MCPcopy Index your code
hub / github.com/ImprintLab/MedSegDiff / sample

Method sample

guided_diffusion/dpm_solver.py:1004–1199  ·  view source on GitHub ↗

Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`. ===================================================== We support the following algorithms for both noise prediction model and data prediction model: - 'singlestep':

(self, x, steps=20, t_start=None, t_end=None, order=2, skip_type='time_uniform',
        method='multistep', lower_order_final=True, denoise_to_zero=False, solver_type='dpmsolver',
        atol=0.0078, rtol=0.05, return_intermediate=False,
    )

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 3

inverseMethod · 0.95
p_sample_loop_knownMethod · 0.95
forward_backwardMethod · 0.45

Calls 8

dpm_solver_adaptiveMethod · 0.95
get_time_stepsMethod · 0.95
model_fnMethod · 0.95
denoise_to_zero_fnMethod · 0.95
marginal_lambdaMethod · 0.80

Tested by

no test coverage detected