Added constants as a lambda layer.

Author: gmalivenko

pytorch2keras/layers.py

@@ -1,4 +1,5 @@
 import keras.layers
+import numpy as np
 import random
 
 
@@ -652,6 +653,25 @@ def convert_reduce_sum(params, w_name, scope_name, inputs, layers, weights):
     layers[scope_name] = lambda_layer(layers[inputs[0]])
 
 
+def convert_constant(params, w_name, scope_name, inputs, layers, weights):
+    """
+    Convert constant layer.
+
+   Args:
+        params: dictionary with layer parameters
+        w_name: name prefix in state_dict
+        scope_name: pytorch scope name
+        inputs: pytorch node inputs
+        layers: dictionary with keras tensors
+        weights: pytorch state_dict
+    """
+    print('Converting constant ...')
+
+    target_layer = lambda x: keras.backend.constant(np.float32(params['value']))
+    lambda_layer = keras.layers.Lambda(target_layer)
+    layers[scope_name] = lambda_layer(layers[inputs[0]])
+
+
 AVAILABLE_CONVERTERS = {
     'Conv': convert_conv,
     'ConvTranspose': convert_convtranspose,
@@ -675,4 +695,5 @@ def convert_reduce_sum(params, w_name, scope_name, inputs, layers, weights):
     'MatMul': convert_matmul,
     'Gather': convert_gather,
     'ReduceSum': convert_reduce_sum,
+    'Constant': convert_constant,
 }

tests/const.py

@@ -0,0 +1,48 @@
+import keras  # work around segfault
+import sys
+import numpy as np
+
+import torch
+import torch.nn as nn
+from torch.autograd import Variable
+
+sys.path.append('../pytorch2keras')
+from converter import pytorch_to_keras
+
+
+class TestConst(nn.Module):
+    """Module for Const conversion testing
+    """
+
+    def __init__(self, inp=10, out=16, bias=True):
+        super(TestConst, self).__init__()
+        self.linear = nn.Linear(inp, out, bias=False)
+
+    def forward(self, x):
+        x = self.linear(x) * 2.0
+        return x
+
+
+if __name__ == '__main__':
+    max_error = 0
+    for i in range(100):
+        inp = np.random.randint(1, 100)
+        out = np.random.randint(1, 100)
+        model = TestConst(inp, out, inp % 2)
+
+        input_np = np.random.uniform(0, 1, (1, inp))
+        input_var = Variable(torch.FloatTensor(input_np))
+
+        output = model(input_var)
+
+        k_model = pytorch_to_keras(model, input_var, (inp,), verbose=True)
+
+        pytorch_output = output.data.numpy()
+        keras_output = k_model.predict(input_np)
+
+        error = np.max(pytorch_output - keras_output)
+        print(error)
+        if max_error < error:
+            max_error = error
+
+    print('Max error: {0}'.format(max_error))