Minor fixes.

README.md

@@ -64,7 +64,7 @@ Additional material can be found in Google Drive folder:
 
 All material, excluding the Flickr-Faces-HQ dataset, is made available under [Creative Commons BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) license by NVIDIA Corporation. You can **use, redistribute, and adapt** the material for **non-commercial purposes**, as long as you give appropriate credit by **citing our paper** and **indicating any changes** that you've made.
 
-For license information regarding the FFHQ dataset, please refer to the corresponding [Flickr-Faces-HQ repository](http://stylegan.xyz/ffhq).
+For license information regarding the FFHQ dataset, please refer to the [Flickr-Faces-HQ repository](http://stylegan.xyz/ffhq).
 
 `inception_v3_features.pkl` and `inception_v3_softmax.pkl` are derived from the pre-trained [Inception-v3](https://arxiv.org/abs/1512.00567) network by Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. The network was originally shared under [Apache 2.0](https://github.com/tensorflow/models/blob/master/LICENSE) license on the [TensorFlow Models](https://github.com/tensorflow/models) repository.
 
@@ -77,7 +77,7 @@ For license information regarding the FFHQ dataset, please refer to the correspo
 * Both Linux and Windows are supported, but we strongly recommend Linux for performance and compatibility reasons.
 * 64-bit Python 3.6 installation. We recommend Anaconda3 with numpy 1.14.3 or newer.
 * TensorFlow 1.10.0 or newer with GPU support.
-* One or more high-end NVIDIA Pascal or Volta GPUs with at least 12GB of DRAM. We recommend NVIDIA DGX-1 with 8 Tesla V100 GPUs.
+* One or more high-end NVIDIA GPUs with at least 11GB of DRAM. We recommend NVIDIA DGX-1 with 8 Tesla V100 GPUs.
 * NVIDIA driver 391.35 or newer, CUDA toolkit 9.0 or newer, cuDNN 7.3.1 or newer.
 
 ## Using pre-trained networks
@@ -97,7 +97,7 @@ images_out                      -         (?, 3, 1024, 1024)   -
 Total                           26219627
 
 > ls results
-example.png # https://drive.google.com/open?id=1UDLT_zb-rof9kKH0GwiJW_bS9MoZi8oP
+example.png # https://drive.google.com/uc?id=1UDLT_zb-rof9kKH0GwiJW_bS9MoZi8oP
 ```
 
 A more advanced example is given in [generate_figures.py](./generate_figures.py). The script reproduces the figures from our paper in order to illustrate style mixing, noise inputs, and truncation:
@@ -156,13 +156,13 @@ There are three ways to use the pre-trained generator:
    src_dlatents = Gs.components.mapping.run(src_latents, None) # [seed, layer, component]
    src_images = Gs.components.synthesis.run(src_dlatents, randomize_noise=False, **synthesis_kwargs)
    ```
-   The above code is from [generate_figures.py](./generate_figures.py). It first network to transform a batch of latent vectors into the intermediate *W* space using the mapping network and then turns these vectors into a batch of images using the synthesis network. The `dlatents` array stores a separate copy of the same *w* vector for each layer of the synthesis network to facilitate style mixing.
+   The above code is from [generate_figures.py](./generate_figures.py). It first transforms a batch of latent vectors into the intermediate *W* space using the mapping network and then turns these vectors into a batch of images using the synthesis network. The `dlatents` array stores a separate copy of the same *w* vector for each layer of the synthesis network to facilitate style mixing.
 
 The exact details of the generator are defined in [training/networks_stylegan.py](./training/networks_stylegan.py) (see `G_style`, `G_mapping`, and `G_synthesis`). The following keyword arguments can be specified to modify the behavior when calling `run()` and `get_output_for()`:
 
 * `truncation_psi` and `truncation_cutoff` control the truncation trick that that is performed by default when using `Gs` (ψ=0.7, cutoff=8). It can be disabled by setting `truncation_psi=1` or `is_validation=True`, and the image quality can be further improved at the cost of variation by setting e.g. `truncation_psi=0.5`. Note that truncation is always disabled when using the sub-networks directly. The average *w* needed to manually perform the truncation trick can be looked up using `Gs.get_var('dlatent_avg')`.
 
-* `randomize_noise` determines whether to use re-randomize the noise inputs for each generated image (`True`, default) or whether to use specific noise values for the entire minibatch (`False`). The specific values can be accessed via the `tf.Variable` instances that are found using `[var for name, var in Gsc.components.synthesis.vars.items() if name.startswith('noise')]`.
+* `randomize_noise` determines whether to use re-randomize the noise inputs for each generated image (`True`, default) or whether to use specific noise values for the entire minibatch (`False`). The specific values can be accessed via the `tf.Variable` instances that are found using `[var for name, var in Gs.components.synthesis.vars.items() if name.startswith('noise')]`.
 
 * When using the mapping network directly, you can specify `dlatent_broadcast=None` to disable the automatic duplication of `dlatents` over the layers of the synthesis network.
 
@@ -201,7 +201,7 @@ Once the datasets are set up, you can train your own StyleGAN networks as follow
 3. The results are written to a newly created directory `results/<ID>-<DESCRIPTION>`.
 4. The training may take several days (or weeks) to complete, depending on the configuration.
 
-By default, the `train.py` is configured to train the highest-quality StyleGAN (configuration F in Table 1) for the FFHQ dataset at 1024&times;1024 resolution using 8 GPUs. Please note that we have used 8 GPUs in all of our experiments. Training with fewer GPUs may not produce identical results &ndash; if you wish to compare against our technique, we strongly recommend using the same number of GPUs.
+By default, `train.py` is configured to train the highest-quality StyleGAN (configuration F in Table 1) for the FFHQ dataset at 1024&times;1024 resolution using 8 GPUs. Please note that we have used 8 GPUs in all of our experiments. Training with fewer GPUs may not produce identical results &ndash; if you wish to compare against our technique, we strongly recommend using the same number of GPUs.
 
 Expected training time for 1024&times;1024 resolution using Tesla V100 GPUs: