MCPcopy Create free account
hub / github.com/openai/point-e / __init__

Method __init__

point_e/diffusion/gaussian_diffusion.py:144–196  ·  view source on GitHub ↗
(
        self,
        *,
        betas: Sequence[float],
        model_mean_type: str,
        model_var_type: str,
        loss_type: str,
        discretized_t0: bool = False,
        channel_scales: Optional[np.ndarray] = None,
        channel_biases: Optional[np.ndarray] = None,
    )

Source from the content-addressed store, hash-verified

142 """
143
144 def __init__(
145 self,
146 *,
147 betas: Sequence[float],
148 model_mean_type: str,
149 model_var_type: str,
150 loss_type: str,
151 discretized_t0: bool = False,
152 channel_scales: Optional[np.ndarray] = None,
153 channel_biases: Optional[np.ndarray] = None,
154 ):
155 self.model_mean_type = model_mean_type
156 self.model_var_type = model_var_type
157 self.loss_type = loss_type
158 self.discretized_t0 = discretized_t0
159 self.channel_scales = channel_scales
160 self.channel_biases = channel_biases
161
162 # Use float64 for accuracy.
163 betas = np.array(betas, dtype=np.float64)
164 self.betas = betas
165 assert len(betas.shape) == 1, "betas must be 1-D"
166 assert (betas > 0).all() and (betas <= 1).all()
167
168 self.num_timesteps = int(betas.shape[0])
169
170 alphas = 1.0 - betas
171 self.alphas_cumprod = np.cumprod(alphas, axis=0)
172 self.alphas_cumprod_prev = np.append(1.0, self.alphas_cumprod[:-1])
173 self.alphas_cumprod_next = np.append(self.alphas_cumprod[1:], 0.0)
174 assert self.alphas_cumprod_prev.shape == (self.num_timesteps,)
175
176 # calculations for diffusion q(x_t | x_{t-1}) and others
177 self.sqrt_alphas_cumprod = np.sqrt(self.alphas_cumprod)
178 self.sqrt_one_minus_alphas_cumprod = np.sqrt(1.0 - self.alphas_cumprod)
179 self.log_one_minus_alphas_cumprod = np.log(1.0 - self.alphas_cumprod)
180 self.sqrt_recip_alphas_cumprod = np.sqrt(1.0 / self.alphas_cumprod)
181 self.sqrt_recipm1_alphas_cumprod = np.sqrt(1.0 / self.alphas_cumprod - 1)
182
183 # calculations for posterior q(x_{t-1} | x_t, x_0)
184 self.posterior_variance = (
185 betas * (1.0 - self.alphas_cumprod_prev) / (1.0 - self.alphas_cumprod)
186 )
187 # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
188 self.posterior_log_variance_clipped = np.log(
189 np.append(self.posterior_variance[1], self.posterior_variance[1:])
190 )
191 self.posterior_mean_coef1 = (
192 betas * np.sqrt(self.alphas_cumprod_prev) / (1.0 - self.alphas_cumprod)
193 )
194 self.posterior_mean_coef2 = (
195 (1.0 - self.alphas_cumprod_prev) * np.sqrt(alphas) / (1.0 - self.alphas_cumprod)
196 )
197
198 def get_sigmas(self, t):
199 return _extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, t.shape)

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected