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 751 additions and 760 deletions
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/datasets/samplers/distributed_sampler.py
View file @ 41b18fd8
......@@ -2,6 +2,7 @@ import math
import torch
from torch.utils.data import DistributedSampler as _DistributedSampler
from .sampler import SAMPLER
......@@ -33,9 +34,9 @@ class DistributedSampler(_DistributedSampler):
assert len(indices) == self.total_size
# subsample
per_replicas = self.total_size//self.num_replicas
per_replicas = self.total_size // self.num_replicas
# indices = indices[self.rank:self.total_size:self.num_replicas]
indices = indices[self.rank*per_replicas:(self.rank+1)*per_replicas]
indices = indices[self.rank * per_replicas:(self.rank + 1) * per_replicas]
assert len(indices) == self.num_samples
return iter(indices)
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/datasets/samplers/group_sampler.py
View file @ 41b18fd8
# Copyright (c) OpenMMLab. All rights reserved.
import math
......@@ -6,9 +5,8 @@ import numpy as np
import torch
from mmcv.runner import get_dist_info
from torch.utils.data import Sampler
from .sampler import SAMPLER
import random
from IPython import embed
@SAMPLER.register_module()
......@@ -107,4 +105,3 @@ class DistributedGroupSampler(Sampler):
def set_epoch(self, epoch):
self.epoch = epoch
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/models/backbones/vovnet.py
View file @ 41b18fd8
from collections import OrderedDict
from mmcv.runner import BaseModule
from mmdet.models.builder import BACKBONES
import torch
import torch.nn as nn
import torch.nn.functional as F
from mmcv.runner import BaseModule
from mmdet.models.builder import BACKBONES
from torch.nn.modules.batchnorm import _BatchNorm
VoVNet19_slim_dw_eSE = {
'stem': [64, 64, 64],
'stage_conv_ch': [64, 80, 96, 112],
'stage_out_ch': [112, 256, 384, 512],
"layer_per_block": 3,
"block_per_stage": [1, 1, 1, 1],
"eSE": True,
"dw": True
'layer_per_block': 3,
'block_per_stage': [1, 1, 1, 1],
'eSE': True,
'dw': True
}
VoVNet19_dw_eSE = {
'stem': [64, 64, 64],
"stage_conv_ch": [128, 160, 192, 224],
"stage_out_ch": [256, 512, 768, 1024],
"layer_per_block": 3,
"block_per_stage": [1, 1, 1, 1],
"eSE": True,
"dw": True
'stage_conv_ch': [128, 160, 192, 224],
'stage_out_ch': [256, 512, 768, 1024],
'layer_per_block': 3,
'block_per_stage': [1, 1, 1, 1],
'eSE': True,
'dw': True
}
VoVNet19_slim_eSE = {
......@@ -35,57 +34,57 @@ VoVNet19_slim_eSE = {
'layer_per_block': 3,
'block_per_stage': [1, 1, 1, 1],
'eSE': True,
"dw": False
'dw': False
}
VoVNet19_eSE = {
'stem': [64, 64, 128],
"stage_conv_ch": [128, 160, 192, 224],
"stage_out_ch": [256, 512, 768, 1024],
"layer_per_block": 3,
"block_per_stage": [1, 1, 1, 1],
"eSE": True,
"dw": False
'stage_conv_ch': [128, 160, 192, 224],
'stage_out_ch': [256, 512, 768, 1024],
'layer_per_block': 3,
'block_per_stage': [1, 1, 1, 1],
'eSE': True,
'dw': False
}
VoVNet39_eSE = {
'stem': [64, 64, 128],
"stage_conv_ch": [128, 160, 192, 224],
"stage_out_ch": [256, 512, 768, 1024],
"layer_per_block": 5,
"block_per_stage": [1, 1, 2, 2],
"eSE": True,
"dw": False
'stage_conv_ch': [128, 160, 192, 224],
'stage_out_ch': [256, 512, 768, 1024],
'layer_per_block': 5,
'block_per_stage': [1, 1, 2, 2],
'eSE': True,
'dw': False
}
VoVNet57_eSE = {
'stem': [64, 64, 128],
"stage_conv_ch": [128, 160, 192, 224],
"stage_out_ch": [256, 512, 768, 1024],
"layer_per_block": 5,
"block_per_stage": [1, 1, 4, 3],
"eSE": True,
"dw": False
'stage_conv_ch': [128, 160, 192, 224],
'stage_out_ch': [256, 512, 768, 1024],
'layer_per_block': 5,
'block_per_stage': [1, 1, 4, 3],
'eSE': True,
'dw': False
}
VoVNet99_eSE = {
'stem': [64, 64, 128],
"stage_conv_ch": [128, 160, 192, 224],
"stage_out_ch": [256, 512, 768, 1024],
"layer_per_block": 5,
"block_per_stage": [1, 3, 9, 3],
"eSE": True,
"dw": False
'stage_conv_ch': [128, 160, 192, 224],
'stage_out_ch': [256, 512, 768, 1024],
'layer_per_block': 5,
'block_per_stage': [1, 3, 9, 3],
'eSE': True,
'dw': False
}
_STAGE_SPECS = {
"V-19-slim-dw-eSE": VoVNet19_slim_dw_eSE,
"V-19-dw-eSE": VoVNet19_dw_eSE,
"V-19-slim-eSE": VoVNet19_slim_eSE,
"V-19-eSE": VoVNet19_eSE,
"V-39-eSE": VoVNet39_eSE,
"V-57-eSE": VoVNet57_eSE,
"V-99-eSE": VoVNet99_eSE,
'V-19-slim-dw-eSE': VoVNet19_slim_dw_eSE,
'V-19-dw-eSE': VoVNet19_dw_eSE,
'V-19-slim-eSE': VoVNet19_slim_eSE,
'V-19-eSE': VoVNet19_eSE,
'V-39-eSE': VoVNet39_eSE,
'V-57-eSE': VoVNet57_eSE,
'V-99-eSE': VoVNet99_eSE,
}
......@@ -117,7 +116,7 @@ def conv3x3(in_channels, out_channels, module_name, postfix, stride=1, groups=1,
"""3x3 convolution with padding"""
return [
(
f"{module_name}_{postfix}/conv",
f'{module_name}_{postfix}/conv',
nn.Conv2d(
in_channels,
out_channels,
......@@ -128,8 +127,8 @@ def conv3x3(in_channels, out_channels, module_name, postfix, stride=1, groups=1,
bias=False,
),
),
(f"{module_name}_{postfix}/norm", nn.BatchNorm2d(out_channels)),
(f"{module_name}_{postfix}/relu", nn.ReLU(inplace=True)),
(f'{module_name}_{postfix}/norm', nn.BatchNorm2d(out_channels)),
(f'{module_name}_{postfix}/relu', nn.ReLU(inplace=True)),
]
......@@ -137,7 +136,7 @@ def conv1x1(in_channels, out_channels, module_name, postfix, stride=1, groups=1,
"""1x1 convolution with padding"""
return [
(
f"{module_name}_{postfix}/conv",
f'{module_name}_{postfix}/conv',
nn.Conv2d(
in_channels,
out_channels,
......@@ -148,8 +147,8 @@ def conv1x1(in_channels, out_channels, module_name, postfix, stride=1, groups=1,
bias=False,
),
),
(f"{module_name}_{postfix}/norm", nn.BatchNorm2d(out_channels)),
(f"{module_name}_{postfix}/relu", nn.ReLU(inplace=True)),
(f'{module_name}_{postfix}/norm', nn.BatchNorm2d(out_channels)),
(f'{module_name}_{postfix}/relu', nn.ReLU(inplace=True)),
]
......@@ -192,7 +191,7 @@ class _OSA_module(nn.Module):
if self.depthwise and in_channel != stage_ch:
self.isReduced = True
self.conv_reduction = nn.Sequential(
OrderedDict(conv1x1(in_channel, stage_ch, "{}_reduction".format(module_name), "0"))
OrderedDict(conv1x1(in_channel, stage_ch, '{}_reduction'.format(module_name), '0'))
)
for i in range(layer_per_block):
if self.depthwise:
......@@ -203,7 +202,7 @@ class _OSA_module(nn.Module):
# feature aggregation
in_channel = in_ch + layer_per_block * stage_ch
self.concat = nn.Sequential(OrderedDict(conv1x1(in_channel, concat_ch, module_name, "concat")))
self.concat = nn.Sequential(OrderedDict(conv1x1(in_channel, concat_ch, module_name, 'concat')))
self.ese = eSEModule(concat_ch)
......@@ -238,18 +237,18 @@ class _OSA_stage(nn.Sequential):
super(_OSA_stage, self).__init__()
if not stage_num == 2:
self.add_module("Pooling", nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True))
self.add_module('Pooling', nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True))
if block_per_stage != 1:
SE = False
module_name = f"OSA{stage_num}_1"
module_name = f'OSA{stage_num}_1'
self.add_module(
module_name, _OSA_module(in_ch, stage_ch, concat_ch, layer_per_block, module_name, SE, depthwise=depthwise)
)
for i in range(block_per_stage - 1):
if i != block_per_stage - 2: # last block
SE = False
module_name = f"OSA{stage_num}_{i + 2}"
module_name = f'OSA{stage_num}_{i + 2}'
self.add_module(
module_name,
_OSA_module(
......@@ -285,32 +284,32 @@ class VoVNet(BaseModule):
self.init_cfg = dict(type='Pretrained', checkpoint=pretrained)
stage_specs = _STAGE_SPECS[spec_name]
stem_ch = stage_specs["stem"]
config_stage_ch = stage_specs["stage_conv_ch"]
config_concat_ch = stage_specs["stage_out_ch"]
block_per_stage = stage_specs["block_per_stage"]
layer_per_block = stage_specs["layer_per_block"]
SE = stage_specs["eSE"]
depthwise = stage_specs["dw"]
stem_ch = stage_specs['stem']
config_stage_ch = stage_specs['stage_conv_ch']
config_concat_ch = stage_specs['stage_out_ch']
block_per_stage = stage_specs['block_per_stage']
layer_per_block = stage_specs['layer_per_block']
SE = stage_specs['eSE']
depthwise = stage_specs['dw']
self._out_features = out_features
# Stem module
conv_type = dw_conv3x3 if depthwise else conv3x3
stem = conv3x3(input_ch, stem_ch[0], "stem", "1", 2)
stem += conv_type(stem_ch[0], stem_ch[1], "stem", "2", 1)
stem += conv_type(stem_ch[1], stem_ch[2], "stem", "3", 2)
self.add_module("stem", nn.Sequential((OrderedDict(stem))))
stem = conv3x3(input_ch, stem_ch[0], 'stem', '1', 2)
stem += conv_type(stem_ch[0], stem_ch[1], 'stem', '2', 1)
stem += conv_type(stem_ch[1], stem_ch[2], 'stem', '3', 2)
self.add_module('stem', nn.Sequential((OrderedDict(stem))))
current_stirde = 4
self._out_feature_strides = {"stem": current_stirde, "stage2": current_stirde}
self._out_feature_channels = {"stem": stem_ch[2]}
self._out_feature_strides = {'stem': current_stirde, 'stage2': current_stirde}
self._out_feature_channels = {'stem': stem_ch[2]}
stem_out_ch = [stem_ch[2]]
in_ch_list = stem_out_ch + config_concat_ch[:-1]
# OSA stages
self.stage_names = []
for i in range(4): # num_stages
name = "stage%d" % (i + 2) # stage 2 ... stage 5
name = 'stage%d' % (i + 2) # stage 2 ... stage 5
self.stage_names.append(name)
self.add_module(
name,
......@@ -341,8 +340,8 @@ class VoVNet(BaseModule):
def forward(self, x):
outputs = {}
x = self.stem(x)
if "stem" in self._out_features:
outputs["stem"] = x
if 'stem' in self._out_features:
outputs['stem'] = x
for name in self.stage_names:
x = getattr(self, name)(x)
if name in self._out_features:
......@@ -358,7 +357,7 @@ class VoVNet(BaseModule):
param.requires_grad = False
for i in range(1, self.frozen_stages + 1):
m = getattr(self, f'stage{i+1}')
m = getattr(self, f'stage{i + 1}')
m.eval()
for param in m.parameters():
param.requires_grad = False
......
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/models/hooks/hooks.py
View file @ 41b18fd8
from mmcv.runner.hooks.hook import HOOKS, Hook
from projects.mmdet3d_plugin.models.utils import run_time
@HOOKS.register_module()
......@@ -7,7 +6,5 @@ class GradChecker(Hook):
def after_train_iter(self, runner):
for key, val in runner.model.named_parameters():
if val.grad == None and val.requires_grad:
if val.grad is None and val.requires_grad:
print('WARNNING: {key}\'s parameters are not be used!!!!'.format(key=key))
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/models/opt/adamw.py
View file @ 41b18fd8
......@@ -4,8 +4,9 @@ except:
print('WARNING!!!, I recommend using torch>=1.8')
import torch
from torch.optim.optimizer import Optimizer
from mmcv.runner.optimizer.builder import OPTIMIZERS
from torch.optim.optimizer import Optimizer
@OPTIMIZERS.register_module()
class AdamW2(Optimizer):
......@@ -38,15 +39,15 @@ class AdamW2(Optimizer):
def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8,
weight_decay=1e-2, amsgrad=False):
if not 0.0 <= lr:
raise ValueError("Invalid learning rate: {}".format(lr))
raise ValueError('Invalid learning rate: {}'.format(lr))
if not 0.0 <= eps:
raise ValueError("Invalid epsilon value: {}".format(eps))
raise ValueError('Invalid epsilon value: {}'.format(eps))
if not 0.0 <= betas[0] < 1.0:
raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
raise ValueError('Invalid beta parameter at index 0: {}'.format(betas[0]))
if not 0.0 <= betas[1] < 1.0:
raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
raise ValueError('Invalid beta parameter at index 1: {}'.format(betas[1]))
if not 0.0 <= weight_decay:
raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
raise ValueError('Invalid weight_decay value: {}'.format(weight_decay))
defaults = dict(lr=lr, betas=betas, eps=eps,
weight_decay=weight_decay, amsgrad=amsgrad)
super(AdamW2, self).__init__(params, defaults)
......@@ -109,7 +110,6 @@ class AdamW2(Optimizer):
if amsgrad:
max_exp_avg_sqs.append(state['max_exp_avg_sq'])
# update the steps for each param group update
state['step'] += 1
# record the step after step update
......
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/models/utils/__init__.py
View file @ 41b18fd8
from .bricks import run_time
from .grid_mask import GridMask
from .position_embedding import RelPositionEmbedding
from .visual import save_tensor
from .positional_encoding import LearnedPositionalEncoding3D
from .visual import save_tensor
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/models/utils/bricks.py
View file @ 41b18fd8
import functools
import time
from collections import defaultdict
import torch
time_maps = defaultdict(lambda :0.)
count_maps = defaultdict(lambda :0.)
time_maps = defaultdict(lambda: 0.)
count_maps = defaultdict(lambda: 0.)
def run_time(name):
def middle(fn):
def wrapper(*args, **kwargs):
......@@ -11,10 +14,12 @@ def run_time(name):
start = time.time()
res = fn(*args, **kwargs)
torch.cuda.synchronize()
time_maps['%s : %s'%(name, fn.__name__) ] += time.time()-start
count_maps['%s : %s'%(name, fn.__name__) ] +=1
print("%s : %s takes up %f "% (name, fn.__name__,time_maps['%s : %s'%(name, fn.__name__) ] /count_maps['%s : %s'%(name, fn.__name__) ] ))
time_maps['%s : %s' % (name, fn.__name__)] += time.time() - start
count_maps['%s : %s' % (name, fn.__name__)] += 1
print('%s : %s takes up %f ' % (name, fn.__name__, time_maps['%s : %s' % (name, fn.__name__)] / count_maps[
'%s : %s' % (name, fn.__name__)]))
return res
return wrapper
return middle
return middle
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/models/utils/grid_mask.py
View file @ 41b18fd8
import numpy as np
import torch
import torch.nn as nn
import numpy as np
from mmcv.runner import auto_fp16
from PIL import Image
from mmcv.runner import force_fp32, auto_fp16
class Grid(object):
def __init__(self, use_h, use_w, rotate = 1, offset=False, ratio = 0.5, mode=0, prob = 1.):
def __init__(self, use_h, use_w, rotate=1, offset=False, ratio=0.5, mode=0, prob=1.):
self.use_h = use_h
self.use_w = use_w
self.rotate = rotate
self.offset = offset
self.ratio = ratio
self.mode=mode
self.mode = mode
self.st_prob = prob
self.prob = prob
......@@ -25,40 +26,40 @@ class Grid(object):
w = img.size(2)
self.d1 = 2
self.d2 = min(h, w)
hh = int(1.5*h)
ww = int(1.5*w)
hh = int(1.5 * h)
ww = int(1.5 * w)
d = np.random.randint(self.d1, self.d2)
if self.ratio == 1:
self.l = np.random.randint(1, d)
else:
self.l = min(max(int(d*self.ratio+0.5),1),d-1)
self.l = min(max(int(d * self.ratio + 0.5), 1), d - 1)
mask = np.ones((hh, ww), np.float32)
st_h = np.random.randint(d)
st_w = np.random.randint(d)
if self.use_h:
for i in range(hh//d):
s = d*i + st_h
t = min(s+self.l, hh)
mask[s:t,:] *= 0
for i in range(hh // d):
s = d * i + st_h
t = min(s + self.l, hh)
mask[s:t, :] *= 0
if self.use_w:
for i in range(ww//d):
s = d*i + st_w
t = min(s+self.l, ww)
mask[:,s:t] *= 0
for i in range(ww // d):
s = d * i + st_w
t = min(s + self.l, ww)
mask[:, s:t] *= 0
r = np.random.randint(self.rotate)
mask = Image.fromarray(np.uint8(mask))
mask = mask.rotate(r)
mask = np.asarray(mask)
mask = mask[(hh-h)//2:(hh-h)//2+h, (ww-w)//2:(ww-w)//2+w]
mask = mask[(hh - h) // 2:(hh - h) // 2 + h, (ww - w) // 2:(ww - w) // 2 + w]
mask = torch.from_numpy(mask).float()
if self.mode == 1:
mask = 1-mask
mask = 1 - mask
mask = mask.expand_as(img)
if self.offset:
offset = torch.from_numpy(2 * (np.random.rand(h,w) - 0.5)).float()
offset = torch.from_numpy(2 * (np.random.rand(h, w) - 0.5)).float()
offset = (1 - mask) * offset
img = img * mask + offset
else:
......@@ -68,7 +69,7 @@ class Grid(object):
class GridMask(nn.Module):
def __init__(self, use_h, use_w, rotate = 1, offset=False, ratio = 0.5, mode=0, prob = 1.):
def __init__(self, use_h, use_w, rotate=1, offset=False, ratio=0.5, mode=0, prob=1.):
super(GridMask, self).__init__()
self.use_h = use_h
self.use_w = use_w
......@@ -79,46 +80,48 @@ class GridMask(nn.Module):
self.st_prob = prob
self.prob = prob
self.fp16_enable = False
def set_prob(self, epoch, max_epoch):
self.prob = self.st_prob * epoch / max_epoch #+ 1.#0.5
self.prob = self.st_prob * epoch / max_epoch # + 1.#0.5
@auto_fp16()
def forward(self, x):
if np.random.rand() > self.prob or not self.training:
return x
n,c,h,w = x.size()
x = x.view(-1,h,w)
hh = int(1.5*h)
ww = int(1.5*w)
n, c, h, w = x.size()
x = x.view(-1, h, w)
hh = int(1.5 * h)
ww = int(1.5 * w)
d = np.random.randint(2, h)
self.l = min(max(int(d*self.ratio+0.5),1),d-1)
self.l = min(max(int(d * self.ratio + 0.5), 1), d - 1)
mask = np.ones((hh, ww), np.float32)
st_h = np.random.randint(d)
st_w = np.random.randint(d)
if self.use_h:
for i in range(hh//d):
s = d*i + st_h
t = min(s+self.l, hh)
mask[s:t,:] *= 0
for i in range(hh // d):
s = d * i + st_h
t = min(s + self.l, hh)
mask[s:t, :] *= 0
if self.use_w:
for i in range(ww//d):
s = d*i + st_w
t = min(s+self.l, ww)
mask[:,s:t] *= 0
for i in range(ww // d):
s = d * i + st_w
t = min(s + self.l, ww)
mask[:, s:t] *= 0
r = np.random.randint(self.rotate)
mask = Image.fromarray(np.uint8(mask))
mask = mask.rotate(r)
mask = np.asarray(mask)
mask = mask[(hh-h)//2:(hh-h)//2+h, (ww-w)//2:(ww-w)//2+w]
mask = mask[(hh - h) // 2:(hh - h) // 2 + h, (ww - w) // 2:(ww - w) // 2 + w]
mask = torch.from_numpy(mask).to(x.dtype).cuda()
if self.mode == 1:
mask = 1-mask
mask = 1 - mask
mask = mask.expand_as(x)
if self.offset:
offset = torch.from_numpy(2 * (np.random.rand(h,w) - 0.5)).to(x.dtype).cuda()
offset = torch.from_numpy(2 * (np.random.rand(h, w) - 0.5)).to(x.dtype).cuda()
x = x * mask + offset * (1 - mask)
else:
x = x * mask
return x.view(n,c,h,w)
\ No newline at end of file
return x.view(n, c, h, w)
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/models/utils/position_embedding.py
View file @ 41b18fd8
import math
import torch
import torch.nn as nn
import math
class RelPositionEmbedding(nn.Module):
def __init__(self, num_pos_feats=64, pos_norm=True):
super().__init__()
self.num_pos_feats = num_pos_feats
self.fc = nn.Linear(4, self.num_pos_feats,bias=False)
#nn.init.orthogonal_(self.fc.weight)
#self.fc.weight.requires_grad = False
self.fc = nn.Linear(4, self.num_pos_feats, bias=False)
# nn.init.orthogonal_(self.fc.weight)
# self.fc.weight.requires_grad = False
self.pos_norm = pos_norm
if self.pos_norm:
self.norm = nn.LayerNorm(self.num_pos_feats)
def forward(self, tensor):
#mask = nesttensor.mask
B,C,H,W = tensor.shape
#print('tensor.shape', tensor.shape)
# mask = nesttensor.mask
B, C, H, W = tensor.shape
# print('tensor.shape', tensor.shape)
y_range = (torch.arange(H) / float(H - 1)).to(tensor.device)
#y_axis = torch.stack((y_range, 1-y_range),dim=1)
# y_axis = torch.stack((y_range, 1-y_range),dim=1)
y_axis = torch.stack((torch.cos(y_range * math.pi), torch.sin(y_range * math.pi)), dim=1)
y_axis = y_axis.reshape(H, 1, 2).repeat(1, W, 1).reshape(H * W, 2)
x_range = (torch.arange(W) / float(W - 1)).to(tensor.device)
#x_axis =torch.stack((x_range,1-x_range),dim=1)
# x_axis =torch.stack((x_range,1-x_range),dim=1)
x_axis = torch.stack((torch.cos(x_range * math.pi), torch.sin(x_range * math.pi)), dim=1)
x_axis = x_axis.reshape(1, W, 2).repeat(H, 1, 1).reshape(H * W, 2)
x_pos = torch.cat((y_axis, x_axis), dim=1)
......@@ -30,5 +33,5 @@ class RelPositionEmbedding(nn.Module):
if self.pos_norm:
x_pos = self.norm(x_pos)
#print('xpos,', x_pos.max(),x_pos.min())
# print('xpos,', x_pos.max(),x_pos.min())
return x_pos
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/models/utils/positional_encoding.py
View file @ 41b18fd8
import math
import torch
import torch.nn as nn
from mmcv.cnn.bricks.transformer import POSITIONAL_ENCODING
......@@ -58,7 +56,8 @@ class LearnedPositionalEncoding3D(BaseModule):
pos = torch.cat(
(x_embed.unsqueeze(0).unsqueeze(0).repeat(l, h, 1, 1),
y_embed.unsqueeze(1).unsqueeze(0).repeat(l, 1, w, 1),
z_embed.unsqueeze(1).unsqueeze(1).repeat(1, h, w, 1)),dim=-1).permute(3, 0, 1, 2).unsqueeze(0).repeat(mask.shape[0],1, 1, 1, 1)
z_embed.unsqueeze(1).unsqueeze(1).repeat(1, h, w, 1)), dim=-1).permute(3, 0, 1, 2).unsqueeze(0).repeat(
mask.shape[0], 1, 1, 1, 1)
return pos
def __repr__(self):
......
autonomous_driving/occupancy_prediction/projects/mmdet3d_plugin/models/utils/visual.py
View file @ 41b18fd8
import cv2
import matplotlib.pyplot as plt
import torch
from torchvision.utils import make_grid
import torchvision
import matplotlib.pyplot as plt
import cv2
from torchvision.utils import make_grid
def convert_color(img_path):
......@@ -12,11 +12,11 @@ def convert_color(img_path):
plt.close()
def save_tensor(tensor, path, pad_value=254.0,):
def save_tensor(tensor, path, pad_value=254.0, ):
print('save_tensor', path)
tensor = tensor.to(torch.float).detach().cpu()
if tensor.type() == 'torch.BoolTensor':
tensor = tensor*255
tensor = tensor * 255
if len(tensor.shape) == 3:
tensor = tensor.unsqueeze(1)
tensor = make_grid(tensor, pad_value=pad_value, normalize=False).permute(1, 2, 0).numpy().copy()
......
autonomous_driving/occupancy_prediction/tools/.ipynb_checkpoints/train-checkpoint.py
View file @ 41b18fd8
......@@ -8,26 +8,25 @@ from __future__ import division
import argparse
import copy
import mmcv
import os
import time
import torch
import warnings
from mmcv import Config, DictAction
from mmcv.runner import get_dist_info, init_dist
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 mmcv.utils import TORCH_VERSION, digit_version
from mmdet import __version__ as mmdet_version
from mmdet3d import __version__ as mmdet3d_version
#from mmdet3d.apis import train_model
from mmdet3d.datasets import build_dataset
from mmdet3d.models import build_model
from mmdet3d.utils import collect_env, get_root_logger
from mmdet.apis import set_random_seed
from mmseg import __version__ as mmseg_version
from mmcv.utils import TORCH_VERSION, digit_version
# from mmdet3d.apis import train_model
def parse_args():
......@@ -134,7 +133,8 @@ def main():
print(_module_path)
plg_lib = importlib.import_module(_module_path)
from projects.mmdet3d_plugin.bevformer.apis.train import custom_train_model
from projects.mmdet3d_plugin.bevformer.apis.train import \
custom_train_model
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
......
autonomous_driving/occupancy_prediction/tools/analysis_tools/analyze_logs.py
View file @ 41b18fd8
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import json
from collections import defaultdict
import numpy as np
import seaborn as sns
from collections import defaultdict
from matplotlib import pyplot as plt
......@@ -85,7 +86,7 @@ def plot_curve(log_dicts, args):
xs = []
ys = []
num_iters_per_epoch = \
log_dict[epochs[args.interval-1]]['iter'][-1]
log_dict[epochs[args.interval - 1]]['iter'][-1]
for epoch in epochs[args.interval - 1::args.interval]:
iters = log_dict[epoch]['iter']
if log_dict[epoch]['mode'][-1] == 'val':
......
autonomous_driving/occupancy_prediction/tools/analysis_tools/benchmark.py
View file @ 41b18fd8
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import sys
import time
import torch
from mmcv import Config
from mmcv.parallel import MMDataParallel
from mmcv.runner import load_checkpoint, wrap_fp16_model
import sys
sys.path.append('.')
from projects.mmdet3d_plugin.datasets.builder import build_dataloader
from projects.mmdet3d_plugin.datasets import custom_build_dataset
# from mmdet3d.datasets import build_dataloader, build_dataset
from mmdet3d.models import build_detector
#from tools.misc.fuse_conv_bn import fuse_module
from projects.mmdet3d_plugin.datasets import custom_build_dataset
from projects.mmdet3d_plugin.datasets.builder import build_dataloader
# from tools.misc.fuse_conv_bn import fuse_module
def parse_args():
......@@ -59,7 +62,7 @@ def main():
wrap_fp16_model(model)
if args.checkpoint is not None:
load_checkpoint(model, args.checkpoint, map_location='cpu')
#if args.fuse_conv_bn:
# if args.fuse_conv_bn:
# model = fuse_module(model)
model = MMDataParallel(model, device_ids=[0])
......
autonomous_driving/occupancy_prediction/tools/analysis_tools/get_params.py
View file @ 41b18fd8
import torch
file_path = './ckpts/bevformer_v4.pth'
model = torch.load(file_path, map_location='cpu')
all = 0
......
autonomous_driving/occupancy_prediction/tools/analysis_tools/visual.py
View file @ 41b18fd8
......@@ -4,30 +4,15 @@
# ---------------------------------------------
import mmcv
from nuscenes.eval.common.data_classes import EvalBoxes
from nuscenes.eval.detection.data_classes import DetectionBox
from nuscenes.eval.detection.render import visualize_sample
from nuscenes.eval.detection.utils import category_to_detection_name
from nuscenes.nuscenes import NuScenes
from nuscenes.utils.geometry_utils import (BoxVisibility, box_in_image,
view_points)
from PIL import Image
from nuscenes.utils.geometry_utils import view_points, box_in_image, BoxVisibility, transform_matrix
from typing import Tuple, List, Iterable
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image
from matplotlib import rcParams
from matplotlib.axes import Axes
from pyquaternion import Quaternion
from PIL import Image
from matplotlib import rcParams
from matplotlib.axes import Axes
from pyquaternion import Quaternion
from tqdm import tqdm
from nuscenes.utils.data_classes import LidarPointCloud, RadarPointCloud, Box
from nuscenes.utils.geometry_utils import view_points, box_in_image, BoxVisibility, transform_matrix
from nuscenes.eval.common.data_classes import EvalBoxes, EvalBox
from nuscenes.eval.detection.data_classes import DetectionBox
from nuscenes.eval.detection.utils import category_to_detection_name
from nuscenes.eval.detection.render import visualize_sample
cams = ['CAM_FRONT',
'CAM_FRONT_RIGHT',
......@@ -36,11 +21,11 @@ cams = ['CAM_FRONT',
'CAM_BACK_LEFT',
'CAM_FRONT_LEFT']
import numpy as np
import matplotlib.pyplot as plt
from nuscenes.utils.data_classes import LidarPointCloud, RadarPointCloud, Box
from PIL import Image
import numpy as np
from matplotlib import rcParams
from nuscenes.utils.data_classes import Box, LidarPointCloud
from PIL import Image
def render_annotation(
......@@ -143,7 +128,6 @@ def render_annotation(
plt.savefig(out_path)
def get_sample_data(sample_data_token: str,
box_vis_level: BoxVisibility = BoxVisibility.ANY,
selected_anntokens=None,
......@@ -206,7 +190,6 @@ def get_sample_data(sample_data_token: str,
return data_path, box_list, cam_intrinsic
def get_predicted_data(sample_data_token: str,
box_vis_level: BoxVisibility = BoxVisibility.ANY,
selected_anntokens=None,
......@@ -270,9 +253,7 @@ def get_predicted_data(sample_data_token: str,
return data_path, box_list, cam_intrinsic
def lidiar_render(sample_token, data,out_path=None):
def lidiar_render(sample_token, data, out_path=None):
bbox_gt_list = []
bbox_pred_list = []
anns = nusc.get('sample', sample_token)['anns']
......@@ -314,7 +295,7 @@ def lidiar_render(sample_token, data,out_path=None):
pred_annotations.add_boxes(sample_token, bbox_pred_list)
print('green is ground truth')
print('blue is the predited result')
visualize_sample(nusc, sample_token, gt_annotations, pred_annotations, savepath=out_path+'_bev')
visualize_sample(nusc, sample_token, gt_annotations, pred_annotations, savepath=out_path + '_bev')
def get_color(category_name: str):
......@@ -325,7 +306,8 @@ def get_color(category_name: str):
a = ['noise', 'animal', 'human.pedestrian.adult', 'human.pedestrian.child', 'human.pedestrian.construction_worker',
'human.pedestrian.personal_mobility', 'human.pedestrian.police_officer', 'human.pedestrian.stroller',
'human.pedestrian.wheelchair', 'movable_object.barrier', 'movable_object.debris',
'movable_object.pushable_pullable', 'movable_object.trafficcone', 'static_object.bicycle_rack', 'vehicle.bicycle',
'movable_object.pushable_pullable', 'movable_object.trafficcone', 'static_object.bicycle_rack',
'vehicle.bicycle',
'vehicle.bus.bendy', 'vehicle.bus.rigid', 'vehicle.car', 'vehicle.construction', 'vehicle.emergency.ambulance',
'vehicle.emergency.police', 'vehicle.motorcycle', 'vehicle.trailer', 'vehicle.truck', 'flat.driveable_surface',
'flat.other', 'flat.sidewalk', 'flat.terrain', 'static.manmade', 'static.other', 'static.vegetation',
......@@ -334,7 +316,7 @@ def get_color(category_name: str):
'car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier',
'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'
]
#print(category_name)
# print(category_name)
if category_name == 'bicycle':
return nusc.colormap['vehicle.bicycle']
elif category_name == 'construction_vehicle':
......@@ -365,7 +347,7 @@ def render_sample_data(
verbose: bool = True,
show_panoptic: bool = False,
pred_data=None,
) -> None:
) -> None:
"""
Render sample data onto axis.
:param sample_data_token: Sample_data token.
......@@ -450,7 +432,7 @@ def render_sample_data(
ax[j + 2, ind].set_ylim(data.size[1], 0)
else:
raise ValueError("Error: Unknown sensor modality!")
raise ValueError('Error: Unknown sensor modality!')
ax[j, ind].axis('off')
ax[j, ind].set_title('PRED: {} {labels_type}'.format(
......@@ -463,11 +445,12 @@ def render_sample_data(
ax[j + 2, ind].set_aspect('equal')
if out_path is not None:
plt.savefig(out_path+'_camera', bbox_inches='tight', pad_inches=0, dpi=200)
plt.savefig(out_path + '_camera', bbox_inches='tight', pad_inches=0, dpi=200)
if verbose:
plt.show()
plt.close()
if __name__ == '__main__':
nusc = NuScenes(version='v1.0-trainval', dataroot='./data/nuscenes', verbose=True)
# render_annotation('7603b030b42a4b1caa8c443ccc1a7d52')
......
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