Skip to content

GitLab

Commit 41b18fd8 authored by zhe chen's avatar zhe chen
Browse files

Use pre-commit to reformat code 


Use pre-commit to reformat code
parent ff20ea39
Show whitespace changes
Inline Side-by-side
Showing with 362 additions and 421 deletions
autonomous_driving/Online-HD-Map-Construction/src/models/heads/polyline_generator.py
View file @ 41b18fd8
import math
import torch import torch
import torch.nn as nn import torch.nn as nn
import torch.nn.functional as F import torch.nn.functional as F
from mmcv.runner import force_fp32
from mmdet.models import HEADS
from torch.distributions.categorical import Categorical from torch.distributions.categorical import Categorical
from mmdet.models import HEADS
from .detgen_utils.causal_trans import (CausalTransformerDecoder, from .detgen_utils.causal_trans import (CausalTransformerDecoder,
CausalTransformerDecoderLayer) CausalTransformerDecoderLayer)
from .detgen_utils.utils import (dequantize_verts, generate_square_subsequent_mask, from .detgen_utils.utils import (generate_square_subsequent_mask, top_k_logits,
quantize_verts, top_k_logits, top_p_logits) top_p_logits)
from mmcv.runner import force_fp32, auto_fp16
@HEADS.register_module(force=True) @HEADS.register_module(force=True)
class PolylineGenerator(nn.Module): class PolylineGenerator(nn.Module):
...@@ -63,7 +63,7 @@ class PolylineGenerator(nn.Module): ...@@ -63,7 +63,7 @@ class PolylineGenerator(nn.Module):
self.fp16_enabled = False self.fp16_enabled = False
self.coord_dim = coord_dim # if we use xyz else 2 when we use xy self.coord_dim = coord_dim # if we use xyz else 2 when we use xy
self.kp_coord_dim = coord_dim if coord_dim==2 else 2 # XXX self.kp_coord_dim = coord_dim if coord_dim == 2 else 2 # XXX
self.register_buffer('canvas_size', torch.tensor(canvas_size)) self.register_buffer('canvas_size', torch.tensor(canvas_size))
# initialize the model # initialize the model
...@@ -126,7 +126,7 @@ class PolylineGenerator(nn.Module): ...@@ -126,7 +126,7 @@ class PolylineGenerator(nn.Module):
# Discrete vertex value embeddings # Discrete vertex value embeddings
vert_embeddings = self.vertex_embed(bbox) vert_embeddings = self.vertex_embed(bbox)
return vert_embeddings + (bbox_embedding+coord_embeddings)[None] return vert_embeddings + (bbox_embedding + coord_embeddings)[None]
def _prepare_context(self, batch, context): def _prepare_context(self, batch, context):
"""Prepare class label and vertex context.""" """Prepare class label and vertex context."""
...@@ -189,7 +189,7 @@ class PolylineGenerator(nn.Module): ...@@ -189,7 +189,7 @@ class PolylineGenerator(nn.Module):
# Aggregate embeddings # Aggregate embeddings
embeddings = vert_embeddings + \ embeddings = vert_embeddings + \
(coord_embeddings+pos_embeddings)[None] (coord_embeddings + pos_embeddings)[None]
embeddings = torch.cat([condition_embedding, embeddings], dim=1) embeddings = torch.cat([condition_embedding, embeddings], dim=1)
return embeddings return embeddings
...@@ -218,24 +218,22 @@ class PolylineGenerator(nn.Module): ...@@ -218,24 +218,22 @@ class PolylineGenerator(nn.Module):
sizes = [size, polyline_length.max()] sizes = [size, polyline_length.max()]
polyline_logits = [] polyline_logits = []
for c_idx, size in zip([c1,c2], sizes): for c_idx, size in zip([c1, c2], sizes):
new_batch = assign_batch(batch, c_idx, size)
new_batch = assign_batch(batch,c_idx, size) _poly_logits = self._forward_train(new_batch, context, **kwargs)
_poly_logits = self._forward_train(new_batch,context,**kwargs)
polyline_logits.append(_poly_logits) polyline_logits.append(_poly_logits)
# maybe imporve the speed # maybe imporve the speed
for i, (_poly_logits, size) in enumerate(zip(polyline_logits, sizes)): for i, (_poly_logits, size) in enumerate(zip(polyline_logits, sizes)):
if size < sizes[1]: if size < sizes[1]:
_poly_logits = F.pad(_poly_logits, (0,0,0,sizes[1]-size), "constant", 0) _poly_logits = F.pad(_poly_logits, (0, 0, 0, sizes[1] - size), 'constant', 0)
polyline_logits[i] = _poly_logits polyline_logits[i] = _poly_logits
polyline_logits = torch.cat(polyline_logits,0) polyline_logits = torch.cat(polyline_logits, 0)
polyline_logits = polyline_logits[revert_idx] polyline_logits = polyline_logits[revert_idx]
cat_dist = Categorical(logits=polyline_logits) cat_dist = Categorical(logits=polyline_logits)
return {'polylines':cat_dist} return {'polylines': cat_dist}
def forward_train(self, batch: dict, context: dict, **kwargs): def forward_train(self, batch: dict, context: dict, **kwargs):
""" """
...@@ -247,7 +245,7 @@ class PolylineGenerator(nn.Module): ...@@ -247,7 +245,7 @@ class PolylineGenerator(nn.Module):
if False: if False:
polyline_logits = self._forward_train(batch, context, **kwargs) polyline_logits = self._forward_train(batch, context, **kwargs)
cat_dist = Categorical(logits=polyline_logits) cat_dist = Categorical(logits=polyline_logits)
return {'polylines':cat_dist} return {'polylines': cat_dist}
else: else:
return self.sperate_forward(batch, context, **kwargs) return self.sperate_forward(batch, context, **kwargs)
...@@ -271,7 +269,7 @@ class PolylineGenerator(nn.Module): ...@@ -271,7 +269,7 @@ class PolylineGenerator(nn.Module):
return logits return logits
@force_fp32(apply_to=('global_context_embedding','sequential_context_embeddings','cache')) @force_fp32(apply_to=('global_context_embedding', 'sequential_context_embeddings', 'cache'))
def body(self, def body(self,
seqs, seqs,
global_context_embedding=None, global_context_embedding=None,
...@@ -314,28 +312,27 @@ class PolylineGenerator(nn.Module): ...@@ -314,28 +312,27 @@ class PolylineGenerator(nn.Module):
decoder_outputs = decoder_outputs.transpose(0, 1) decoder_outputs = decoder_outputs.transpose(0, 1)
# since we only need the predict seq # since we only need the predict seq
decoder_outputs = decoder_outputs[:, condition_len-1:] decoder_outputs = decoder_outputs[:, condition_len - 1:]
# Get logits and optionally process for sampling # Get logits and optionally process for sampling
logits = self._project_to_logits(decoder_outputs) logits = self._project_to_logits(decoder_outputs)
# y mask # y mask
_vert_mask = torch.arange(logits.shape[-1], device=logits.device) _vert_mask = torch.arange(logits.shape[-1], device=logits.device)
vertices_mask_y = (_vert_mask < self.canvas_size[1]+1) vertices_mask_y = (_vert_mask < self.canvas_size[1] + 1)
vertices_mask_y[0] = False # y position doesn't have stop sign vertices_mask_y[0] = False # y position doesn't have stop sign
logits[:, 1::self.coord_dim] = logits[:, 1::self.coord_dim] * \ logits[:, 1::self.coord_dim] = logits[:, 1::self.coord_dim] * \
vertices_mask_y - ~vertices_mask_y*1e9 vertices_mask_y - ~vertices_mask_y * 1e9
if self.coord_dim > 2: if self.coord_dim > 2:
# z mask # z mask
_vert_mask = torch.arange(logits.shape[-1], device=logits.device) _vert_mask = torch.arange(logits.shape[-1], device=logits.device)
vertices_mask_z = (_vert_mask < self.canvas_size[2]+1) vertices_mask_z = (_vert_mask < self.canvas_size[2] + 1)
vertices_mask_z[0] = False # y position doesn't have stop sign vertices_mask_z[0] = False # y position doesn't have stop sign
logits[:, 2::self.coord_dim] = logits[:, 2::self.coord_dim] * \ logits[:, 2::self.coord_dim] = logits[:, 2::self.coord_dim] * \
vertices_mask_z - ~vertices_mask_z*1e9 vertices_mask_z - ~vertices_mask_z * 1e9
logits = logits / temperature
logits = logits/temperature
logits = top_k_logits(logits, top_k) logits = top_k_logits(logits, top_k)
logits = top_p_logits(logits, top_p) logits = top_p_logits(logits, top_p)
if return_logits: if return_logits:
...@@ -352,7 +349,7 @@ class PolylineGenerator(nn.Module): ...@@ -352,7 +349,7 @@ class PolylineGenerator(nn.Module):
mask = gt['polyline_masks'] mask = gt['polyline_masks']
loss = -torch.sum( loss = -torch.sum(
pred['polylines'].log_prob(gt['polylines']) * mask * weight)/weight.sum() pred['polylines'].log_prob(gt['polylines']) * mask * weight) / weight.sum()
return {'seq': loss} return {'seq': loss}
...@@ -395,16 +392,15 @@ class PolylineGenerator(nn.Module): ...@@ -395,16 +392,15 @@ class PolylineGenerator(nn.Module):
samples = torch.empty( samples = torch.empty(
[batch_size, 0], dtype=torch.int32, device=device) [batch_size, 0], dtype=torch.int32, device=device)
max_sample_length = max_sample_length or self.max_seq_length max_sample_length = max_sample_length or self.max_seq_length
seq_len = max_sample_length*self.coord_dim+1 seq_len = max_sample_length * self.coord_dim + 1
cache = None cache = None
decoded_tokens = \ decoded_tokens = \
torch.zeros((batch_size,seq_len), torch.zeros((batch_size, seq_len),
device=device,dtype=torch.long) device=device, dtype=torch.long)
remain_idx = torch.arange(batch_size, device=device) remain_idx = torch.arange(batch_size, device=device)
for i in range(seq_len): for i in range(seq_len):
# While-loop body for autoregression calculation. # While-loop body for autoregression calculation.
pred_dist, cache = self.body( pred_dist, cache = self.body(
samples, samples,
...@@ -417,22 +413,22 @@ class PolylineGenerator(nn.Module): ...@@ -417,22 +413,22 @@ class PolylineGenerator(nn.Module):
is_training=False) is_training=False)
samples = pred_dist.sample() samples = pred_dist.sample()
decoded_tokens[remain_idx,i] = samples[:,-1] decoded_tokens[remain_idx, i] = samples[:, -1]
# Stopping conditions for autoregressive calculation. # Stopping conditions for autoregressive calculation.
if not (decoded_tokens[:,:i+1] != 0).all(-1).any(): if not (decoded_tokens[:, :i + 1] != 0).all(-1).any():
break break
# update state, check the new position is zero. # update state, check the new position is zero.
valid_idx = (samples[:,-1] != 0).nonzero(as_tuple=True)[0] valid_idx = (samples[:, -1] != 0).nonzero(as_tuple=True)[0]
remain_idx = remain_idx[valid_idx] remain_idx = remain_idx[valid_idx]
cache = cache[:,:,valid_idx] cache = cache[:, :, valid_idx]
global_context = global_context[valid_idx] global_context = global_context[valid_idx]
seq_context = seq_context[valid_idx] seq_context = seq_context[valid_idx]
samples = samples[valid_idx] samples = samples[valid_idx]
# decoded_tokens = torch.cat(decoded_tokens,dim=1) # decoded_tokens = torch.cat(decoded_tokens,dim=1)
decoded_tokens = decoded_tokens[:,:i+1] decoded_tokens = decoded_tokens[:, :i + 1]
outputs = self.post_process(decoded_tokens, seq_len, outputs = self.post_process(decoded_tokens, seq_len,
device, only_return_complete) device, only_return_complete)
...@@ -455,7 +451,7 @@ class PolylineGenerator(nn.Module): ...@@ -455,7 +451,7 @@ class PolylineGenerator(nn.Module):
_polyline_mask = torch.arange(sample_seq_length)[None].to(device) _polyline_mask = torch.arange(sample_seq_length)[None].to(device)
# Get largest stopping point for incomplete samples. # Get largest stopping point for incomplete samples.
valid_polyline_len = torch.full_like(polyline[:,0], sample_seq_length) valid_polyline_len = torch.full_like(polyline[:, 0], sample_seq_length)
zero_inds = (polyline == 0).type(torch.int32).argmax(-1) zero_inds = (polyline == 0).type(torch.int32).argmax(-1)
# Real length # Real length
...@@ -463,7 +459,7 @@ class PolylineGenerator(nn.Module): ...@@ -463,7 +459,7 @@ class PolylineGenerator(nn.Module):
polyline_mask = _polyline_mask < valid_polyline_len[:, None] polyline_mask = _polyline_mask < valid_polyline_len[:, None]
# Mask faces beyond stopping token with zeros # Mask faces beyond stopping token with zeros
polyline = polyline*polyline_mask polyline = polyline * polyline_mask
# Pad to maximum size with zeros # Pad to maximum size with zeros
pad_size = max_seq_len - sample_seq_length pad_size = max_seq_len - sample_seq_length
...@@ -486,25 +482,25 @@ class PolylineGenerator(nn.Module): ...@@ -486,25 +482,25 @@ class PolylineGenerator(nn.Module):
} }
return outputs return outputs
def find_best_sperate_plan(idx,array):
def find_best_sperate_plan(idx, array):
h = array[-1] - array[idx] h = array[-1] - array[idx]
w = idx w = idx
cost = h*w cost = h * w
return cost return cost
def get_chunk_idx(polyline_length): def get_chunk_idx(polyline_length):
_polyline_length, polyline_length_idx = torch.sort(polyline_length) _polyline_length, polyline_length_idx = torch.sort(polyline_length)
costs = [] costs = []
for i in range(len(_polyline_length)): for i in range(len(_polyline_length)):
cost = find_best_sperate_plan(i, _polyline_length)
cost = find_best_sperate_plan(i,_polyline_length)
costs.append(cost) costs.append(cost)
seperate_point = torch.stack(costs).argmax() seperate_point = torch.stack(costs).argmax()
chunk1 = polyline_length_idx[:seperate_point+1] chunk1 = polyline_length_idx[:seperate_point + 1]
chunk2 = polyline_length_idx[seperate_point+1:] chunk2 = polyline_length_idx[seperate_point + 1:]
revert_idx = torch.argsort(polyline_length_idx) revert_idx = torch.argsort(polyline_length_idx)
...@@ -517,9 +513,9 @@ def assign_bev(feat, idx): ...@@ -517,9 +513,9 @@ def assign_bev(feat, idx):
def assign_batch(batch, idx, size): def assign_batch(batch, idx, size):
new_batch = {} new_batch = {}
for k,v in batch.items(): for k, v in batch.items():
new_batch[k] = v[idx] new_batch[k] = v[idx]
if new_batch[k].ndim > 1: if new_batch[k].ndim > 1:
new_batch[k] = new_batch[k][:,:size] new_batch[k] = new_batch[k][:, :size]
return new_batch return new_batch
autonomous_driving/Online-HD-Map-Construction/src/models/losses/detr_loss.py
View file @ 41b18fd8
import mmcv
import torch import torch
from mmdet.models.builder import LOSSES
from mmdet.models.losses.utils import weighted_loss
from torch import nn as nn from torch import nn as nn
from torch.nn import functional as F from torch.nn import functional as F
from mmdet.models.losses import l1_loss
from mmdet.models.losses.utils import weighted_loss
import mmcv
from mmdet.models.builder import LOSSES
@mmcv.jit(derivate=True, coderize=True) @mmcv.jit(derivate=True, coderize=True)
...@@ -77,7 +75,7 @@ class LinesLoss(nn.Module): ...@@ -77,7 +75,7 @@ class LinesLoss(nn.Module):
loss = smooth_l1_loss( loss = smooth_l1_loss(
pred, target, weight, reduction=reduction, avg_factor=avg_factor, beta=self.beta) pred, target, weight, reduction=reduction, avg_factor=avg_factor, beta=self.beta)
return loss*self.loss_weight return loss * self.loss_weight
@mmcv.jit(derivate=True, coderize=True) @mmcv.jit(derivate=True, coderize=True)
...@@ -123,7 +121,8 @@ class MasksLoss(nn.Module): ...@@ -123,7 +121,8 @@ class MasksLoss(nn.Module):
loss = bce(pred, target, weight, reduction=reduction, loss = bce(pred, target, weight, reduction=reduction,
avg_factor=avg_factor) avg_factor=avg_factor)
return loss*self.loss_weight return loss * self.loss_weight
@mmcv.jit(derivate=True, coderize=True) @mmcv.jit(derivate=True, coderize=True)
@weighted_loss @weighted_loss
...@@ -167,4 +166,4 @@ class LenLoss(nn.Module): ...@@ -167,4 +166,4 @@ class LenLoss(nn.Module):
loss = ce(pred, target, weight, reduction=reduction, loss = ce(pred, target, weight, reduction=reduction,
avg_factor=avg_factor) avg_factor=avg_factor)
return loss*self.loss_weight return loss * self.loss_weight
\ No newline at end of file
autonomous_driving/Online-HD-Map-Construction/src/models/mapers/base_mapper.py
View file @ 41b18fd8
from abc import ABCMeta, abstractmethod from abc import ABCMeta
import torch.nn as nn import torch.nn as nn
from mmcv.runner import auto_fp16
from mmcv.utils import print_log from mmcv.utils import print_log
from mmdet.utils import get_root_logger
from mmdet3d.models.builder import DETECTORS from mmdet3d.models.builder import DETECTORS
from mmdet.utils import get_root_logger
MAPPERS = DETECTORS MAPPERS = DETECTORS
class BaseMapper(nn.Module, metaclass=ABCMeta): class BaseMapper(nn.Module, metaclass=ABCMeta):
"""Base class for mappers.""" """Base class for mappers."""
...@@ -40,7 +39,7 @@ class BaseMapper(nn.Module, metaclass=ABCMeta): ...@@ -40,7 +39,7 @@ class BaseMapper(nn.Module, metaclass=ABCMeta):
return ((hasattr(self, 'roi_head') and self.roi_head.with_mask) return ((hasattr(self, 'roi_head') and self.roi_head.with_mask)
or (hasattr(self, 'mask_head') and self.mask_head is not None)) or (hasattr(self, 'mask_head') and self.mask_head is not None))
#@abstractmethod # @abstractmethod
def extract_feat(self, imgs): def extract_feat(self, imgs):
"""Extract features from images.""" """Extract features from images."""
pass pass
...@@ -48,11 +47,11 @@ class BaseMapper(nn.Module, metaclass=ABCMeta): ...@@ -48,11 +47,11 @@ class BaseMapper(nn.Module, metaclass=ABCMeta):
def forward_train(self, *args, **kwargs): def forward_train(self, *args, **kwargs):
pass pass
#@abstractmethod # @abstractmethod
def simple_test(self, img, img_metas, **kwargs): def simple_test(self, img, img_metas, **kwargs):
pass pass
#@abstractmethod # @abstractmethod
def aug_test(self, imgs, img_metas, **kwargs): def aug_test(self, imgs, img_metas, **kwargs):
"""Test function with test time augmentation.""" """Test function with test time augmentation."""
pass pass
......
autonomous_driving/Online-HD-Map-Construction/src/models/mapers/vectormapnet.py
View file @ 41b18fd8
import mmcv
import numpy as np import numpy as np
import torch import torch
import torch.nn as nn import torch.nn as nn
import torch.nn.functional as F from mmdet3d.models.builder import build_backbone, build_head, build_neck
from torch.nn.utils.rnn import pad_sequence from torch.nn.utils.rnn import pad_sequence
from torchvision.models.resnet import resnet18, resnet50 from torchvision.models.resnet import resnet18
from mmdet3d.models.builder import (build_backbone, build_head, from .base_mapper import MAPPERS, BaseMapper
build_neck)
from .base_mapper import BaseMapper, MAPPERS
@MAPPERS.register_module() @MAPPERS.register_module()
...@@ -31,8 +27,7 @@ class VectorMapNet(BaseMapper): ...@@ -31,8 +27,7 @@ class VectorMapNet(BaseMapper):
model_name=None, **kwargs): model_name=None, **kwargs):
super(VectorMapNet, self).__init__() super(VectorMapNet, self).__init__()
# Attribute
#Attribute
self.model_name = model_name self.model_name = model_name
self.last_epoch = None self.last_epoch = None
self.only_det = only_det self.only_det = only_det
...@@ -59,11 +54,10 @@ class VectorMapNet(BaseMapper): ...@@ -59,11 +54,10 @@ class VectorMapNet(BaseMapper):
) )
# BEV # BEV
if hasattr(self.backbone,'bev_w'): if hasattr(self.backbone, 'bev_w'):
self.bev_w = self.backbone.bev_w self.bev_w = self.backbone.bev_w
self.bev_h = self.backbone.bev_h self.bev_h = self.backbone.bev_h
self.head = build_head(head_cfg) self.head = build_head(head_cfg)
def multiscale_neck(self, bev_embedding): def multiscale_neck(self, bev_embedding):
...@@ -97,7 +91,7 @@ class VectorMapNet(BaseMapper): ...@@ -97,7 +91,7 @@ class VectorMapNet(BaseMapper):
if self.last_epoch is None: if self.last_epoch is None:
self.last_epoch = [batch, img, img_metas, valid_idx, points] self.last_epoch = [batch, img, img_metas, valid_idx, points]
if len(valid_idx)==0: if len(valid_idx) == 0:
batch, img, img_metas, valid_idx, points = self.last_epoch batch, img, img_metas, valid_idx, points = self.last_epoch
else: else:
del self.last_epoch del self.last_epoch
...@@ -184,8 +178,8 @@ class VectorMapNet(BaseMapper): ...@@ -184,8 +178,8 @@ class VectorMapNet(BaseMapper):
return None, None, None, valid_idx, None return None, None, None, valid_idx, None
batch = {} batch = {}
batch['det'] = format_det(polys,device) batch['det'] = format_det(polys, device)
batch['gen'] = format_gen(polys,device) batch['gen'] = format_gen(polys, device)
return batch, imgs, img_metas, valid_idx, points return batch, imgs, img_metas, valid_idx, points
...@@ -193,7 +187,7 @@ class VectorMapNet(BaseMapper): ...@@ -193,7 +187,7 @@ class VectorMapNet(BaseMapper):
pad_points = pad_sequence(points, batch_first=True) pad_points = pad_sequence(points, batch_first=True)
points_mask = torch.zeros_like(pad_points[:,:,0]).bool() points_mask = torch.zeros_like(pad_points[:, :, 0]).bool()
for i in range(len(points)): for i in range(len(points)):
valid_num = points[i].shape[0] valid_num = points[i].shape[0]
points_mask[i][:valid_num] = True points_mask[i][:valid_num] = True
...@@ -202,15 +196,13 @@ class VectorMapNet(BaseMapper): ...@@ -202,15 +196,13 @@ class VectorMapNet(BaseMapper):
def format_det(polys, device): def format_det(polys, device):
batch = { batch = {
'class_label':[], 'class_label': [],
'batch_idx':[], 'batch_idx': [],
'bbox': [], 'bbox': [],
} }
for batch_idx, poly in enumerate(polys): for batch_idx, poly in enumerate(polys):
keypoint_label = torch.from_numpy(poly['det_label']).to(device) keypoint_label = torch.from_numpy(poly['det_label']).to(device)
keypoint = torch.from_numpy(poly['keypoint']).to(device) keypoint = torch.from_numpy(poly['keypoint']).to(device)
...@@ -220,8 +212,7 @@ def format_det(polys, device): ...@@ -220,8 +212,7 @@ def format_det(polys, device):
return batch return batch
def format_gen(polys,device): def format_gen(polys, device):
line_cls = [] line_cls = []
polylines, polyline_masks, polyline_weights = [], [], [] polylines, polyline_masks, polyline_weights = [], [], []
bbox, line_cls, line_bs_idx = [], [], [] bbox, line_cls, line_bs_idx = [], [], []
...@@ -230,13 +221,13 @@ def format_gen(polys,device): ...@@ -230,13 +221,13 @@ def format_gen(polys,device):
# convert to cuda tensor # convert to cuda tensor
for k in poly.keys(): for k in poly.keys():
if isinstance(poly[k],np.ndarray): if isinstance(poly[k], np.ndarray):
poly[k] = torch.from_numpy(poly[k]).to(device) poly[k] = torch.from_numpy(poly[k]).to(device)
else: else:
poly[k] = [torch.from_numpy(v).to(device) for v in poly[k]] poly[k] = [torch.from_numpy(v).to(device) for v in poly[k]]
line_cls += poly['gen_label'] line_cls += poly['gen_label']
line_bs_idx += [batch_idx]*len(poly['gen_label']) line_bs_idx += [batch_idx] * len(poly['gen_label'])
# condition # condition
bbox += poly['qkeypoint'] bbox += poly['qkeypoint']
......
autonomous_driving/Online-HD-Map-Construction/src/models/transformer_utils/__init__.py
View file @ 41b18fd8
from .deformable_transformer import DeformableDetrTransformer_, DeformableDetrTransformerDecoder_
from .base_transformer import PlaceHolderEncoder
\ No newline at end of file
autonomous_driving/Online-HD-Map-Construction/src/models/transformer_utils/base_transformer.py
View file @ 41b18fd8
import numpy as np
import torch
import torch.nn as nn import torch.nn as nn
import torch.nn.functional as F from mmcv.cnn.bricks.registry import TRANSFORMER_LAYER_SEQUENCE
from mmcv.cnn import xavier_init, constant_init
from mmcv.cnn.bricks.registry import (ATTENTION,
TRANSFORMER_LAYER_SEQUENCE)
from mmcv.cnn.bricks.transformer import (MultiScaleDeformableAttention,
TransformerLayerSequence,
build_transformer_layer_sequence)
from mmcv.runner.base_module import BaseModule
from mmdet.models.utils.builder import TRANSFORMER
@TRANSFORMER_LAYER_SEQUENCE.register_module() @TRANSFORMER_LAYER_SEQUENCE.register_module()
class PlaceHolderEncoder(nn.Module): class PlaceHolderEncoder(nn.Module):
...@@ -21,5 +10,4 @@ class PlaceHolderEncoder(nn.Module): ...@@ -21,5 +10,4 @@ class PlaceHolderEncoder(nn.Module):
self.embed_dims = embed_dims self.embed_dims = embed_dims
def forward(self, *args, query=None, **kwargs): def forward(self, *args, query=None, **kwargs):
return query return query
autonomous_driving/Online-HD-Map-Construction/src/models/transformer_utils/deformable_transformer.py
View file @ 41b18fd8
...@@ -4,18 +4,12 @@ import warnings ...@@ -4,18 +4,12 @@ import warnings
import torch import torch
import torch.nn as nn import torch.nn as nn
from mmcv.cnn import build_activation_layer, build_norm_layer, xavier_init from mmcv.cnn import xavier_init
from mmcv.cnn.bricks.registry import (TRANSFORMER_LAYER, from mmcv.cnn.bricks.registry import TRANSFORMER_LAYER_SEQUENCE
TRANSFORMER_LAYER_SEQUENCE) from mmcv.cnn.bricks.transformer import TransformerLayerSequence
from mmcv.cnn.bricks.transformer import (BaseTransformerLayer,
TransformerLayerSequence,
build_transformer_layer_sequence)
from mmcv.runner.base_module import BaseModule
from torch.nn.init import normal_
from mmdet.models.utils.builder import TRANSFORMER from mmdet.models.utils.builder import TRANSFORMER
from mmdet.models.utils.transformer import Transformer from mmdet.models.utils.transformer import Transformer
from torch.nn.init import normal_
try: try:
from mmcv.ops.multi_scale_deform_attn import MultiScaleDeformableAttention from mmcv.ops.multi_scale_deform_attn import MultiScaleDeformableAttention
...@@ -27,6 +21,7 @@ except ImportError: ...@@ -27,6 +21,7 @@ except ImportError:
from .fp16_dattn import MultiScaleDeformableAttentionFp16 from .fp16_dattn import MultiScaleDeformableAttentionFp16
def inverse_sigmoid(x, eps=1e-5): def inverse_sigmoid(x, eps=1e-5):
"""Inverse function of sigmoid. """Inverse function of sigmoid.
Args: Args:
...@@ -44,6 +39,7 @@ def inverse_sigmoid(x, eps=1e-5): ...@@ -44,6 +39,7 @@ def inverse_sigmoid(x, eps=1e-5):
x2 = (1 - x).clamp(min=eps) x2 = (1 - x).clamp(min=eps)
return torch.log(x1 / x2) return torch.log(x1 / x2)
@TRANSFORMER_LAYER_SEQUENCE.register_module() @TRANSFORMER_LAYER_SEQUENCE.register_module()
class DeformableDetrTransformerDecoder_(TransformerLayerSequence): class DeformableDetrTransformerDecoder_(TransformerLayerSequence):
"""Implements the decoder in DETR transformer. """Implements the decoder in DETR transformer.
...@@ -94,13 +90,13 @@ class DeformableDetrTransformerDecoder_(TransformerLayerSequence): ...@@ -94,13 +90,13 @@ class DeformableDetrTransformerDecoder_(TransformerLayerSequence):
for lid, layer in enumerate(self.layers): for lid, layer in enumerate(self.layers):
reference_points_input = \ reference_points_input = \
reference_points[:, :, None,:self.kp_coord_dim] * \ reference_points[:, :, None, :self.kp_coord_dim] * \
valid_ratios[:, None,:,:self.kp_coord_dim] valid_ratios[:, None, :, :self.kp_coord_dim]
# if reference_points.shape[-1] == 3 and self.kp_coord_dim==2: # if reference_points.shape[-1] == 3 and self.kp_coord_dim==2:
output = layer( output = layer(
output, output,
*args, *args,
reference_points=reference_points_input[...,:self.kp_coord_dim], reference_points=reference_points_input[..., :self.kp_coord_dim],
**kwargs) **kwargs)
output = output.permute(1, 0, 2) output = output.permute(1, 0, 2)
...@@ -108,11 +104,12 @@ class DeformableDetrTransformerDecoder_(TransformerLayerSequence): ...@@ -108,11 +104,12 @@ class DeformableDetrTransformerDecoder_(TransformerLayerSequence):
tmp = reg_branches[lid](output) tmp = reg_branches[lid](output)
new_reference_points = tmp new_reference_points = tmp
new_reference_points[..., :self.kp_coord_dim] = tmp[ new_reference_points[..., :self.kp_coord_dim] = tmp[
..., :self.kp_coord_dim] + inverse_sigmoid(reference_points) ..., :self.kp_coord_dim] + inverse_sigmoid(
reference_points)
new_reference_points = new_reference_points.sigmoid() new_reference_points = new_reference_points.sigmoid()
if reference_points.shape[-1] == 3 and self.kp_coord_dim==2: if reference_points.shape[-1] == 3 and self.kp_coord_dim == 2:
reference_points[...,-1] = tmp[...,-1].sigmoid().detach() reference_points[..., -1] = tmp[..., -1].sigmoid().detach()
reference_points[...,:self.coord_dim] = new_reference_points.detach() reference_points[..., :self.coord_dim] = new_reference_points.detach()
output = output.permute(1, 0, 2) output = output.permute(1, 0, 2)
if self.return_intermediate: if self.return_intermediate:
...@@ -174,7 +171,7 @@ class DeformableDetrTransformer_(Transformer): ...@@ -174,7 +171,7 @@ class DeformableDetrTransformer_(Transformer):
for m in self.modules(): for m in self.modules():
if isinstance(m, MultiScaleDeformableAttention): if isinstance(m, MultiScaleDeformableAttention):
m.init_weights() m.init_weights()
elif isinstance(m,MultiScaleDeformableAttentionFp16): elif isinstance(m, MultiScaleDeformableAttentionFp16):
m.init_weights() m.init_weights()
if not self.as_two_stage: if not self.as_two_stage:
xavier_init(self.reference_points_embed, distribution='uniform', bias=0.) xavier_init(self.reference_points_embed, distribution='uniform', bias=0.)
...@@ -231,7 +228,7 @@ class DeformableDetrTransformer_(Transformer): ...@@ -231,7 +228,7 @@ class DeformableDetrTransformer_(Transformer):
scale = 2 * math.pi scale = 2 * math.pi
dim_t = torch.arange( dim_t = torch.arange(
num_pos_feats, dtype=torch.float32, device=proposals.device) num_pos_feats, dtype=torch.float32, device=proposals.device)
dim_t = temperature**(2 * (dim_t // 2) / num_pos_feats) dim_t = temperature ** (2 * (dim_t // 2) / num_pos_feats)
# N, L, 4 # N, L, 4
proposals = proposals.sigmoid() * scale proposals = proposals.sigmoid() * scale
# N, L, 4, 128 # N, L, 4, 128
...@@ -317,7 +314,7 @@ class DeformableDetrTransformer_(Transformer): ...@@ -317,7 +314,7 @@ class DeformableDetrTransformer_(Transformer):
spatial_shapes = torch.as_tensor( spatial_shapes = torch.as_tensor(
spatial_shapes, dtype=torch.long, device=feat_flatten.device) spatial_shapes, dtype=torch.long, device=feat_flatten.device)
level_start_index = torch.cat((spatial_shapes.new_zeros( level_start_index = torch.cat((spatial_shapes.new_zeros(
(1, )), spatial_shapes.prod(1).cumsum(0)[:-1])) (1,)), spatial_shapes.prod(1).cumsum(0)[:-1]))
valid_ratios = torch.stack( valid_ratios = torch.stack(
[self.get_valid_ratio(m) for m in mlvl_masks], 1) [self.get_valid_ratio(m) for m in mlvl_masks], 1)
......
autonomous_driving/Online-HD-Map-Construction/src/models/transformer_utils/fp16_dattn.py
View file @ 41b18fd8
from turtle import forward
import warnings import warnings
try: try:
from mmcv.ops.multi_scale_deform_attn import MultiScaleDeformableAttention from mmcv.ops.multi_scale_deform_attn import MultiScaleDeformableAttention
except ImportError: except ImportError:
...@@ -7,12 +7,6 @@ except ImportError: ...@@ -7,12 +7,6 @@ except ImportError:
'`MultiScaleDeformableAttention` in MMCV has been moved to ' '`MultiScaleDeformableAttention` in MMCV has been moved to '
'`mmcv.ops.multi_scale_deform_attn`, please update your MMCV') '`mmcv.ops.multi_scale_deform_attn`, please update your MMCV')
from mmcv.cnn.bricks.transformer import MultiScaleDeformableAttention from mmcv.cnn.bricks.transformer import MultiScaleDeformableAttention
from mmcv.runner import force_fp32, auto_fp16
from mmcv.cnn.bricks.registry import ATTENTION
from mmcv.runner.base_module import BaseModule, ModuleList, Sequential
from mmcv.cnn.bricks.transformer import build_attention
import math import math
import warnings import warnings
...@@ -20,13 +14,15 @@ import warnings ...@@ -20,13 +14,15 @@ import warnings
import torch import torch
import torch.nn as nn import torch.nn as nn
import torch.nn.functional as F import torch.nn.functional as F
from torch.autograd.function import Function, once_differentiable
from mmcv import deprecated_api_warning from mmcv import deprecated_api_warning
from mmcv.cnn import constant_init, xavier_init from mmcv.cnn import constant_init, xavier_init
from mmcv.cnn.bricks.registry import ATTENTION from mmcv.cnn.bricks.registry import ATTENTION
from mmcv.runner import BaseModule from mmcv.cnn.bricks.transformer import build_attention
from mmcv.runner import force_fp32
from mmcv.runner.base_module import BaseModule
from mmcv.utils import ext_loader from mmcv.utils import ext_loader
from torch.autograd.function import Function, once_differentiable
ext_module = ext_loader.load_ext( ext_module = ext_loader.load_ext(
'_ext', ['ms_deform_attn_backward', 'ms_deform_attn_forward']) '_ext', ['ms_deform_attn_backward', 'ms_deform_attn_forward'])
from torch.cuda.amp import custom_bwd, custom_fwd from torch.cuda.amp import custom_bwd, custom_fwd
...@@ -35,16 +31,15 @@ from torch.cuda.amp import custom_bwd, custom_fwd ...@@ -35,16 +31,15 @@ from torch.cuda.amp import custom_bwd, custom_fwd
@ATTENTION.register_module() @ATTENTION.register_module()
class MultiScaleDeformableAttentionFp16(BaseModule): class MultiScaleDeformableAttentionFp16(BaseModule):
def __init__(self, attn_cfg=None,init_cfg=None,**kwarg): def __init__(self, attn_cfg=None, init_cfg=None, **kwarg):
super(MultiScaleDeformableAttentionFp16,self).__init__(init_cfg) super(MultiScaleDeformableAttentionFp16, self).__init__(init_cfg)
# import ipdb; ipdb.set_trace() # import ipdb; ipdb.set_trace()
self.deformable_attention = build_attention(attn_cfg) self.deformable_attention = build_attention(attn_cfg)
self.deformable_attention.init_weights() self.deformable_attention.init_weights()
self.fp16_enabled = False self.fp16_enabled = False
@force_fp32(apply_to=('query', 'key', 'value', 'query_pos', 'reference_points', 'identity'))
@force_fp32(apply_to=('query', 'key', 'value', 'query_pos', 'reference_points','identity'))
def forward(self, query, def forward(self, query,
key=None, key=None,
value=None, value=None,
...@@ -64,8 +59,7 @@ class MultiScaleDeformableAttentionFp16(BaseModule): ...@@ -64,8 +59,7 @@ class MultiScaleDeformableAttentionFp16(BaseModule):
key_padding_mask=key_padding_mask, key_padding_mask=key_padding_mask,
reference_points=reference_points, reference_points=reference_points,
spatial_shapes=spatial_shapes, spatial_shapes=spatial_shapes,
level_start_index=level_start_index,**kwargs) level_start_index=level_start_index, **kwargs)
class MultiScaleDeformableAttnFunctionFp32(Function): class MultiScaleDeformableAttnFunctionFp32(Function):
...@@ -118,7 +112,7 @@ class MultiScaleDeformableAttnFunctionFp32(Function): ...@@ -118,7 +112,7 @@ class MultiScaleDeformableAttnFunctionFp32(Function):
Tuple[Tensor]: Gradient Tuple[Tensor]: Gradient
of input tensors in forward. of input tensors in forward.
""" """
value, value_spatial_shapes, value_level_start_index,\ value, value_spatial_shapes, value_level_start_index, \
sampling_locations, attention_weights = ctx.saved_tensors sampling_locations, attention_weights = ctx.saved_tensors
grad_value = torch.zeros_like(value) grad_value = torch.zeros_like(value)
grad_sampling_loc = torch.zeros_like(sampling_locations) grad_sampling_loc = torch.zeros_like(sampling_locations)
...@@ -161,7 +155,7 @@ def multi_scale_deformable_attn_pytorch(value, value_spatial_shapes, ...@@ -161,7 +155,7 @@ def multi_scale_deformable_attn_pytorch(value, value_spatial_shapes,
""" """
bs, _, num_heads, embed_dims = value.shape bs, _, num_heads, embed_dims = value.shape
_, num_queries, num_heads, num_levels, num_points, _ =\ _, num_queries, num_heads, num_levels, num_points, _ = \
sampling_locations.shape sampling_locations.shape
value_list = value.split([H_ * W_ for H_, W_ in value_spatial_shapes], value_list = value.split([H_ * W_ for H_, W_ in value_spatial_shapes],
dim=1) dim=1)
......
autonomous_driving/Online-HD-Map-Construction/tools/evaluate_submission.py
View file @ 41b18fd8
import sys
import os import os
import sys
sys.path.append(os.path.abspath('.')) sys.path.append(os.path.abspath('.'))
from src.datasets.evaluation.vector_eval import VectorEvaluate
import argparse import argparse
from src.datasets.evaluation.vector_eval import VectorEvaluate
def parse_args(): def parse_args():
parser = argparse.ArgumentParser( parser = argparse.ArgumentParser(
description='Evaluate a submission file') description='Evaluate a submission file')
...@@ -17,12 +20,14 @@ def parse_args(): ...@@ -17,12 +20,14 @@ def parse_args():
args = parser.parse_args() args = parser.parse_args()
return args return args
def main(args): def main(args):
evaluator = VectorEvaluate(args.gt, n_workers=0) evaluator = VectorEvaluate(args.gt, n_workers=0)
results = evaluator.evaluate(args.submission) results = evaluator.evaluate(args.submission)
print(results) print(results)
if __name__ == '__main__': if __name__ == '__main__':
args = parse_args() args = parse_args()
main(args) main(args)
autonomous_driving/Online-HD-Map-Construction/tools/mmdet_test.py
View file @ 41b18fd8
...@@ -9,7 +9,6 @@ import torch ...@@ -9,7 +9,6 @@ import torch
import torch.distributed as dist import torch.distributed as dist
from mmcv.image import tensor2imgs from mmcv.image import tensor2imgs
from mmcv.runner import get_dist_info from mmcv.runner import get_dist_info
from mmdet.core import encode_mask_results from mmdet.core import encode_mask_results
...@@ -120,7 +119,7 @@ def collect_results_cpu(result_part, size, tmpdir=None): ...@@ -120,7 +119,7 @@ def collect_results_cpu(result_part, size, tmpdir=None):
if tmpdir is None: if tmpdir is None:
MAX_LEN = 512 MAX_LEN = 512
# 32 is whitespace # 32 is whitespace
dir_tensor = torch.full((MAX_LEN, ), dir_tensor = torch.full((MAX_LEN,),
32, 32,
dtype=torch.uint8, dtype=torch.uint8,
device='cuda') device='cuda')
......
autonomous_driving/Online-HD-Map-Construction/tools/mmdet_train.py
View file @ 41b18fd8
...@@ -8,7 +8,6 @@ from mmcv.runner import (HOOKS, DistSamplerSeedHook, EpochBasedRunner, ...@@ -8,7 +8,6 @@ from mmcv.runner import (HOOKS, DistSamplerSeedHook, EpochBasedRunner,
Fp16OptimizerHook, OptimizerHook, build_optimizer, Fp16OptimizerHook, OptimizerHook, build_optimizer,
build_runner) build_runner)
from mmcv.utils import build_from_cfg from mmcv.utils import build_from_cfg
from mmdet.core import DistEvalHook, EvalHook from mmdet.core import DistEvalHook, EvalHook
from mmdet.datasets import (build_dataloader, build_dataset, from mmdet.datasets import (build_dataloader, build_dataset,
replace_ImageToTensor) replace_ImageToTensor)
......
autonomous_driving/Online-HD-Map-Construction/tools/test.py
View file @ 41b18fd8
import argparse import argparse
import mmcv
import os import os
import os.path as osp import os.path as osp
import torch import torch
import warnings from mmcv import Config
from mmcv import Config, DictAction
from mmcv.cnn import fuse_conv_bn from mmcv.cnn import fuse_conv_bn
from mmcv.parallel import MMDataParallel, MMDistributedDataParallel from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
from mmcv.runner import (get_dist_info, init_dist, load_checkpoint, from mmcv.runner import (get_dist_info, init_dist, load_checkpoint,
wrap_fp16_model) wrap_fp16_model)
from mmdet3d.apis import single_gpu_test from mmdet3d.apis import single_gpu_test
from mmdet3d.datasets import build_dataloader, build_dataset from mmdet3d.datasets import build_dataloader, build_dataset
from mmdet3d.models import build_model from mmdet3d.models import build_model
from mmdet.datasets import replace_ImageToTensor
from mmdet_test import multi_gpu_test from mmdet_test import multi_gpu_test
from mmdet_train import set_random_seed from mmdet_train import set_random_seed
from mmdet.datasets import replace_ImageToTensor
def parse_args(): def parse_args():
...@@ -106,8 +104,8 @@ def main(): ...@@ -106,8 +104,8 @@ def main():
plg_lib = importlib.import_module(_module_path) plg_lib = importlib.import_module(_module_path)
plugin_dirs = cfg.plugin_dir plugin_dirs = cfg.plugin_dir
if not isinstance(plugin_dirs,list): if not isinstance(plugin_dirs, list):
plugin_dirs = [plugin_dirs,] plugin_dirs = [plugin_dirs, ]
for plugin_dir in plugin_dirs: for plugin_dir in plugin_dirs:
import_path(plugin_dir) import_path(plugin_dir)
...@@ -154,7 +152,7 @@ def main(): ...@@ -154,7 +152,7 @@ def main():
osp.splitext(osp.basename(args.config))[0]) osp.splitext(osp.basename(args.config))[0])
cfg_data_dict.work_dir = cfg.work_dir cfg_data_dict.work_dir = cfg.work_dir
print('work_dir: ',cfg.work_dir) print('work_dir: ', cfg.work_dir)
dataset = build_dataset(cfg_data_dict) dataset = build_dataset(cfg_data_dict)
data_loader = build_dataloader( data_loader = build_dataloader(
dataset, dataset,
......
autonomous_driving/Online-HD-Map-Construction/tools/train.py
View file @ 41b18fd8
...@@ -2,26 +2,25 @@ from __future__ import division ...@@ -2,26 +2,25 @@ from __future__ import division
import argparse import argparse
import copy import copy
import mmcv
import os import os
import time import time
import torch
import warnings import warnings
from mmcv import Config, DictAction
from mmcv.runner import get_dist_info, init_dist
from os import path as osp from os import path as osp
import mmcv
import torch
from mmcv import Config, DictAction
from mmcv.runner import get_dist_info, init_dist
from mmdet import __version__ as mmdet_version from mmdet import __version__ as mmdet_version
from mmdet3d import __version__ as mmdet3d_version from mmdet3d import __version__ as mmdet3d_version
from mmdet3d.apis import train_model from mmdet3d.apis import train_model
from mmdet3d.datasets import build_dataset from mmdet3d.datasets import build_dataset
# from builder import build_model
from mmdet3d.models import build_model
from mmdet3d.utils import collect_env, get_root_logger from mmdet3d.utils import collect_env, get_root_logger
from mmseg import __version__ as mmseg_version
# warper # warper
from mmdet_train import set_random_seed from mmdet_train import set_random_seed
# from builder import build_model from mmseg import __version__ as mmseg_version
from mmdet3d.models import build_model
def parse_args(): def parse_args():
...@@ -126,8 +125,8 @@ def main(): ...@@ -126,8 +125,8 @@ def main():
plg_lib = importlib.import_module(_module_path) plg_lib = importlib.import_module(_module_path)
plugin_dirs = cfg.plugin_dir plugin_dirs = cfg.plugin_dir
if not isinstance(plugin_dirs,list): if not isinstance(plugin_dirs, list):
plugin_dirs = [plugin_dirs,] plugin_dirs = [plugin_dirs, ]
for plugin_dir in plugin_dirs: for plugin_dir in plugin_dirs:
import_path(plugin_dir) import_path(plugin_dir)
......
autonomous_driving/Online-HD-Map-Construction/tools/visualization/renderer.py
View file @ 41b18fd8
import os.path as osp
import os
import numpy as np
import copy import copy
import os
import os.path as osp
import cv2 import cv2
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import numpy as np
from PIL import Image from PIL import Image
from shapely.geometry import LineString from shapely.geometry import LineString
def remove_nan_values(uv): def remove_nan_values(uv):
is_u_valid = np.logical_not(np.isnan(uv[:, 0])) is_u_valid = np.logical_not(np.isnan(uv[:, 0]))
is_v_valid = np.logical_not(np.isnan(uv[:, 1])) is_v_valid = np.logical_not(np.isnan(uv[:, 1]))
...@@ -15,6 +17,7 @@ def remove_nan_values(uv): ...@@ -15,6 +17,7 @@ def remove_nan_values(uv):
uv_valid = uv[is_uv_valid] uv_valid = uv[is_uv_valid]
return uv_valid return uv_valid
def points_ego2img(pts_ego, extrinsics, intrinsics): def points_ego2img(pts_ego, extrinsics, intrinsics):
pts_ego_4d = np.concatenate([pts_ego, np.ones([len(pts_ego), 1])], axis=-1) pts_ego_4d = np.concatenate([pts_ego, np.ones([len(pts_ego), 1])], axis=-1)
pts_cam_4d = extrinsics @ pts_ego_4d.T pts_cam_4d = extrinsics @ pts_ego_4d.T
...@@ -26,6 +29,7 @@ def points_ego2img(pts_ego, extrinsics, intrinsics): ...@@ -26,6 +29,7 @@ def points_ego2img(pts_ego, extrinsics, intrinsics):
return uv, depth return uv, depth
def interp_fixed_dist(line, sample_dist): def interp_fixed_dist(line, sample_dist):
''' Interpolate a line at fixed interval. ''' Interpolate a line at fixed interval.
...@@ -39,13 +43,14 @@ def interp_fixed_dist(line, sample_dist): ...@@ -39,13 +43,14 @@ def interp_fixed_dist(line, sample_dist):
distances = list(np.arange(sample_dist, line.length, sample_dist)) distances = list(np.arange(sample_dist, line.length, sample_dist))
# make sure to sample at least two points when sample_dist > line.length # make sure to sample at least two points when sample_dist > line.length
distances = [0,] + distances + [line.length,] distances = [0, ] + distances + [line.length, ]
sampled_points = np.array([list(line.interpolate(distance).coords) sampled_points = np.array([list(line.interpolate(distance).coords)
for distance in distances]).squeeze() for distance in distances]).squeeze()
return sampled_points return sampled_points
def draw_polyline_ego_on_img(polyline_ego, img_bgr, extrinsics, intrinsics, color_bgr, thickness): def draw_polyline_ego_on_img(polyline_ego, img_bgr, extrinsics, intrinsics, color_bgr, thickness):
# if 2-dimension, assume z=0 # if 2-dimension, assume z=0
if polyline_ego.shape[1] == 2: if polyline_ego.shape[1] == 2:
...@@ -103,6 +108,7 @@ def draw_polyline_ego_on_img(polyline_ego, img_bgr, extrinsics, intrinsics, colo ...@@ -103,6 +108,7 @@ def draw_polyline_ego_on_img(polyline_ego, img_bgr, extrinsics, intrinsics, colo
# thickness_px=thickness, # thickness_px=thickness,
# ) # )
def draw_visible_polyline_cv2(line, valid_pts_bool, image, color, thickness_px): def draw_visible_polyline_cv2(line, valid_pts_bool, image, color, thickness_px):
"""Draw a polyline onto an image using given line segments. """Draw a polyline onto an image using given line segments.
Args: Args:
...@@ -147,8 +153,9 @@ COLOR_MAPS_PLT = { ...@@ -147,8 +153,9 @@ COLOR_MAPS_PLT = {
} }
CAM_NAMES_AV2 = ['ring_front_center', 'ring_front_right', 'ring_front_left', CAM_NAMES_AV2 = ['ring_front_center', 'ring_front_right', 'ring_front_left',
'ring_rear_right','ring_rear_left', 'ring_side_right', 'ring_side_left', 'ring_rear_right', 'ring_rear_left', 'ring_side_right', 'ring_side_left',
] ]
class Renderer(object): class Renderer(object):
"""Render map elements on image views. """Render map elements on image views.
...@@ -171,8 +178,8 @@ class Renderer(object): ...@@ -171,8 +178,8 @@ class Renderer(object):
map_path = os.path.join(out_dir, 'map.jpg') map_path = os.path.join(out_dir, 'map.jpg')
plt.figure(figsize=(self.roi_size[0], self.roi_size[1])) plt.figure(figsize=(self.roi_size[0], self.roi_size[1]))
plt.xlim(-self.roi_size[0]/2 - 1, self.roi_size[0]/2 + 1) plt.xlim(-self.roi_size[0] / 2 - 1, self.roi_size[0] / 2 + 1)
plt.ylim(-self.roi_size[1]/2 - 1, self.roi_size[1]/2 + 1) plt.ylim(-self.roi_size[1] / 2 - 1, self.roi_size[1] / 2 + 1)
plt.axis('off') plt.axis('off')
plt.imshow(car_img, extent=[-1.5, 1.5, -1.2, 1.2]) plt.imshow(car_img, extent=[-1.5, 1.5, -1.2, 1.2])
......
autonomous_driving/Online-HD-Map-Construction/tools/visualization/visualize.py
View file @ 41b18fd8
import argparse import argparse
import mmcv
from mmcv import Config
import os import os
import mmcv
from renderer import Renderer from renderer import Renderer
CAT2ID = { CAT2ID = {
...@@ -14,6 +14,7 @@ ID2CAT = {v: k for k, v in CAT2ID.items()} ...@@ -14,6 +14,7 @@ ID2CAT = {v: k for k, v in CAT2ID.items()}
ROI_SIZE = (60, 30) ROI_SIZE = (60, 30)
def parse_args(): def parse_args():
parser = argparse.ArgumentParser( parser = argparse.ArgumentParser(
description='Visualize groundtruth and results') description='Visualize groundtruth and results')
...@@ -37,6 +38,7 @@ def parse_args(): ...@@ -37,6 +38,7 @@ def parse_args():
return args return args
def import_plugin(cfg): def import_plugin(cfg):
''' '''
import modules, registry will be update import modules, registry will be update
...@@ -59,8 +61,8 @@ def import_plugin(cfg): ...@@ -59,8 +61,8 @@ def import_plugin(cfg):
plg_lib = importlib.import_module(_module_path) plg_lib = importlib.import_module(_module_path)
plugin_dirs = cfg.plugin_dir plugin_dirs = cfg.plugin_dir
if not isinstance(plugin_dirs,list): if not isinstance(plugin_dirs, list):
plugin_dirs = [plugin_dirs,] plugin_dirs = [plugin_dirs, ]
for plugin_dir in plugin_dirs: for plugin_dir in plugin_dirs:
import_path(plugin_dir) import_path(plugin_dir)
...@@ -74,6 +76,7 @@ def import_plugin(cfg): ...@@ -74,6 +76,7 @@ def import_plugin(cfg):
print(f'importing {_module_path}/') print(f'importing {_module_path}/')
plg_lib = importlib.import_module(_module_path) plg_lib = importlib.import_module(_module_path)
def main(args): def main(args):
log_id = args.log_id log_id = args.log_id
ann = mmcv.load(args.ann_file) ann = mmcv.load(args.ann_file)
......
autonomous_driving/README.md
View file @ 41b18fd8
<div id="top" align="center"> <div id="top" align="center">
# InternImage for CVPR 2023 Workshop on End-to-End Autonomous Driving # InternImage for CVPR 2023 Workshop on End-to-End Autonomous Driving
</div>
</div>
## 1. InternImage-based Baseline for CVPR23 Occupancy Prediction Challenge ## 1. InternImage-based Baseline for CVPR23 Occupancy Prediction Challenge
We achieve an improvement of 1.44 in MIOU baseline by leveraging the InterImage-based model. We achieve an improvement of 1.44 in MIOU baseline by leveraging the InterImage-based model.
model name|weight| mIoU | others | barrier | bicycle | bus | car | construction_vehicle | motorcycle | pedestrian | traffic_cone | trailer | truck | driveable_surface | other_flat | sidewalk | terrain | manmade | vegetation | | model name | weight | mIoU | others | barrier | bicycle | bus | car | construction_vehicle | motorcycle | pedestrian | traffic_cone | trailer | truck | driveable_surface | other_flat | sidewalk | terrain | manmade | vegetation |
----|:----------:| :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :--: | :----------------------: | :---: | :------: | :------: | | ---------------------- | :---------------------------------------------------------------------------------------------------: | :---: | :----: | :-----: | :-----: | :---: | :---: | :------------------: | :--------: | :--------: | :----------: | :-----: | :---: | :---------------: | :--------: | :------: | :-----: | :-----: | :--------: |
bevformer_intern-s_occ|[Google Drive](https://drive.google.com/file/d/1LV9K8hrskKf51xY1wbqTKzK7WZmVXEV_/view?usp=sharing)| 25.11 | 6.93 | 35.57 | 10.40 | 35.97 | 41.23 | 13.72 | 20.30 | 21.10 | 18.34 | 19.18 | 28.64 | 49.82 | 30.74 | 31.00 | 27.44 | 19.29 | 17.29 | | bevformer_intern-s_occ | [Google Drive](https://drive.google.com/file/d/1LV9K8hrskKf51xY1wbqTKzK7WZmVXEV_/view?usp=sharing) | 25.11 | 6.93 | 35.57 | 10.40 | 35.97 | 41.23 | 13.72 | 20.30 | 21.10 | 18.34 | 19.18 | 28.64 | 49.82 | 30.74 | 31.00 | 27.44 | 19.29 | 17.29 |
bevformer_base_occ|[Google Drive](https://drive.google.com/file/d/1NyoiosafAmne1qiABeNOPXR-P-y0i7_I/view?usp=share_link)| 23.67 | 5.03 | 38.79 | 9.98 | 34.41 | 41.09 | 13.24 | 16.50 | 18.15 | 17.83 | 18.66 | 27.70 | 48.95 | 27.73 | 29.08 | 25.38 | 15.41 | 14.46 | | bevformer_base_occ | [Google Drive](https://drive.google.com/file/d/1NyoiosafAmne1qiABeNOPXR-P-y0i7_I/view?usp=share_link) | 23.67 | 5.03 | 38.79 | 9.98 | 34.41 | 41.09 | 13.24 | 16.50 | 18.15 | 17.83 | 18.66 | 27.70 | 48.95 | 27.73 | 29.08 | 25.38 | 15.41 | 14.46 |
### Get Started ### Get Started
please refer to [README.md](./occupancy_prediction/README.md)
please refer to [README.md](./occupancy_prediction/README.md)
## 2. InternImage-based Baseline for Online HD Map Construction Challenge For Autonomous Driving ## 2. InternImage-based Baseline for Online HD Map Construction Challenge For Autonomous Driving
By incorporating the InterImage-based model, we observe an enhancement of 6.56 in mAP baseline. By incorporating the InterImage-based model, we observe an enhancement of 6.56 in mAP baseline.
model name|weight|$\mathrm{mAP}$ | $\mathrm{AP}_{pc}$ | $\mathrm{AP}_{div}$ | $\mathrm{AP}_{bound}$ | | model name | weight | $\\mathrm{mAP}$ | $\\mathrm{AP}\_{pc}$ | $\\mathrm{AP}\_{div}$ | $\\mathrm{AP}\_{bound}$ |
----|:----------:| :--: | :--: | :--: | :--: | | ------------------- | :---------------------------------------------------------------------------------------------------------------: | :-------------: | :------------------: | :-------------------: | :---------------------: |
vectormapnet_intern|[Checkpoint](https://github.com/OpenGVLab/InternImage/releases/download/track_model/vectormapnet_internimage.pth) | 49.35 | 45.05 | 56.78 | 46.22 | | vectormapnet_intern | [Checkpoint](https://github.com/OpenGVLab/InternImage/releases/download/track_model/vectormapnet_internimage.pth) | 49.35 | 45.05 | 56.78 | 46.22 |
vectormapnet_base|[Google Drive](https://drive.google.com/file/d/16D1CMinwA8PG1sd9PV9_WtHzcBohvO-D/view) | 42.79 | 37.22 | 50.47 | 40.68 | | vectormapnet_base | [Google Drive](https://drive.google.com/file/d/16D1CMinwA8PG1sd9PV9_WtHzcBohvO-D/view) | 42.79 | 37.22 | 50.47 | 40.68 |
### Get Started ### Get Started
please refer to [README.md](Online-HD-Map-Construction/README.md)
please refer to [README.md](Online-HD-Map-Construction/README.md)
## 3. InternImage-based Baseline for CVPR23 OpenLane-V2 Challenge ## 3. InternImage-based Baseline for CVPR23 OpenLane-V2 Challenge
Through the implementation of the InterImage-based model, we achieve an advancement of 0.009 in F-score baseline.
Through the implementation of the InterImage-based model, we achieve an advancement of 0.009 in F-score baseline.
| | OpenLane-V2 Score | DET<sub>l</sub> | DET<sub>t</sub> | TOP<sub>ll</sub> | TOP<sub>lt</sub> | F-Score | | | OpenLane-V2 Score | DET<sub>l</sub> | DET<sub>t</sub> | TOP<sub>ll</sub> | TOP<sub>lt</sub> | F-Score |
|-------------|-------------------|-----------------|-----------------|------------------|------------------|---------| | ----------- | ----------------- | --------------- | --------------- | ---------------- | ---------------- | ------- |
| base r50 | 0.292 | 0.183 | 0.457 | 0.022 | 0.143 | 0.215 | | base r50 | 0.292 | 0.183 | 0.457 | 0.022 | 0.143 | 0.215 |
| InternImage | 0.325 | 0.194 | 0.537 | 0.02 | 0.17 | 0.224 | | InternImage | 0.325 | 0.194 | 0.537 | 0.02 | 0.17 | 0.224 |
### Get Started ### Get Started
please refer to [README.md](./openlane-v2/README.md)
please refer to [README.md](./openlane-v2/README.md)
autonomous_driving/occupancy_prediction/CODE_OF_CONDUCT.md
View file @ 41b18fd8
...@@ -2,127 +2,101 @@ ...@@ -2,127 +2,101 @@
## Our Pledge ## Our Pledge
We as members, contributors, and leaders pledge to make participation in our We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for
community a harassment-free experience for everyone, regardless of age, body everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity
size, visible or invisible disability, ethnicity, sex characteristics, gender and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion,
identity and expression, level of experience, education, socio-economic status, or sexual identity and orientation.
nationality, personal appearance, race, religion, or sexual identity
and orientation.
We pledge to act and interact in ways that contribute to an open, welcoming, We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
diverse, inclusive, and healthy community.
## Our Standards ## Our Standards
Examples of behavior that contributes to a positive environment for our Examples of behavior that contributes to a positive environment for our community include:
community include:
* Demonstrating empathy and kindness toward other people - Demonstrating empathy and kindness toward other people
* Being respectful of differing opinions, viewpoints, and experiences - Being respectful of differing opinions, viewpoints, and experiences
* Giving and gracefully accepting constructive feedback - Giving and gracefully accepting constructive feedback
* Accepting responsibility and apologizing to those affected by our mistakes, - Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
and learning from the experience - Focusing on what is best not just for us as individuals, but for the overall community
* Focusing on what is best not just for us as individuals, but for the
overall community
Examples of unacceptable behavior include: Examples of unacceptable behavior include:
* The use of sexualized language or imagery, and sexual attention or - The use of sexualized language or imagery, and sexual attention or advances of any kind
advances of any kind - Trolling, insulting or derogatory comments, and personal or political attacks
* Trolling, insulting or derogatory comments, and personal or political attacks - Public or private harassment
* Public or private harassment - Publishing others' private information, such as a physical or email address, without their explicit permission
* Publishing others' private information, such as a physical or email - Other conduct which could reasonably be considered inappropriate in a professional setting
address, without their explicit permission
* Other conduct which could reasonably be considered inappropriate in a
professional setting
## Enforcement Responsibilities ## Enforcement Responsibilities
Community leaders are responsible for clarifying and enforcing our standards of Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take
acceptable behavior and will take appropriate and fair corrective action in appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive,
response to any behavior that they deem inappropriate, threatening, offensive,
or harmful. or harmful.
Community leaders have the right and responsibility to remove, edit, or reject Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits,
comments, commits, code, wiki edits, issues, and other contributions that are issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for
not aligned to this Code of Conduct, and will communicate reasons for moderation moderation decisions when appropriate.
decisions when appropriate.
## Scope ## Scope
This Code of Conduct applies within all community spaces, and also applies when This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing
an individual is officially representing the community in public spaces. the community in public spaces. Examples of representing our community include using an official e-mail address, posting
Examples of representing our community include using an official e-mail address, via an official social media account, or acting as an appointed representative at an online or offline event.
posting via an official social media account, or acting as an appointed
representative at an online or offline event.
## Enforcement ## Enforcement
Instances of abusive, harassing, or otherwise unacceptable behavior may be Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible
reported to the community leaders responsible for enforcement at for enforcement at contact@opendrivelab.com. All complaints will be reviewed and investigated promptly and fairly.
contact@opendrivelab.com.
All complaints will be reviewed and investigated promptly and fairly.
All community leaders are obligated to respect the privacy and security of the All community leaders are obligated to respect the privacy and security of the reporter of any incident.
reporter of any incident.
## Enforcement Guidelines ## Enforcement Guidelines
Community leaders will follow these Community Impact Guidelines in determining Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem
the consequences for any action they deem in violation of this Code of Conduct: in violation of this Code of Conduct:
### 1. Correction ### 1. Correction
**Community Impact**: Use of inappropriate language or other behavior deemed **Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the
unprofessional or unwelcome in the community. community.
**Consequence**: A private, written warning from community leaders, providing **Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation
clarity around the nature of the violation and an explanation of why the and an explanation of why the behavior was inappropriate. A public apology may be requested.
behavior was inappropriate. A public apology may be requested.
### 2. Warning ### 2. Warning
**Community Impact**: A violation through a single incident or series **Community Impact**: A violation through a single incident or series of actions.
of actions.
**Consequence**: A warning with consequences for continued behavior. No **Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including
interaction with the people involved, including unsolicited interaction with unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding
those enforcing the Code of Conduct, for a specified period of time. This interactions in community spaces as well as external channels like social media. Violating these terms may lead to a
includes avoiding interactions in community spaces as well as external channels temporary or permanent ban.
like social media. Violating these terms may lead to a temporary or
permanent ban.
### 3. Temporary Ban ### 3. Temporary Ban
**Community Impact**: A serious violation of community standards, including **Community Impact**: A serious violation of community standards, including sustained inappropriate behavior.
sustained inappropriate behavior.
**Consequence**: A temporary ban from any sort of interaction or public **Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified
communication with the community for a specified period of time. No public or period of time. No public or private interaction with the people involved, including unsolicited interaction with those
private interaction with the people involved, including unsolicited interaction enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
with those enforcing the Code of Conduct, is allowed during this period.
Violating these terms may lead to a permanent ban.
### 4. Permanent Ban ### 4. Permanent Ban
**Community Impact**: Demonstrating a pattern of violation of community **Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate
standards, including sustained inappropriate behavior, harassment of an behavior, harassment of an individual, or aggression toward or disparagement of classes of individuals.
individual, or aggression toward or disparagement of classes of individuals.
**Consequence**: A permanent ban from any sort of public interaction within **Consequence**: A permanent ban from any sort of public interaction within the community.
the community.
## Attribution ## Attribution
This Code of Conduct is adapted from the [Contributor Covenant][homepage], This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.0, available at
version 2.0, available at
https://www.contributor-covenant.org/version/2/0/code_of_conduct.html. https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
Community Impact Guidelines were inspired by [Mozilla's code of conduct Community Impact Guidelines were inspired
enforcement ladder](https://github.com/mozilla/diversity). by [Mozilla's code of conduct enforcement ladder](https://github.com/mozilla/diversity).
[homepage]: https://www.contributor-covenant.org
For answers to common questions about this code of conduct, see the FAQ at For answers to common questions about this code of conduct, see the FAQ at
https://www.contributor-covenant.org/faq. Translations are available at https://www.contributor-covenant.org/faq. Translations are available at
https://www.contributor-covenant.org/translations. https://www.contributor-covenant.org/translations.
[homepage]: https://www.contributor-covenant.org
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment