex, and input into a three-layer perceptron with 128 hidden channels. The input batch size was 64 and optimization was performed using stochastic gradient descent. We trained the deep learning model as a regression for BMD and multiclass classification (one-vs.-all classification) for the T-score. In the multi-classification, we trained the deep learning model for three classification tasks as follows: (1) T-score above −1.0 vs. the rest; (2) T-score between −1.0 and −2.5 vs. the rest; and (3) T-score below −2.5 vs. the rest.