Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updates

This commit is contained in:
Glenn Jocher 2020-02-19 14:57:58 -08:00
parent f4a9e5cd58
commit a9cbc28214
1 changed files with 20 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
models.py
View File

@ -264,9 +264,9 @@ class Darknet(nn.Module):
if mtype in ['convolutional', 'upsample', 'maxpool']:
x = module(x)
elif mtype == 'shortcut': # sum
x = module(x, layer_outputs) # weightedFeatureFusion()
if verbose:
print('shortcut/add %s' % ([layer_outputs[i].shape for i in module.layers]))
print('shortcut/add %s + %s' % (x.shape, [layer_outputs[i].shape for i in module.layers]))
x = module(x, layer_outputs) # weightedFeatureFusion()
elif mtype == 'route': # concat
layers = [int(x) for x in mdef['layers'].split(',')]
if verbose:
@ -354,38 +354,33 @@ def load_darknet_weights(self, weights, cutoff=-1):
ptr = 0
for i, (mdef, module) in enumerate(zip(self.module_defs[:cutoff], self.module_list[:cutoff])):
if mdef['type'] == 'convolutional':
conv_layer = module[0]
conv = module[0]
if mdef['batch_normalize']:
# Load BN bias, weights, running mean and running variance
bn_layer = module[1]
num_b = bn_layer.bias.numel() # Number of biases
bn = module[1]
nb = bn.bias.numel() # number of biases
# Bias
bn_b = torch.from_numpy(weights[ptr:ptr + num_b]).view_as(bn_layer.bias)
bn_layer.bias.data.copy_(bn_b)
ptr += num_b
bn.bias.data.copy_(torch.from_numpy(weights[ptr:ptr + nb]).view_as(bn.bias))
ptr += nb
# Weight
bn_w = torch.from_numpy(weights[ptr:ptr + num_b]).view_as(bn_layer.weight)
bn_layer.weight.data.copy_(bn_w)
ptr += num_b
bn.weight.data.copy_(torch.from_numpy(weights[ptr:ptr + nb]).view_as(bn.weight))
ptr += nb
# Running Mean
bn_rm = torch.from_numpy(weights[ptr:ptr + num_b]).view_as(bn_layer.running_mean)
bn_layer.running_mean.data.copy_(bn_rm)
ptr += num_b
bn.running_mean.data.copy_(torch.from_numpy(weights[ptr:ptr + nb]).view_as(bn.running_mean))
ptr += nb
# Running Var
bn_rv = torch.from_numpy(weights[ptr:ptr + num_b]).view_as(bn_layer.running_var)
bn_layer.running_var.data.copy_(bn_rv)
ptr += num_b
bn.running_var.data.copy_(torch.from_numpy(weights[ptr:ptr + nb]).view_as(bn.running_var))
ptr += nb
else:
# Load conv. bias
num_b = conv_layer.bias.numel()
conv_b = torch.from_numpy(weights[ptr:ptr + num_b]).view_as(conv_layer.bias)
conv_layer.bias.data.copy_(conv_b)
ptr += num_b
nb = conv.bias.numel()
conv_b = torch.from_numpy(weights[ptr:ptr + nb]).view_as(conv.bias)
conv.bias.data.copy_(conv_b)
ptr += nb
# Load conv. weights
num_w = conv_layer.weight.numel()
conv_w = torch.from_numpy(weights[ptr:ptr + num_w]).view_as(conv_layer.weight)
conv_layer.weight.data.copy_(conv_w)
ptr += num_w
nw = conv.weight.numel() # number of weights
conv.weight.data.copy_(torch.from_numpy(weights[ptr:ptr + nw]).view_as(conv.weight))
ptr += nw
def save_weights(self, path='model.weights', cutoff=-1):