mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity

Merge branch 'cnet' of https://github.com/ceccocats/tkDNN into cnet

Browse Source
This commit is contained in:
xavier
2020-02-10 18:19:12 +01:00
parent d601e980f6 b06dc286e9
commit 10831ab450
5 changed files with 410 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+63
View File
@@ -27,6 +27,36 @@ make
during the cmake configuration it will be dowloaded the weights needed for running
the tests
## DLA34 and ResNet101 weights
To get weights and outputs needed for running the tests you can use the Python
script and the Anaconda environment included in the repository.
Create Anaconda environment and activate it:
```
conda env create -f file_name.yml
source activate env_name
```
Run the Python script inside the environment.
## CenterNet weights
To get the weights needed for running the tests:
* clone the forked repository by the original CenterNet:
```
git clone https://github.com/sapienzadavide/CenterNet.git
```
* follow the instruction in the README.md and INSTALL.md
* copy the weigths and outputs from /path/to/CenterNet/src/ in ./test/centernet-path/ . For example:
```
cp /path/to/CenterNet/src/layers_dla/* ./test/dla34_cnet/layers/
cp /path/to/CenterNet/src/debug_dla/* ./test/dla34_cnet/debug/
```
or
```
cp /path/to/CenterNet/src/layers_resdcn/* ./test/resnet101_cnet/layers/
cp /path/to/CenterNet/src/debug_resdcn/* ./test/resnet101_cnet/debug/
```
## Test
Assumiung you have correctly builded the library these are the test ready to exec:
* test_simple: a simple convolutional and dense network (CUDNN only)
@@ -35,6 +65,11 @@ Assumiung you have correctly builded the library these are the test ready to exe
* test_yolo: YOLO detection network (CUDNN and TENSORRT)
* test_yolo_tiny: smaller version of YOLO (CUDNN and TENSRRT)
* test_yolo3_berkeley: our yolo3 version trained with BDD100K dateset
* test_resnet101: ResNet101 network (CUDNN and TENSORRT)
* test_resnet101_cnet: CenterNet detection based on ResNet101 (CUDNN and TENSORRT)
* test_dla34: DLA34 network (CUDNN and TENSORRT)
* test_dla34_cnet: CenterNet detection based on DLA34 (CUDNN and TENSORRT)
## yolo3 berkeley demo detection
For the live detection you need to precompile the tensorRT file by luncing the desidered network test, this is the recommended process:
@@ -50,3 +85,31 @@ this will genereate a yolo3_berkeley.rt file that can be used for live detection
./yolo3_demo yolo3_berkeley.rt /dev/video0 # launch detection on device 0
```
![demo](https://user-images.githubusercontent.com/11562617/72547657-540e7800-388d-11ea-83c6-49dfea2a0607.gif)
## CenterNet (DLA34, ResNet101) demo detection
For the live detection you need to precompile the tensorRT file by luncing the desidered network test, this is the recommended process:
```
export TKDNN_MODE=FP16 # set the half floating point optimization
```
For CenterNet based on ResNet101:
```
rm resnet101_cnet.rt # be sure to delete(or move) old tensorRT files
./test_resnet101_cnet # run the yolo test (is slow)
# with f16 inference the result will be a bit incorrect
```
For CenterNet based on DLA34:
```
rm dla34_cnet.rt # be sure to delete(or move) old tensorRT files
./test_dla34_cnet # run the yolo test (is slow)
# with f16 inference the result will be a bit incorrect
```
this will genereate resnet101_cnet.rt and dla34_cnet.rt file that can be used for live detection:
```
./centernet_demo # launch detection on a demo video
./centernet_demo resnet101_cnet.rt /dev/video0 # launch detection on device 0
./centernet_demo dla34_cnet.rt /dev/video0 # launch detection on device 0
```
tests/dla34/dla34_weightsexporter.py
+162
View File
@@ -0,0 +1,162 @@
import torch
import urllib
from PIL import Image
from torchvision import transforms
import numpy as np
import struct
import os
from pytorchcv.model_provider import get_model as ptcv_get_model
from torch.autograd import Variable
from torchsummary import summary
import torch.nn as nn
from torch.jit import trace
def create_folders():
if not os.path.exists('debug'):
os.makedirs('debug')
if not os.path.exists('layers'):
os.makedirs('layers')
def bin_write(f, data):
data =data.flatten()
fmt = 'f'*len(data)
bin = struct.pack(fmt, *data)
f.write(bin)
def hook(module, input, output):
setattr(module, "_value_hook", output)
def load_ex_image(model):
# Download an example image from the pytorch website
url, filename = (
"https://github.com/pytorch/hub/raw/master/dog.jpg", "dog.jpg")
try:
urllib.URLopener().retrieve(url, filename)
except:
urllib.request.urlretrieve(url, filename)
# sample execution (requires torchvision)
input_image = Image.open(filename)
print("input_image: ",input_image.size)
preprocess = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[
0.229, 0.224, 0.225]),
])
input_tensor = preprocess(input_image)
print("input_tensor: ",input_tensor.shape)
# create a mini-batch as expected by the model
input_batch = input_tensor.unsqueeze(0)
# move the input and model to GPU for speed if available
if torch.cuda.is_available():
input_batch = input_batch.to('cuda')
model.to('cuda')
return model, input_batch
def exp_input(model, input_batch):
# Export the input batch
model(input_batch)
i = input_batch.cpu().data.numpy()
i = np.array(i, dtype=np.float32)
i.tofile("debug/input.bin", format="f")
print("input: ", i.shape)
def print_wb_output(model):
f = None
for n, m in model.named_modules():
m.eval()
if 'DLAResBlock' in str(m.type):
continue
in_output = m._value_hook
o = in_output.data.numpy()
o = np.array(o, dtype=np.float32)
t = '-'.join(n.split('.'))
o.tofile("debug/" + t + ".bin", format="f")
print('------- ', n, ' ------')
print("debug ",o.shape)
if not(' of Conv2d' in str(m.type) or ' of Linear' in str(m.type) or ' of BatchNorm2d' in str(m.type)):
continue
if ' of Conv2d' in str(m.type) or ' of Linear' in str(m.type):
file_name = "layers/" + t + ".bin"
print("open file: ", file_name)
f = open(file_name, mode='wb')
w = np.array([])
b = np.array([])
if 'weight' in m._parameters and m._parameters['weight'] is not None:
w = m._parameters['weight'].data.numpy()
w = np.array(w, dtype=np.float32)
print (" weights shape:", np.shape(w))
if 'bias' in m._parameters and m._parameters['bias'] is not None:
b = m._parameters['bias'].data.numpy()
b = np.array(b, dtype=np.float32)
print (" bias shape:", np.shape(b))
if 'BatchNorm2d' in str(m.type):
b = m._parameters['bias'].data.numpy()
b = np.array(b, dtype=np.float32)
s = m._parameters['weight'].data.numpy()
s = np.array(s, dtype=np.float32)
rm = m.running_mean.data.numpy()
rm = np.array(rm, dtype=np.float32)
rv = m.running_var.data.numpy()
rv = np.array(rv, dtype=np.float32)
bin_write(f,b)
bin_write(f,s)
bin_write(f,rm)
bin_write(f,rv)
print (" b shape:", np.shape(b))
print (" s shape:", np.shape(s))
print (" rm shape:", np.shape(rm))
print (" rv shape:", np.shape(rv))
else:
bin_write(f,w)
if b.size > 0 and b is not None:
bin_write(f,b)
if ' of BatchNorm2d' in str(m.type) or ' of Linear' in str(m.type):
f.close()
print("close file")
f = None
if __name__ == '__main__':
model = ptcv_get_model("dla34", pretrained=True)
model.eval()
# load an example image and load it on model
model, input_batch = load_ex_image(model)
model.eval()
with torch.no_grad():
output = model(input_batch)
# create folders debug and layers if do not exist
create_folders()
# add output attribute to the layers
for n, m in model.named_modules():
m.register_forward_hook(hook)
# export input bin
exp_input(model, input_batch)
print_wb_output(model)
with open("dla34.txt", 'w') as f:
for item in list(model.children()):
f.write("%s\n" % item)
summary(model, (3, 224, 224))
# print(trace(model, input_batch))
tests/dla34/env_dla34.yml
+60
View File
@@ -0,0 +1,60 @@
name: dla34
channels:
- defaults
dependencies:
- _libgcc_mutex=0.1=main
- _pytorch_select=0.2=gpu_0
- blas=1.0=mkl
- ca-certificates=2019.10.16=0
- certifi=2019.9.11=py36_0
- cffi=1.13.1=py36h2e261b9_0
- cudatoolkit=10.0.130=0
- cudnn=7.6.0=cuda10.0_0
- freetype=2.9.1=h8a8886c_1
- intel-openmp=2019.4=243
- jpeg=9b=h024ee3a_2
- libedit=3.1.20181209=hc058e9b_0
- libffi=3.2.1=hd88cf55_4
- libgcc-ng=9.1.0=hdf63c60_0
- libgfortran-ng=7.3.0=hdf63c60_0
- libpng=1.6.37=hbc83047_0
- libstdcxx-ng=9.1.0=hdf63c60_0
- libtiff=4.0.10=h2733197_2
- mkl=2019.4=243
- mkl-service=2.3.0=py36he904b0f_0
- mkl_fft=1.0.14=py36ha843d7b_0
- mkl_random=1.1.0=py36hd6b4f25_0
- ncurses=6.1=he6710b0_1
- ninja=1.9.0=py36hfd86e86_0
- numpy=1.17.2=py36haad9e8e_0
- numpy-base=1.17.2=py36hde5b4d6_0
- olefile=0.46=py36_0
- openssl=1.1.1d=h7b6447c_3
- pillow=6.2.0=py36h34e0f95_0
- pip=19.3.1=py36_0
- pycparser=2.19=py36_0
- python=3.6.9=h265db76_0
- readline=7.0=h7b6447c_5
- setuptools=41.6.0=py36_0
- six=1.12.0=py36_0
- sqlite=3.30.1=h7b6447c_0
- tk=8.6.8=hbc83047_0
- wheel=0.33.6=py36_0
- xz=5.2.4=h14c3975_4
- zlib=1.2.11=h7b6447c_3
- zstd=1.3.7=h0b5b093_0
- pip:
- chardet==3.0.4
- decorator==4.4.1
- idna==2.8
- lxml==4.4.2
- networkx==2.4
- nltk==3.4.5
- pytorchcv==0.0.55
- requests==2.22.0
- summary==0.2.0
- torch==1.3.0
- torchsummary==1.5.1
- torchvision==0.4.1
- urllib3==1.25.8
tests/resnet101/env_resnet101.yml
+56
View File
@@ -0,0 +1,56 @@
name: resnet101
channels:
- defaults
dependencies:
- _libgcc_mutex=0.1=main
- _pytorch_select=0.2=gpu_0
- blas=1.0=mkl
- ca-certificates=2019.10.16=0
- certifi=2019.9.11=py36_0
- cffi=1.13.1=py36h2e261b9_0
- cudatoolkit=10.0.130=0
- cudnn=7.6.0=cuda10.0_0
- freetype=2.9.1=h8a8886c_1
- intel-openmp=2019.4=243
- jpeg=9b=h024ee3a_2
- libedit=3.1.20181209=hc058e9b_0
- libffi=3.2.1=hd88cf55_4
- libgcc-ng=9.1.0=hdf63c60_0
- libgfortran-ng=7.3.0=hdf63c60_0
- libpng=1.6.37=hbc83047_0
- libstdcxx-ng=9.1.0=hdf63c60_0
- libtiff=4.0.10=h2733197_2
- mkl=2019.4=243
- mkl-service=2.3.0=py36he904b0f_0
- mkl_fft=1.0.14=py36ha843d7b_0
- mkl_random=1.1.0=py36hd6b4f25_0
- ncurses=6.1=he6710b0_1
- ninja=1.9.0=py36hfd86e86_0
- numpy=1.17.2=py36haad9e8e_0
- numpy-base=1.17.2=py36hde5b4d6_0
- olefile=0.46=py36_0
- openssl=1.1.1d=h7b6447c_3
- pillow=6.2.0=py36h34e0f95_0
- pip=19.3.1=py36_0
- pycparser=2.19=py36_0
- python=3.6.9=h265db76_0
- pytorch=1.2.0=cuda100py36h938c94c_0
- readline=7.0=h7b6447c_5
- setuptools=41.6.0=py36_0
- six=1.12.0=py36_0
- sqlite=3.30.1=h7b6447c_0
- tk=8.6.8=hbc83047_0
- wheel=0.33.6=py36_0
- xz=5.2.4=h14c3975_4
- zlib=1.2.11=h7b6447c_3
- zstd=1.3.7=h0b5b093_0
- pip:
- chardet==3.0.4
- idna==2.8
- pytorchcv==0.0.55
- requests==2.22.0
- torch==1.3.0
- torchsummary==1.5.1
- torchvision==0.4.1
- urllib3==1.25.8
tests/resnet101/resnet101_weightsexporter.py
+69 -70
View File
@@ -2,15 +2,26 @@ import torch
import urllib
from PIL import Image
from torchvision import transforms
from torchsummary import summary
import numpy as np
import struct
import os
from pytorchcv.model_provider import get_model as ptcv_get_model
from torch.autograd import Variable
from torchsummary import summary
import torch.nn as nn
from torch.jit import trace
def create_folders():
if not os.path.exists('debug'):
os.makedirs('debug')
if not os.path.exists('layers'):
os.makedirs('layers')
def bin_write(f, data):
data =data.flatten()
# print(data)
fmt = 'f'*len(data)
bin = struct.pack(fmt, *data)
f.write(bin)
@@ -18,38 +29,46 @@ def bin_write(f, data):
def hook(module, input, output):
setattr(module, "_value_hook", output)
def load_ex_image(model):
# Download an example image from the pytorch website
url, filename = (
"https://github.com/pytorch/hub/raw/master/dog.jpg", "dog.jpg")
try:
urllib.URLopener().retrieve(url, filename)
except:
urllib.request.urlretrieve(url, filename)
# sample execution (requires torchvision)
input_image = Image.open(filename)
print("input_image: ",input_image.size)
preprocess = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[
0.229, 0.224, 0.225]),
])
input_tensor = preprocess(input_image)
print("input_tensor: ",input_tensor.shape)
# create a mini-batch as expected by the model
input_batch = input_tensor.unsqueeze(0)
# move the input and model to GPU for speed if available
if torch.cuda.is_available():
input_batch = input_batch.to('cuda')
model.to('cuda')
return model, input_batch
def print_wb(model, folder):
for name, param in model.named_parameters():
# print ("Layer", name)
t = name.split('.')[0:-1]
arg = name.split('.')[-1]
t = '-'.join(t)
print (" type: ", t)
if arg == 'weight':
w = param.data.numpy()
print (" weights shape:", np.shape(w))
w.tofile(folder + "/" + t + ".bin", format="f")
elif arg == 'bias':
b = param.data.numpy()
print (" bias shape:", np.shape(b))
b.tofile(folder + "/" + t + ".bias.bin", format="f")
else:
print("Ops!")
def print_wb_output(model, input_batch):
for n, m in model.named_modules():
m.register_forward_hook(hook)
def exp_input(model, input_batch):
# Export the input batch
model(input_batch)
i = input_batch.data.numpy()
i = input_batch.cpu().data.numpy()
i = np.array(i, dtype=np.float32)
print(i.shape)
i.tofile("debug/input.bin", format="f")
print("input: ", i.shape)
def print_wb_output(model):
f = None
for n, m in model.named_modules():
in_output = m._value_hook
@@ -57,7 +76,9 @@ def print_wb_output(model, input_batch):
o = np.array(o, dtype=np.float32)
t = '-'.join(n.split('.'))
o.tofile("debug/" + t + ".bin", format="f")
print('------- ', n, ' ------')
print("debug ",o.shape)
if not(' of Conv2d' in str(m.type) or ' of Linear' in str(m.type) or ' of BatchNorm2d' in str(m.type)):
continue
@@ -66,14 +87,8 @@ def print_wb_output(model, input_batch):
print("open file: ", file_name)
f = open(file_name, mode='wb')
print(n, ' ----------------------------------------------------------------')
# print(m._parameters)
#print(m.type)
w = np.array([])
b = np.array([])
if 'weight' in m._parameters and m._parameters['weight'] is not None:
w = m._parameters['weight'].data.numpy()
w = np.array(w, dtype=np.float32)
@@ -83,9 +98,6 @@ def print_wb_output(model, input_batch):
b = m._parameters['bias'].data.numpy()
b = np.array(b, dtype=np.float32)
print (" bias shape:", np.shape(b))
# else:
# b = np.zeros(w.shape[0], dtype=np.float32)
# print (" bias shape:", np.shape(b))
if 'BatchNorm2d' in str(m.type):
b = m._parameters['bias'].data.numpy()
@@ -96,30 +108,24 @@ def print_wb_output(model, input_batch):
rm = np.array(rm, dtype=np.float32)
rv = m.running_var.data.numpy()
rv = np.array(rv, dtype=np.float32)
#s.tofile(f, format="f")
bin_write(f,b)
bin_write(f,s)
bin_write(f,rm)
bin_write(f,rv)
print (" b shape:", np.shape(b))
print (" s shape:", np.shape(s))
print (" rm shape:", np.shape(rm))
print (" rv shape:", np.shape(rv))
else:
# w.tofile(f, format="f")
bin_write(f,w)
# print("w- ",w)
if b.size > 0:
# b.tofile(f, format="f")
bin_write(f,b)
# print("b - ",b)
if ' of BatchNorm2d' in str(m.type) or ' of Linear' in str(m.type):
f.close()
print("close file")
f = None
# return
@@ -130,34 +136,27 @@ if __name__ == '__main__':
model = torch.hub.load('pytorch/vision', 'resnet101', pretrained=True)
model.eval()
# Download an example image from the pytorch website
url, filename = ("https://github.com/pytorch/hub/raw/master/dog.jpg", "dog.jpg")
try: urllib.URLopener().retrieve(url, filename)
except: urllib.request.urlretrieve(url, filename)
# sample execution (requires torchvision)
input_image = Image.open(filename)
preprocess = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model
# move the input and model to GPU for speed if available
if torch.cuda.is_available():
input_batch = input_batch.to('cuda')
model.to('cuda')
# load an example image and load it on model
model, input_batch = load_ex_image(model)
model.eval()
with torch.no_grad():
output = model(input_batch)
# Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes
# print(output)
# create folders debug and layers if do not exist
create_folders()
# add output attribute to the layers
for n, m in model.named_modules():
m.register_forward_hook(hook)
print_wb_output(model, input_batch)
# export input bin
exp_input(model, input_batch)
# print(list(model.children()))
print_wb_output(model)
with open("resnet101.txt", 'w') as f:
for item in list(model.children()):
f.write("%s\n" % item)
summary(model, (3, 224, 224))
# print(trace(model, input_batch))