Hello everyone,
I am trying to convert a pytorch model saved into .pth : resnet-34-kinetics.pth to keras’ hdf5 format. I downloaded the saved model from the internet.
To do so, I am following the guidelines explained here : https://github.com/nerox8664/pytorch2keras
However, I am not able to load the model resnet-34-kinetics.pth into the implementation I found on github from this repository : https://github.com/kenshohara/3D-ResNets-PyTorch
import math
from functools import partial
import torch
import torch.nn as nn
import torch.nn.functional as F
def get_inplanes():
return [64, 128, 256, 512]
def conv3x3x3(in_planes, out_planes, stride=1):
return nn.Conv3d(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
def conv1x1x1(in_planes, out_planes, stride=1):
return nn.Conv3d(in_planes,
out_planes,
kernel_size=1,
stride=stride,
bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1, downsample=None):
super().__init__()
self.conv1 = conv3x3x3(in_planes, planes, stride)
self.bn1 = nn.BatchNorm3d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3x3(planes, planes)
self.bn2 = nn.BatchNorm3d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, in_planes, planes, stride=1, downsample=None):
super().__init__()
self.conv1 = conv1x1x1(in_planes, planes)
self.bn1 = nn.BatchNorm3d(planes)
self.conv2 = conv3x3x3(planes, planes, stride)
self.bn2 = nn.BatchNorm3d(planes)
self.conv3 = conv1x1x1(planes, planes * self.expansion)
self.bn3 = nn.BatchNorm3d(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self,
block,
layers,
block_inplanes,
n_input_channels=3,
conv1_t_size=7,
conv1_t_stride=1,
no_max_pool=False,
shortcut_type='B',
widen_factor=1.0,
n_classes=400):
super().__init__()
block_inplanes = [int(x * widen_factor) for x in block_inplanes]
self.in_planes = block_inplanes[0]
self.no_max_pool = no_max_pool
self.conv1 = nn.Conv3d(n_input_channels,
self.in_planes,
kernel_size=(conv1_t_size, 7, 7),
stride=(conv1_t_stride, 2, 2),
padding=(conv1_t_size // 2, 3, 3),
bias=False)
self.bn1 = nn.BatchNorm3d(self.in_planes)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool3d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, block_inplanes[0], layers[0],
shortcut_type)
self.layer2 = self._make_layer(block,
block_inplanes[1],
layers[1],
shortcut_type,
stride=2)
self.layer3 = self._make_layer(block,
block_inplanes[2],
layers[2],
shortcut_type,
stride=2)
self.layer4 = self._make_layer(block,
block_inplanes[3],
layers[3],
shortcut_type,
stride=2)
self.avgpool = nn.AdaptiveAvgPool3d((1, 1, 1))
self.fc = nn.Linear(block_inplanes[3] * block.expansion, n_classes)
for m in self.modules():
if isinstance(m, nn.Conv3d):
nn.init.kaiming_normal_(m.weight,
mode='fan_out',
nonlinearity='relu')
elif isinstance(m, nn.BatchNorm3d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def _downsample_basic_block(self, x, planes, stride):
out = F.avg_pool3d(x, kernel_size=1, stride=stride)
zero_pads = torch.zeros(out.size(0), planes - out.size(1), out.size(2),
out.size(3), out.size(4))
if isinstance(out.data, torch.cuda.FloatTensor):
zero_pads = zero_pads.cuda()
out = torch.cat([out.data, zero_pads], dim=1)
return out
def _make_layer(self, block, planes, blocks, shortcut_type, stride=1):
downsample = None
if stride != 1 or self.in_planes != planes * block.expansion:
if shortcut_type == 'A':
downsample = partial(self._downsample_basic_block,
planes=planes * block.expansion,
stride=stride)
else:
downsample = nn.Sequential(
conv1x1x1(self.in_planes, planes * block.expansion, stride),
nn.BatchNorm3d(planes * block.expansion))
layers = []
layers.append(
block(in_planes=self.in_planes,
planes=planes,
stride=stride,
downsample=downsample))
self.in_planes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.in_planes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
if not self.no_max_pool:
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def generate_model(model_depth, **kwargs):
assert model_depth in [10, 18, 34, 50, 101, 152, 200]
if model_depth == 10:
model = ResNet(BasicBlock, [1, 1, 1, 1], get_inplanes(), **kwargs)
elif model_depth == 18:
model = ResNet(BasicBlock, [2, 2, 2, 2], get_inplanes(), **kwargs)
elif model_depth == 34:
model = ResNet(BasicBlock, [3, 4, 6, 3], get_inplanes(), **kwargs)
elif model_depth == 50:
model = ResNet(Bottleneck, [3, 4, 6, 3], get_inplanes(), **kwargs)
elif model_depth == 101:
model = ResNet(Bottleneck, [3, 4, 23, 3], get_inplanes(), **kwargs)
elif model_depth == 152:
model = ResNet(Bottleneck, [3, 8, 36, 3], get_inplanes(), **kwargs)
elif model_depth == 200:
model = ResNet(Bottleneck, [3, 24, 36, 3], get_inplanes(), **kwargs)
return model
model = generate_model(34);
# load weights here
model.load_state_dict(torch.load("resnet-34-kinetics.pth"))
Here is the error I am getting after trying to load these weights into the architecture :
Traceback (most recent call last):
File "resnet3d_pytorch.py", line 241, in <module>
model.load_state_dict(torch.load("resnet-34-kinetics.pth"))
File "/home/yellowishlights/anaconda3/envs/py37/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1052, in load_state_dict
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for ResNet:
Missing key(s) in state_dict: "conv1.weight", "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "layer1.0.conv1.weight", "layer1.0.bn1.weight", "layer1.0.bn1.bias", "layer1.0.bn1.running_mean", "layer1.0.bn1.running_var", "layer1.0.conv2.weight", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.1.conv1.weight", "layer1.1.bn1.weight", "layer1.1.bn1.bias", "layer1.1.bn1.running_mean", "layer1.1.bn1.running_var", "layer1.1.conv2.weight", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.1.bn2.running_mean", "layer1.1.bn2.running_var", "layer1.2.conv1.weight", "layer1.2.bn1.weight", "layer1.2.bn1.bias", "layer1.2.bn1.running_mean", "layer1.2.bn1.running_var", "layer1.2.conv2.weight", "layer1.2.bn2.weight", "layer1.2.bn2.bias", "layer1.2.bn2.running_mean", "layer1.2.bn2.running_var", "layer2.0.conv1.weight", "layer2.0.bn1.weight", "layer2.0.bn1.bias", "layer2.0.bn1.running_mean", "layer2.0.bn1.running_var", "layer2.0.conv2.weight", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.0.downsample.0.weight", "layer2.0.downsample.1.weight", "layer2.0.downsample.1.bias", "layer2.0.downsample.1.running_mean", "layer2.0.downsample.1.running_var", "layer2.1.conv1.weight", "layer2.1.bn1.weight", "layer2.1.bn1.bias", "layer2.1.bn1.running_mean", "layer2.1.bn1.running_var", "layer2.1.conv2.weight", "layer2.1.bn2.weight", "layer2.1.bn2.bias", "layer2.1.bn2.running_mean", "layer2.1.bn2.running_var", "layer2.2.conv1.weight", "layer2.2.bn1.weight", "layer2.2.bn1.bias", "layer2.2.bn1.running_mean", "layer2.2.bn1.running_var", "layer2.2.conv2.weight", "layer2.2.bn2.weight", "layer2.2.bn2.bias", "layer2.2.bn2.running_mean", "layer2.2.bn2.running_var", "layer2.3.conv1.weight", "layer2.3.bn1.weight", "layer2.3.bn1.bias", "layer2.3.bn1.running_mean", "layer2.3.bn1.running_var", "layer2.3.conv2.weight", "layer2.3.bn2.weight", "layer2.3.bn2.bias", "layer2.3.bn2.running_mean", "layer2.3.bn2.running_var", "layer3.0.conv1.weight", "layer3.0.bn1.weight", "layer3.0.bn1.bias", "layer3.0.bn1.running_mean", "layer3.0.bn1.running_var", "layer3.0.conv2.weight", "layer3.0.bn2.weight", "layer3.0.bn2.bias", "layer3.0.bn2.running_mean", "layer3.0.bn2.running_var", "layer3.0.downsample.0.weight", "layer3.0.downsample.1.weight", "layer3.0.downsample.1.bias", "layer3.0.downsample.1.running_mean", "layer3.0.downsample.1.running_var", "layer3.1.conv1.weight", "layer3.1.bn1.weight", "layer3.1.bn1.bias", "layer3.1.bn1.running_mean", "layer3.1.bn1.running_var", "layer3.1.conv2.weight", "layer3.1.bn2.weight", "layer3.1.bn2.bias", "layer3.1.bn2.running_mean", "layer3.1.bn2.running_var", "layer3.2.conv1.weight", "layer3.2.bn1.weight", "layer3.2.bn1.bias", "layer3.2.bn1.running_mean", "layer3.2.bn1.running_var", "layer3.2.conv2.weight", "layer3.2.bn2.weight", "layer3.2.bn2.bias", "layer3.2.bn2.running_mean", "layer3.2.bn2.running_var", "layer3.3.conv1.weight", "layer3.3.bn1.weight", "layer3.3.bn1.bias", "layer3.3.bn1.running_mean", "layer3.3.bn1.running_var", "layer3.3.conv2.weight", "layer3.3.bn2.weight", "layer3.3.bn2.bias", "layer3.3.bn2.running_mean", "layer3.3.bn2.running_var", "layer3.4.conv1.weight", "layer3.4.bn1.weight", "layer3.4.bn1.bias", "layer3.4.bn1.running_mean", "layer3.4.bn1.running_var", "layer3.4.conv2.weight", "layer3.4.bn2.weight", "layer3.4.bn2.bias", "layer3.4.bn2.running_mean", "layer3.4.bn2.running_var", "layer3.5.conv1.weight", "layer3.5.bn1.weight", "layer3.5.bn1.bias", "layer3.5.bn1.running_mean", "layer3.5.bn1.running_var", "layer3.5.conv2.weight", "layer3.5.bn2.weight", "layer3.5.bn2.bias", "layer3.5.bn2.running_mean", "layer3.5.bn2.running_var", "layer4.0.conv1.weight", "layer4.0.bn1.weight", "layer4.0.bn1.bias", "layer4.0.bn1.running_mean", "layer4.0.bn1.running_var", "layer4.0.conv2.weight", "layer4.0.bn2.weight", "layer4.0.bn2.bias", "layer4.0.bn2.running_mean", "layer4.0.bn2.running_var", "layer4.0.downsample.0.weight", "layer4.0.downsample.1.weight", "layer4.0.downsample.1.bias", "layer4.0.downsample.1.running_mean", "layer4.0.downsample.1.running_var", "layer4.1.conv1.weight", "layer4.1.bn1.weight", "layer4.1.bn1.bias", "layer4.1.bn1.running_mean", "layer4.1.bn1.running_var", "layer4.1.conv2.weight", "layer4.1.bn2.weight", "layer4.1.bn2.bias", "layer4.1.bn2.running_mean", "layer4.1.bn2.running_var", "layer4.2.conv1.weight", "layer4.2.bn1.weight", "layer4.2.bn1.bias", "layer4.2.bn1.running_mean", "layer4.2.bn1.running_var", "layer4.2.conv2.weight", "layer4.2.bn2.weight", "layer4.2.bn2.bias", "layer4.2.bn2.running_mean", "layer4.2.bn2.running_var", "fc.weight", "fc.bias".
Unexpected key(s) in state_dict: "epoch", "arch", "state_dict", "optimizer".