merge_mode="concat",
batchnorm=True)
plot_net_rescue(model, shape=(1, 1, 64, 64, 64), outfileroot=None)
############################################################################
# Inspect a network
# -----------------
#
# The module propose utilities to inspect easyly some layers of the network.
from pynet.utils import test_model
from pprint import pprint
import numpy as np
from pynet.utils import get_named_layers
from pynet.utils import layer_at
from pynet.plotting import plot_data
out = test_model(model, shape=(1, 1, 64, 64, 64))
layers = get_named_layers(model)
pprint(layers)
hook_x, weight = layer_at(model=model,
layer_name="down.1.doubleconv.conv1-8.16",
x=torch.FloatTensor(
np.random.random((1, 1, 64, 64, 64))))
print(hook_x.shape)
print(weight.shape)
plot_data(hook_x[:, :1])
# import matplotlib.pyplot as plt
# plt.show()
# Load the model
# --------------
#
# Load the model and fix all weights.
# Change the last linear layer.
cl = classifier.ResNet18(
num_classes=1000,
pretrained="/neurospin/nsap/torch/models/resnet18-5c106cde.pth",
batch_size=50,
optimizer_name="Adam",
learning_rate=1e-4,
loss_name="NLLLoss",
metrics=["accuracy"])
print(cl.model)
layers = get_named_layers(cl.model, allowed_layers=[nn.Module], resume=True)
print(layers.keys())
to_freeze_layers = [
"conv1", "bn1", "relu", "maxpool", "layer1", "layer2", "layer3", "layer4"
]
freeze_layers(cl.model, to_freeze_layers)
nb_features = cl.model.fc.in_features
cl.model.fc = nn.Linear(nb_features, 9)
#############################################################################
# Retrain the model
# -----------------
#
# Train the model