How ggormm1/qiren works
QIREN provides image and sound implicit-representation training in qinr, alongside an INR-GAN face-generation stack. The principal workflows are task data/configuration into model training, and GAN training from prepared image datasets through evaluation or generation. The graph also preserves GAN projection, style mixing, and custom training operators. Several GAN capabilities are represented from the file tree and README, but their implementation details were not sampled; unsupported connections are therefore omitted.
Main entry points: metric_main.py Metric dispatcher · train.py Task training · training_loop.py Training loop · networks.py Generator and discriminator
Components 32
QIREN representations
- Task training
qinr/train.py - Configuration
qinr/config_parser.py - Image data
qinr/image/data_process.py - Sound data
qinr/sound/data_process.py - Implicit models
qinr/modules.py - Differential operators
qinr/diff_operators.py - Training logs
qinr/Log.py
GAN training
- GAN trainer
inr-gan/train.py - Dataset loader
inr-gan/training/dataset.py - Dataset preparation
inr-gan/dataset_tool.py - Training loop
inr-gan/training/training_loop.py - GAN loss
inr-gan/training/loss.py - Training statistics
inr-gan/torch_utils/training_stats.py
GAN workflows
- Metric command
inr-gan/calc_metrics.py - Image generation
inr-gan/generate.py - Style mixing
inr-gan/style_mixing.py - Latent projection
inr-gan/projector.py - Legacy model loading
inr-gan/legacy.py
GAN evaluation
- Metric dispatcher
inr-gan/metrics/metric_main.py - Metric utilities
inr-gan/metrics/metric_utils.py - FID metric
inr-gan/metrics/frechet_inception_distance.py - KID metric
inr-gan/metrics/kernel_inception_distance.py - Inception score
inr-gan/metrics/inception_score.py - Precision recall
inr-gan/metrics/precision_recall.py - Path length
inr-gan/metrics/perceptual_path_length.py
GAN model core
- Generator and discriminator
inr-gan/training/networks.py - Network layers
inr-gan/training/layers.py - Image operations
inr-gan/torch_utils/ops/upfirdn2d.py - Convolution gradients
inr-gan/torch_utils/ops/conv2d_gradfix.py - Model persistence
inr-gan/torch_utils/persistence.py - Custom operators
inr-gan/torch_utils/custom_ops.py
Other components
- Researcher
Connections 35
- Researcher → Task training: starts training
qinr/train.py - Task training → Configuration: loads settings
qinr/train.py - Task training → Image data: loads image data
qinr/train.py - Task training → Sound data: loads sound data
qinr/train.py - Task training → Implicit models: trains models
qinr/train.py - Task training → Differential operators: uses operators
qinr/train.py - Task training → Training logs: writes logs
qinr/train.py - Researcher → GAN trainer: starts training
inr-gan/train.py - GAN trainer → Training loop: runs loop
inr-gan/train.py - GAN trainer → Metric dispatcher: selects metrics
inr-gan/train.py - GAN trainer → Training statistics: initializes statistics
inr-gan/train.py - Training loop → Dataset loader: loads dataset
inr-gan/training/training_loop.py - Training loop → Generator and discriminator: trains networks
- Training loop → GAN loss: uses loss
- Training loop → Training statistics: reports statistics
inr-gan/training/training_loop.py - Generator and discriminator → Network layers: uses layers
inr-gan/training/networks.py - Generator and discriminator → Image operations: uses resampling
inr-gan/training/networks.py - Network layers → Image operations: uses resampling
inr-gan/training/layers.py - Image operations → Custom operators: loads kernels
inr-gan/torch_utils/ops/upfirdn2d.py - Training loop → Metric dispatcher: calculates metrics
inr-gan/training/training_loop.py - Metric dispatcher → Metric utilities: uses utilities
inr-gan/metrics/metric_main.py - Metric dispatcher → FID metric: dispatches FID
inr-gan/metrics/metric_main.py - Metric dispatcher → KID metric: dispatches KID
inr-gan/metrics/metric_main.py - Metric dispatcher → Inception score: dispatches score
inr-gan/metrics/metric_main.py - Metric dispatcher → Precision recall: dispatches precision
inr-gan/metrics/metric_main.py - Metric dispatcher → Path length: dispatches path length
inr-gan/metrics/metric_main.py - Metric command → Metric dispatcher: calculates metrics
inr-gan/calc_metrics.py - Researcher → Metric command: requests evaluation
inr-gan/calc_metrics.py - Researcher → Image generation: requests images
- Researcher → Style mixing: requests style mixing
- Researcher → Latent projection: requests projection
inr-gan/projector.py - Latent projection → Legacy model loading: loads network
inr-gan/projector.py - Legacy model loading → Generator and discriminator: reconstructs networks
inr-gan/legacy.py - Generator and discriminator → Model persistence: decorates models
inr-gan/training/networks.py - Training loop → Convolution gradients: enables gradients
inr-gan/training/training_loop.py