run_wild.py

# Copyright (c) 2018-present, Facebook, Inc.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
#

# Run arguments: python run_wild -k detections -arc 3,3,3,3,3 -c checkpoint --evaluate d-pt-243.bin --render --viz-subject S1 --viz-action Directions
# --viz-video InTheWildData/out_cutted.mp4 --viz-camera 0 --viz-output output_scater.mp4 --viz-size 5 --viz-downsample 1 --viz-skip 9

import numpy as np

from common.arguments import parse_args
import torch

import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import os
import sys
import errno

from common.camera import *
from common.model import *
from common.loss import *
from common.generators import ChunkedGenerator, UnchunkedGenerator
from time import time
from common.utils import deterministic_random

args = parse_args()
print(args)

try:
    # Create checkpoint directory if it does not exist
    os.makedirs(args.checkpoint)
except OSError as e:
    if e.errno != errno.EEXIST:
        raise RuntimeError('Unable to create checkpoint directory:', args.checkpoint)


print('Loading dataset...')
dataset_path = 'data/data_3d_' + args.dataset + '.npz'
if args.dataset == 'h36m':
    from common.h36m_dataset import Human36mDataset
    dataset = Human36mDataset(dataset_path)
elif args.dataset.startswith('humaneva'):
    from common.humaneva_dataset import HumanEvaDataset
    dataset = HumanEvaDataset(dataset_path)
else:
    raise KeyError('Invalid dataset')

print('Preparing data...')
for subject in dataset.subjects():
    for action in dataset[subject].keys():
        anim = dataset[subject][action]

        positions_3d = []
        for cam in anim['cameras']:
            pos_3d = world_to_camera(anim['positions'], R=cam['orientation'], t=cam['translation'])
            pos_3d[:, 1:] -= pos_3d[:, :1] # Remove global offset, but keep trajectory in first position
            positions_3d.append(pos_3d)
        anim['positions_3d'] = positions_3d

print('Loading 2D detections...')
#keypoints = np.load('data/data_2d_' + args.dataset + '_' + args.keypoints + '.npz')
keypoints = np.load('data/data_2d_' + args.keypoints + '.npz')
keypoints_symmetry = keypoints['metadata'].item()['keypoints_symmetry']
kps_left, kps_right = list(keypoints_symmetry[0]), list(keypoints_symmetry[1])
kps_left = [1, 3, 5, 7, 9, 11, 13, 15]
kps_right = [2, 4, 6, 8, 10, 12, 14, 16]
joints_left, joints_right = list(dataset.skeleton().joints_left()), list(dataset.skeleton().joints_right())
keypoints = keypoints['positions_2d'].item()
# keypoints['S1']['Directions 1'][0].shape == 1384,17,2 should be 3 though
# when loading the file provided py pavllo as example the shape is fine (1384,17,3) and the joints left = <class 'list'>: [4, 5, 6, 11, 12, 13] and right = <class 'list'>: [1, 2, 3, 14, 15, 16]




subject = 'S1'

action = 'Directions 1'

#for subject in keypoints.keys():
#    for action in keypoints[subject]:
#        for cam_idx, kps in enumerate(keypoints[subject][action]):
#            # Normalize camera frame
#            cam = dataset.cameras()[subject][cam_idx]
#            kps[..., :2] = normalize_screen_coordinates(kps[..., :2], w=cam['res_w'], h=cam['res_h'])
#            keypoints[subject][action][cam_idx] = kps

width_of = 1080
height_of = 1080

for cam_idx, kps in enumerate(keypoints[subject][action]):

    # Normalize camera frame
    cam = dataset.cameras()[subject][cam_idx]
    kps[..., :2] = normalize_screen_coordinates(kps[..., :2], w=width_of, h=height_of)
    keypoints[subject][action][cam_idx] = kps

subjects_train = args.subjects_train.split(',')
subjects_semi = [] if not args.subjects_unlabeled else args.subjects_unlabeled.split(',')
subjects_test = args.subjects_test.split(',')

semi_supervised = len(subjects_semi) > 0
if semi_supervised and not dataset.supports_semi_supervised():
    raise RuntimeError('Semi-supervised training is not implemented for this dataset')
            
def fetch(subjects, action_filter=None, subset=1, parse_3d_poses=True):
    out_poses_3d = []
    out_poses_2d = []
    out_camera_params = []
    subject = 'S1'
    action = 'Directions 1'

                
    poses_2d = keypoints[subject][action]
    for i in range(len(poses_2d)): # Iterate across cameras
        out_poses_2d.append(poses_2d[i])


    if len(out_camera_params) == 0:
        out_camera_params = None
    if len(out_poses_3d) == 0:
        out_poses_3d = None
    
    stride = args.downsample
    if subset < 1:
        for i in range(len(out_poses_2d)):
            n_frames = int(round(len(out_poses_2d[i])//stride * subset)*stride)
            start = deterministic_random(0, len(out_poses_2d[i]) - n_frames + 1, str(len(out_poses_2d[i])))
            out_poses_2d[i] = out_poses_2d[i][start:start+n_frames:stride]
            if out_poses_3d is not None:
                out_poses_3d[i] = out_poses_3d[i][start:start+n_frames:stride]
    elif stride > 1:
        # Downsample as requested
        for i in range(len(out_poses_2d)):
            out_poses_2d[i] = out_poses_2d[i][::stride]
            if out_poses_3d is not None:
                out_poses_3d[i] = out_poses_3d[i][::stride]
    

    return out_camera_params, out_poses_3d, out_poses_2d

action_filter = None if args.actions == '*' else args.actions.split(',')
if action_filter is not None:
    print('Selected actions:', action_filter)
    
cameras_valid, poses_valid, poses_valid_2d = fetch(subjects_test, action_filter)

filter_widths = [int(x) for x in args.architecture.split(',')]

model_pos = TemporalModel(poses_valid_2d[0].shape[-2], poses_valid_2d[0].shape[-1], 17,
                            filter_widths=filter_widths, causal=args.causal, dropout=args.dropout, channels=args.channels,
                            dense=args.dense)


receptive_field = model_pos.receptive_field()
print('INFO: Receptive field: {} frames'.format(receptive_field))
pad = (receptive_field - 1) // 2 # Padding on each side
if args.causal:
    print('INFO: Using causal convolutions')
    causal_shift = pad
else:
    causal_shift = 0

model_params = 0
for parameter in model_pos.parameters():
    model_params += parameter.numel()
print('INFO: Trainable parameter count:', model_params)

if torch.cuda.is_available():
    model_pos = model_pos.cuda()
#    model_pos_train = model_pos_train.cuda()
    
if args.resume or args.evaluate:
    chk_filename = os.path.join(args.checkpoint, args.resume if args.resume else args.evaluate)
    print('Loading checkpoint', chk_filename)
    checkpoint = torch.load(chk_filename, map_location=lambda storage, loc: storage)
    print('This model was trained for {} epochs'.format(checkpoint['epoch']))
#    model_pos_train.load_state_dict(checkpoint['model_pos'])
    model_pos.load_state_dict(checkpoint['model_pos'])
    
test_generator = UnchunkedGenerator(cameras_valid, poses_valid, poses_valid_2d,
                                    pad=pad, causal_shift=causal_shift, augment=False,
                                    kps_left=kps_left, kps_right=kps_right, joints_left=joints_left, joints_right=joints_right)
print('INFO: Testing on {} frames'.format(test_generator.num_frames()))


def evaluate(test_generator, action=None, return_predictions=False):
    epoch_loss_3d_pos = 0
    epoch_loss_3d_pos_procrustes = 0
    epoch_loss_3d_pos_scale = 0
    epoch_loss_3d_vel = 0
    with torch.no_grad():
        model_pos.eval()
        N = 0
        for _, batch, batch_2d in test_generator.next_epoch():
            inputs_2d = torch.from_numpy(batch_2d.astype('float32'))
            if torch.cuda.is_available():
                inputs_2d = inputs_2d.cuda()

            # Positional model
            predicted_3d_pos = model_pos(inputs_2d)

            # Test-time augmentation (if enabled)
            if test_generator.augment_enabled():
                # Undo flipping and take average with non-flipped version
                predicted_3d_pos[1, :, :, 0] *= -1
                predicted_3d_pos[1, :, joints_left + joints_right] = predicted_3d_pos[1, :, joints_right + joints_left]
                predicted_3d_pos = torch.mean(predicted_3d_pos, dim=0, keepdim=True)
                
            if return_predictions:
                return predicted_3d_pos.squeeze(0).cpu().numpy()
                
            inputs_3d = torch.from_numpy(batch.astype('float32'))
            if torch.cuda.is_available():
                inputs_3d = inputs_3d.cuda()
            inputs_3d[:, :, 0] = 0    
            if test_generator.augment_enabled():
                inputs_3d = inputs_3d[:1]

            error = mpjpe(predicted_3d_pos, inputs_3d)
            epoch_loss_3d_pos_scale += inputs_3d.shape[0]*inputs_3d.shape[1] * n_mpjpe(predicted_3d_pos, inputs_3d).item()

            epoch_loss_3d_pos += inputs_3d.shape[0]*inputs_3d.shape[1] * error.item()
            N += inputs_3d.shape[0] * inputs_3d.shape[1]
            
            inputs = inputs_3d.cpu().numpy().reshape(-1, inputs_3d.shape[-2], inputs_3d.shape[-1])
            predicted_3d_pos = predicted_3d_pos.cpu().numpy().reshape(-1, inputs_3d.shape[-2], inputs_3d.shape[-1])

            epoch_loss_3d_pos_procrustes += inputs_3d.shape[0]*inputs_3d.shape[1] * p_mpjpe(predicted_3d_pos, inputs)

            # Compute velocity error
            epoch_loss_3d_vel += inputs_3d.shape[0]*inputs_3d.shape[1] * mean_velocity_error(predicted_3d_pos, inputs)
            
    if action is None:
        print('----------')
    else:
        print('----'+action+'----')
    e1 = (epoch_loss_3d_pos / N)*1000
    e2 = (epoch_loss_3d_pos_procrustes / N)*1000
    e3 = (epoch_loss_3d_pos_scale / N)*1000
    ev = (epoch_loss_3d_vel / N)*1000
    print('Test time augmentation:', test_generator.augment_enabled())
    print('Protocol #1 Error (MPJPE):', e1, 'mm')
    print('Protocol #2 Error (P-MPJPE):', e2, 'mm')
    print('Protocol #3 Error (N-MPJPE):', e3, 'mm')
    print('Velocity Error (MPJVE):', ev, 'mm')
    print('----------')

    return e1, e2, e3, ev


if args.render:
    print('Rendering...')
    my_action = 'Directions 1'
    #input_keypoints = keypoints[args.viz_subject][args.viz_action][args.viz_camera].copy()
    input_keypoints = keypoints[args.viz_subject][my_action][args.viz_camera].copy()
    if args.viz_subject in dataset.subjects() and args.viz_action in dataset[args.viz_subject]:
        ground_truth = dataset[args.viz_subject][args.viz_action]['positions_3d'][args.viz_camera].copy()
        ##Changes
        ground_truth = None
    else:
        ground_truth = None
        print('INFO: this action is unlabeled. Ground truth will not be rendered.')
        
    gen = UnchunkedGenerator(None, None, [input_keypoints],
                             pad=pad, causal_shift=causal_shift, augment=args.test_time_augmentation,
                             kps_left=kps_left, kps_right=kps_right, joints_left=joints_left, joints_right=joints_right)
    prediction = evaluate(gen, return_predictions=True)
    
    if ground_truth is not None:
        # Reapply trajectory
        trajectory = ground_truth[:, :1]
        ground_truth[:, 1:] += trajectory
        prediction += trajectory
    
    # Invert camera transformation
    cam = dataset.cameras()[args.viz_subject][args.viz_camera]
    if ground_truth is not None:
        prediction = camera_to_world(prediction, R=cam['orientation'], t=cam['translation'])
        ground_truth = camera_to_world(ground_truth, R=cam['orientation'], t=cam['translation'])
    else:
        # If the ground truth is not available, take the camera extrinsic params from a random subject.
        # They are almost the same, and anyway, we only need this for visualization purposes.
        for subject in dataset.cameras():
            if 'orientation' in dataset.cameras()[subject][args.viz_camera]:
                rot = dataset.cameras()[subject][args.viz_camera]['orientation']
                break
        prediction = camera_to_world(prediction, R=rot, t=0)
        # We don't have the trajectory, but at least we can rebase the height
        prediction[:, :, 2] -= np.min(prediction[:, :, 2])
    
    anim_output = {'Reconstruction': prediction}
    if ground_truth is not None and not args.viz_no_ground_truth:
        anim_output['Ground truth'] = ground_truth
    
    input_keypoints = image_coordinates(input_keypoints[..., :2], w=width_of, h=height_of)

    manual_fps = 29

    np.savez('out_3D_vp3d', anim_output['Reconstruction'])

    from common.visualization import render_animation
    render_animation(input_keypoints, anim_output,
                     dataset.skeleton(), manual_fps, args.viz_bitrate, cam['azimuth'], args.viz_output,
                     limit=args.viz_limit, downsample=args.viz_downsample, size=args.viz_size,
                     input_video_path=args.viz_video, viewport=(cam['res_w'], cam['res_h']),
                     input_video_skip=args.viz_skip)

else:
    print('Evaluating...')
    all_actions = {}
    all_actions_by_subject = {}
    for subject in subjects_test:
        if subject not in all_actions_by_subject:
            all_actions_by_subject[subject] = {}

        for action in dataset[subject].keys():
            action_name = action.split(' ')[0]
            if action_name not in all_actions:
                all_actions[action_name] = []
            if action_name not in all_actions_by_subject:
                all_actions_by_subject[subject][action_name] = []
            all_actions[action_name].append((subject, action))
            all_actions_by_subject[subject][action_name].append((subject, action))

    def fetch_actions(actions):
        out_poses_3d = []
        out_poses_2d = []

        for subject, action in actions:
            poses_2d = keypoints[subject][action]
            for i in range(len(poses_2d)): # Iterate across cameras
                out_poses_2d.append(poses_2d[i])

            poses_3d = dataset[subject][action]['positions_3d']
            assert len(poses_3d) == len(poses_2d), 'Camera count mismatch'
            for i in range(len(poses_3d)): # Iterate across cameras
                out_poses_3d.append(poses_3d[i])

        stride = args.downsample
        if stride > 1:
            # Downsample as requested
            for i in range(len(out_poses_2d)):
                out_poses_2d[i] = out_poses_2d[i][::stride]
                if out_poses_3d is not None:
                    out_poses_3d[i] = out_poses_3d[i][::stride]

        return out_poses_3d, out_poses_2d

    def run_evaluation(actions, action_filter=None):
        errors_p1 = []
        errors_p2 = []
        errors_p3 = []
        errors_vel = []

        for action_key in actions.keys():
            if action_filter is not None:
                found = False
                for a in action_filter:
                    if action_key.startswith(a):
                        found = True
                        break
                if not found:
                    continue

            poses_act, poses_2d_act = fetch_actions(actions[action_key])
            gen = UnchunkedGenerator(None, poses_act, poses_2d_act,
                                     pad=pad, causal_shift=causal_shift, augment=args.test_time_augmentation,
                                     kps_left=kps_left, kps_right=kps_right, joints_left=joints_left, joints_right=joints_right)
            e1, e2, e3, ev = evaluate(gen, action_key)
            errors_p1.append(e1)
            errors_p2.append(e2)
            errors_p3.append(e3)
            errors_vel.append(ev)

        print('Protocol #1   (MPJPE) action-wise average:', round(np.mean(errors_p1), 1), 'mm')
        print('Protocol #2 (P-MPJPE) action-wise average:', round(np.mean(errors_p2), 1), 'mm')
        print('Protocol #3 (N-MPJPE) action-wise average:', round(np.mean(errors_p3), 1), 'mm')
        print('Velocity      (MPJVE) action-wise average:', round(np.mean(errors_vel), 2), 'mm')

    if not args.by_subject:
        run_evaluation(all_actions, action_filter)
    else:
        for subject in all_actions_by_subject.keys():
            print('Evaluating on subject', subject)
            run_evaluation(all_actions_by_subject[subject], action_filter)
            print('')