torch version

[rom1504]

class Normalization(nn.Module):
    def __init__(self, shape):
        super().__init__()
        self.register_buffer('mean', torch.zeros(shape))
        self.register_buffer('variance', torch.ones(shape))

    def forward(self, x):
        return (x - self.mean) / self.variance.sqrt()
    

class NSFWModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.norm = Normalization([768])
        self.linear_1 = nn.Linear(768, 64)
        self.linear_2 = nn.Linear(64, 512)
        self.linear_3 = nn.Linear(512, 256)
        self.linear_4 = nn.Linear(256, 1)
        self.act = nn.ReLU()
        self.act_out = nn.Sigmoid()

    def forward(self, x):
        x = self.norm(x)
        x = self.act(self.linear_1(x))
        x = self.act(self.linear_2(x))
        x = self.act(self.linear_3(x))
        x = self.act_out(self.linear_4(x))
        return x

clip_autokeras_binary_nsfw.zip

conversion notebook:
port_nsfw_to_pytorch.zip

from @crowsonkb

[SingL3]

Hi, @rom1504, I tried this and got this error:
ValueError: Unknown optimizer: 'Custom>AdamWeightDecay'. Please ensure you are using a keras.utils.custom_object_scope and that this object is included in the scope. See https://www.tensorflow.org/guide/keras/save_and_serialize#registering_the_custom_object for details.

[a574824551]

Hi, @rom1504, I tried this and got this error: ValueError: Unknown optimizer: 'Custom>AdamWeightDecay'. Please ensure you are using a keras.utils.custom_object_scope and that this object is included in the scope. See https://www.tensorflow.org/guide/keras/save_and_serialize#registering_the_custom_object for details.

model = tf.keras.models.load_model(path_to_model, compile=False)

[doublex]

Is it possible to inference using torch?

[a574824551]

Is it possible to inference using torch?

yes, I have tried.