ss_baselines/av_nav/models/visual_cnn.py [81:120]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if self._n_input_rgb > 0:
            cnn_dims = np.array(
                observation_space.spaces["rgb"].shape[:2], dtype=np.float32
            )
        elif self._n_input_depth > 0:
            cnn_dims = np.array(
                observation_space.spaces["depth"].shape[:2], dtype=np.float32
            )

        if self.is_blind:
            self.cnn = nn.Sequential()
        else:
            for kernel_size, stride in zip(
                self._cnn_layers_kernel_size, self._cnn_layers_stride
            ):
                cnn_dims = conv_output_dim(
                    dimension=cnn_dims,
                    padding=np.array([0, 0], dtype=np.float32),
                    dilation=np.array([1, 1], dtype=np.float32),
                    kernel_size=np.array(kernel_size, dtype=np.float32),
                    stride=np.array(stride, dtype=np.float32),
                )

            self.cnn = nn.Sequential(
                nn.Conv2d(
                    in_channels=self._n_input_rgb + self._n_input_depth,
                    out_channels=32,
                    kernel_size=self._cnn_layers_kernel_size[0],
                    stride=self._cnn_layers_stride[0],
                ),
                nn.ReLU(True),
                nn.Conv2d(
                    in_channels=32,
                    out_channels=64,
                    kernel_size=self._cnn_layers_kernel_size[1],
                    stride=self._cnn_layers_stride[1],
                ),
                nn.ReLU(True),
                nn.Conv2d(
                    in_channels=64,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



ss_baselines/av_wan/models/visual_cnn.py [45:84]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if self._n_input_rgb > 0:
            cnn_dims = np.array(
                observation_space.spaces["rgb"].shape[:2], dtype=np.float32
            )
        elif self._n_input_depth > 0:
            cnn_dims = np.array(
                observation_space.spaces["depth"].shape[:2], dtype=np.float32
            )

        if self.is_blind:
            self.cnn = nn.Sequential()
        else:
            for kernel_size, stride in zip(
                self._cnn_layers_kernel_size, self._cnn_layers_stride
            ):
                cnn_dims = conv_output_dim(
                    dimension=cnn_dims,
                    padding=np.array([0, 0], dtype=np.float32),
                    dilation=np.array([1, 1], dtype=np.float32),
                    kernel_size=np.array(kernel_size, dtype=np.float32),
                    stride=np.array(stride, dtype=np.float32),
                )

            self.cnn = nn.Sequential(
                nn.Conv2d(
                    in_channels=self._n_input_rgb + self._n_input_depth,
                    out_channels=32,
                    kernel_size=self._cnn_layers_kernel_size[0],
                    stride=self._cnn_layers_stride[0],
                ),
                nn.ReLU(True),
                nn.Conv2d(
                    in_channels=32,
                    out_channels=64,
                    kernel_size=self._cnn_layers_kernel_size[1],
                    stride=self._cnn_layers_stride[1],
                ),
                nn.ReLU(True),
                nn.Conv2d(
                    in_channels=64,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -