Inputs: -tensor: 2D tensor of any shape -num_reps: Number of times to repeat each row Outpus: -repeat_tensor:

Input: - pred_traj: Tensor of shape (seq_len, batch, 2). Predicted trajectory. - pred_traj_gt: Tensor of shape (seq_len, batch, 2). Groun

Input: - pred_pos: Tensor of shape (batch, 2). Predicted last pos. - pred_pos_gt: Tensor of shape (seq_len, batch, 2). Groud truth la

Inputs: - rel_traj: pytorch tensor of shape (seq_len, batch, 2) - start_pos: pytorch tensor of shape (batch, 2) Outputs: - abs_tr

Numerically stable version of the binary cross-entropy loss function. As per https://github.com/pytorch/pytorch/issues/751 See the Tensor

Input: - pred_traj: Tensor of shape (seq_len, batch, 2). Predicted trajectory. - pred_traj_gt: Tensor of shape (seq_len, batch, 2). Groud

Inputs: -tensor: 2D tensor of any shape -num_reps: Number of times to repeat each row Outpus: -repeat_tensor:

Inputs: - _input: Tensor of shape (_, decoder_h_dim - noise_first_dim) - seq_start_end: A list of tuples which delimit sequen

Input: - traj: Numpy array of shape (2, traj_len) - traj_len: Len of trajectory - threshold: Minimum error to be considered for non l

Args: - data_dir: Directory containing dataset files in the format <frame_id> <ped_id> <x> <y> - obs_len: Number of t

Inputs: - obs_traj: Tensor of shape (obs_len, batch, 2) Output: - final_h: Tensor of shape (self.num_layers, batch, s

Inputs: - last_pos: Tensor of shape (batch, 2) - last_pos_rel: Tensor of shape (batch, 2) - state_tuple: (hh, ch) eac

Inputs: - h_states: Tensor of shape (num_layers, batch, h_dim) - seq_start_end: A list of tuples which delimit sequences with

Inputs: - h_states: Tesnsor of shape (num_layers, batch, h_dim) - seq_start_end: A list of tuples which delimit sequences wit

Inputs: - obs_traj: Tensor of shape (obs_len, batch, 2) - obs_traj_rel: Tensor of shape (obs_len, batch, 2) - seq_sta

Inputs: - traj: Tensor of shape (obs_len + pred_len, batch, 2) - traj_rel: Tensor of shape (obs_len + pred_len, batch, 2)

Input: - scores_real: Tensor of shape (N,) giving scores for real samples - scores_fake: Tensor of shape (N,) giving scores for fake samp

Input: - scores_fake: Tensor of shape (N,) containing scores for fake samples Output: - loss: Tensor of shape (,) giving GAN generat