BasicVSROptions
Options & Configuration · AiDotNet.Video.Options
Configuration options for the BasicVSR bidirectional recurrent video super-resolution model.
Inheritance: ModelOptions → NeuralNetworkOptions → BasicVSROptions
For Beginners
BasicVSR treats video frames like a sequence. It processes frames both forward in time and backward, so each frame benefits from information in both directions. Optical flow tells the model how pixels moved between frames, so it can align them before combining their features for higher resolution output.
How It Works
Defaults follow Chan et al., CVPR 2021, and the authors’ release (open-mmlab/mmagic, BasicVSRNet and configs/basicvsr/basicvsr_2xb4_reds4.py): 64-channel features, 30 residual blocks per propagation branch, x4 upsampling, 15-frame training clips, Charbonnier loss, and Adam (0.9, 0.99) at 2e-4 with SPyNet at 0.125 times the rate and frozen for the first 5,000 iterations, cosine-annealed to 1e-7 over 300,000 iterations.
Constructors
| Constructor | Summary |
|---|---|
BasicVSROptions() |
Initializes a new instance with default values. |
BasicVSROptions(BasicVSROptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
OnnxModelOptions OnnxOptions { get; set; } |
Gets or sets the ONNX runtime options. |
double CharbonnierEpsilon { get; set; } |
Gets or sets the Charbonnier ε; the release’s loss is sqrt(d² + 1e-12), so ε = 1e-6. |
double LearningRate { get; set; } |
Gets or sets Adam’s starting learning rate (2e-4). |
double MinLearningRate { get; set; } |
Gets or sets the floor of the cosine schedule (1e-7). |
double SpyNetLearningRateMultiplier { get; set; } |
Gets or sets the multiplier of SPyNet’s learning rate (0.125, i.e. |
int CosineIterations { get; set; } |
Gets or sets the iterations of the cosine schedule (300,000). |
int FlowFreezeIterations { get; set; } |
Gets or sets the iterations SPyNet stays frozen at the start of training (5,000). |
int MidChannels { get; set; } |
Gets or sets the feature channels of the propagation branches (64). |
int NumFrames { get; set; } |
Gets or sets the frames of a training clip (15, the REDS recipe). |
int NumResBlocks { get; set; } |
Gets or sets the residual blocks per propagation branch (30). |
string ModelPath { get; set; } |
Gets or sets the path to the ONNX model file. |