Upload folder using huggingface_hub

predict.py

@@ -155,8 +155,7 @@ def predict_next_frame(ens, context_frames: np.ndarray) -> np.ndarray:
             ctx = context_tensor.clone()
             last_t = last_tensor.clone()
             for step in range(PRED_FRAMES):
-                pong_scale = 1.01 + step * (1.05 - 1.01) / (PRED_FRAMES - 1)
-                predicted = _predict_ar_frame(ens.models["pong"], ctx, last_t, residual_scale=pong_scale)
+                predicted = _predict_ar_frame(ens.models["pong"], ctx, last_t, residual_scale=1.03)
                 ar_preds.append(predicted)
                 ctx_frames = ctx.reshape(1, CONTEXT_FRAMES, 3, 64, 64)
                 ctx_frames = torch.cat([ctx_frames[:, 1:], predicted.unsqueeze(1)], dim=1)
@@ -167,7 +166,7 @@ def predict_next_frame(ens, context_frames: np.ndarray) -> np.ndarray:
 
             predicted = torch.zeros_like(direct_pred)
             for step in range(PRED_FRAMES):
-                ar_weight = 0.85 - (step / (PRED_FRAMES - 1)) * 0.3
+                ar_weight = 0.90 - (step / (PRED_FRAMES - 1)) * 0.3
                 direct_weight = 1.0 - ar_weight
                 predicted[:, step] = ar_weight * ar_pred[:, step] + direct_weight * direct_pred[:, step]
 
@@ -214,9 +213,8 @@ def predict_next_frame(ens, context_frames: np.ndarray) -> np.ndarray:
                 for step in range(PRED_FRAMES):
                     ctx_in = ctx if noise_std == 0 else torch.clamp(ctx + torch.randn_like(ctx) * noise_std, 0, 1)
                     ctx_flip_in = ctx_flip if noise_std == 0 else torch.clamp(ctx_flip + torch.randn_like(ctx_flip) * noise_std, 0, 1)
-                    sonic_scale = 1.02 + step * (1.16 - 1.02) / (PRED_FRAMES - 1)
-                    ar_orig = _predict_ar_frame(ens.sonic_ar, ctx_in, last_t, residual_scale=sonic_scale)
-                    ar_flip = _predict_ar_frame(ens.sonic_ar, ctx_flip_in, last_f, residual_scale=sonic_scale)
+                    ar_orig = _predict_ar_frame(ens.sonic_ar, ctx_in, last_t, residual_scale=1.08)
+                    ar_flip = _predict_ar_frame(ens.sonic_ar, ctx_flip_in, last_f, residual_scale=1.08)
                     ar_flip_back = torch.flip(ar_flip, dims=[3])
                     ar_frame = (ar_orig + ar_flip_back) / 2.0
                     ar_preds_run.append(ar_frame)
@@ -234,7 +232,7 @@ def predict_next_frame(ens, context_frames: np.ndarray) -> np.ndarray:
 
             predicted = torch.zeros_like(direct_pred)
             for step in range(PRED_FRAMES):
-                ar_weight = 0.65 - (step / (PRED_FRAMES - 1)) * 0.3
+                ar_weight = 0.70 - (step / (PRED_FRAMES - 1)) * 0.3
                 direct_weight = 1.0 - ar_weight
                 predicted[:, step] = ar_weight * ar_pred[:, step] + direct_weight * direct_pred[:, step]