{"_class_name": "CausalVideoAutoencoder", "dims": 3, "in_channels": 3, "out_channels": 3, "latent_channels": 128, "blocks": [["res_x", 4], ["compress_all", 1], ["res_x_y", 1], ["res_x", 3], ["compress_all", 1], ["res_x_y", 1], ["res_x", 3], ["compress_all", 1], ["res_x", 3], ["res_x", 4]], "scaling_factor": 1.0, "norm_layer": "pixel_norm", "patch_size": 4, "latent_log_var": "uniform", "use_quant_conv": false, "causal_decoder": false} |