fixed typos and added info pointed out in evaluation

README.md

@@ -7,7 +7,7 @@ tags:
 
 ## Model Details
 
-This model is a finetuned [CLIP by OpenAI](https://huggingface.co/openai/clip-vit-base-patch32). It is designed with aim to improve zero-shot image classification, text-to-image and image-to-image retrieval specically on remote sencing images.
+This model is a finetuned [CLIP by OpenAI](https://huggingface.co/openai/clip-vit-base-patch32). It is designed with an aim to improve zero-shot image classification, text-to-image and image-to-image retrieval specifically on remote sensing images.
 
 ### Model Date
 
@@ -19,22 +19,22 @@ The base model uses a ViT-B/32 Transformer architecture as an image encoder and
 
 ### Model Version
 
-We release several checkpoints for `clip-rsicd` model. Refer to [our github repo](https://github.com/arampacha/CLIP-rsicd) for zero-shot classification for each of those.
+We release several checkpoints for `clip-rsicd` model. Refer to [our github repo](https://github.com/arampacha/CLIP-rsicd#evaluation-results) for performance metrics on zero-shot classification for each of those.
 
 ### Training
 
 To reproduce the fine-tuning procedure one can use released [script](https://github.com/arampacha/CLIP-rsicd/blob/master/run_clip_flax_tv.py). 
-The model was trained using batch size 1024, adafactor optimizer with linear warmup and decay with peack learning rate 1e-4 on 1 TPU-v3-8.
-Full log of the training run done to produce can be found on [WandB](https://wandb.ai/wandb/hf-flax-clip-rsicd/runs/1ts243k3).
+The model was trained using batch size 1024, adafactor optimizer with linear warmup and decay with peak learning rate 1e-4 on 1 TPU-v3-8.
+Full log of the training run can be found on [WandB](https://wandb.ai/wandb/hf-flax-clip-rsicd/runs/1ts243k3).
 
 ### Demo
 
-Checko out the model text-to-image and image-to-image capabilities using [this demo](https://huggingface.co/spaces/sujitpal/clip-rsicd-demo).
+Check out the model text-to-image and image-to-image capabilities using [this demo](https://huggingface.co/spaces/sujitpal/clip-rsicd-demo).
 
 
 ### Documents
 
-- [Fine-tuning CLIP on RSICD with HuggingFace and flax/jax on colab using TPU]()
+- [Fine-tuning CLIP on RSICD with HuggingFace and flax/jax on colab using TPU](https://colab.research.google.com/github/arampacha/CLIP-rsicd/blob/master/nbs/Finetuning_CLIP_with_HF_and_jax.ipynb)
 
 
 ### Use with Transformers
@@ -67,7 +67,12 @@ for l, p in zip(labels, probs[0]):
 
 ### Intended Use
 
-The model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such models - the CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis.
+The model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. 
+
+In addition, we can imagine applications in defense and law enforcement, climate change and global warming, and even some consumer applications. A partial list of applications can be found [here](https://github.com/arampacha/CLIP-rsicd#applications). In general we think such models can be useful as digital assistants for humans engaged in searching through large collections of images.
+
+We also hope it can be used for interdisciplinary studies of the potential impact of such models - the CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis.
+
 
 #### Primary intended uses
 
@@ -79,7 +84,7 @@ We primarily imagine the model will be used by researchers to better understand
 
 ## Data
 
-The model was trained on publicly available remote sensing image cations datasets. Namely [RSICD](), [UCM]() and [Sydney]().
+The model was trained on publicly available remote sensing image captions datasets. Namely [RSICD](https://github.com/201528014227051/RSICD_optimal), [UCM](https://mega.nz/folder/wCpSzSoS#RXzIlrv--TDt3ENZdKN8JA) and [Sydney](https://mega.nz/folder/pG4yTYYA#4c4buNFLibryZnlujsrwEQ). More information on the datasets used can be found on [our project page](https://github.com/arampacha/CLIP-rsicd#dataset).
 
 
 ## Performance and Limitations