| | |
|---|
| | | "{}.resnet{}_dense.weight".format(tensor_name_prefix_torch, layer_idx): |
|---|
| | | {"name": "{}/resnet{}_dense/kernel".format(tensor_name_prefix_tf, layer_idx), |
|---|
| | | "squeeze": None, |
|---|
| | | "transpose": (3, 2, 0, 1) if layer_idx == 0 else (1, 0), |
|---|
| | | "transpose": (2, 1, 0) if layer_idx == 0 else (1, 0), |
|---|
| | | }, |
|---|
| | | "{}.resnet{}_dense.bias".format(tensor_name_prefix_torch, layer_idx): |
|---|
| | | {"name": "{}/resnet{}_dense/bias".format(tensor_name_prefix_tf, layer_idx), |
|---|
| | |
|---|
| | | name, data_tf.size(), name_tf, var_dict_tf[name_tf].shape |
|---|
| | | )) |
|---|
| | | else: |
|---|
| | | var_dict_torch_update[name] = torch.Tensor(map_dict[name]).type(torch.int64).to("cpu") |
|---|
| | | var_dict_torch_update[name] = torch.from_numpy(np.array(map_dict[name])).type(torch.int64).to("cpu") |
|---|
| | | logging.info("torch tensor: {}, manually assigning to: {}".format( |
|---|
| | | name, map_dict[name] |
|---|
| | | )) |
|---|
