Update README 2

.ipynb_checkpoints/README-checkpoint.md

@@ -14,6 +14,7 @@ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-
 # Stable diffusion finetune using LoRA
 
 ## HuggingFace Spaces URL: https://huggingface.co/spaces/asrimanth/person-thumbs-up
+## Please note that the app on spaces is very slow due to compute constraints. For good results, please try locally.
 
 ## Approach
 
@@ -43,8 +44,8 @@ Number of epochs : 50-60
 Augmentations used : Center crop, Random Flip
 Gradient accumulation steps : Tried 1, 3, and 4 for different experiments. 4 gave decent results.
 
-text2image_fine-tune wandb dashboard:
-**https://wandb.ai/asrimanth/text2image_fine-tune**
+text2image_fine-tune :
+**wandb dashboard : https://wandb.ai/asrimanth/text2image_fine-tune**
 **Model card for asrimanth/person-thumbs-up-lora: https://huggingface.co/asrimanth/person-thumbs-up-lora**
 **Prompt: ```<tom_cruise> #thumbsup```**
 
@@ -52,12 +53,12 @@ Deployed models:
 
 When the above experiment failed, I had to try different datasets. One of them was "tom cruise".
 
-srimanth-thumbs-up-lora-plain wandb dashboard: We use the plain dataset with srimanth mentioned above.
+srimanth-thumbs-up-lora-plain : We use the plain dataset with srimanth mentioned above.
 **wandb link: https://wandb.ai/asrimanth/srimanth-thumbs-up-lora-plain**
 **Model card for srimanth-thumbs-up-lora-plain: https://huggingface.co/asrimanth/srimanth-thumbs-up-lora-plain**
 **Prompt: ```srimanth thumbs up```**
 
-person-thumbs-up-plain-lora wandb dashboard:
+person-thumbs-up-plain-lora wandb : We use the 
 **wandb link: https://wandb.ai/asrimanth/person-thumbs-up-plain-lora**
 **Model card for asrimanth/person-thumbs-up-plain-lora: https://huggingface.co/asrimanth/person-thumbs-up-plain-lora**
 **Prompt: ```tom cruise thumbs up```**
@@ -77,5 +78,18 @@ person-thumbs-up-lora-no-cap wandb dashboard:
 
 ### Deployment
 
+To run inference locally, choose a model and run the command:
+```
+python3 inference.py
+```
+
+To run the streamlit app locally, run the command:
+```
+streamlit run app.py
+```
+
 + I chose streamlit to deploy the application on HuggingFace spaces. It was developer friendly and the app logic can be found in app.py
 + Streamlit app would be a great choice for an MVP.
++ AWS sagemaker would be a good choice for deploying models, since it supports huggingface models with minimal friction.
++ A docker container orchestrated in a kubernetes cluster would be ideal.
++ In practice, evaluation of models in real-time would let us know if there is model drift and retrain accordingly.

.ipynb_checkpoints/app-checkpoint.py

@@ -71,7 +71,7 @@ if __name__ == "__main__":
         with col1_inp:
             n_images = int(st.number_input("Enter the number of images", value=3, min_value=0, max_value=50))
         with col2_inp:
-            n_inference_steps = int(st.number_input("Enter the number of inference steps", value=3, min_value=0))
+            n_inference_steps = int(st.number_input("Enter the number of inference steps", value=5, min_value=0))
         with col_3_inp:
             seed_input = int(st.number_input("Enter the seed (default=25)", value=25, min_value=0))
         submitted = st.form_submit_button("Predict")

README.md

@@ -14,6 +14,7 @@ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-
 # Stable diffusion finetune using LoRA
 
 ## HuggingFace Spaces URL: https://huggingface.co/spaces/asrimanth/person-thumbs-up
+## Please note that the app on spaces is very slow due to compute constraints. For good results, please try locally.
 
 ## Approach
 
@@ -43,8 +44,8 @@ Number of epochs : 50-60
 Augmentations used : Center crop, Random Flip
 Gradient accumulation steps : Tried 1, 3, and 4 for different experiments. 4 gave decent results.
 
-text2image_fine-tune wandb dashboard:
-**https://wandb.ai/asrimanth/text2image_fine-tune**
+text2image_fine-tune :
+**wandb dashboard : https://wandb.ai/asrimanth/text2image_fine-tune**
 **Model card for asrimanth/person-thumbs-up-lora: https://huggingface.co/asrimanth/person-thumbs-up-lora**
 **Prompt: ```<tom_cruise> #thumbsup```**
 
@@ -52,12 +53,12 @@ Deployed models:
 
 When the above experiment failed, I had to try different datasets. One of them was "tom cruise".
 
-srimanth-thumbs-up-lora-plain wandb dashboard: We use the plain dataset with srimanth mentioned above.
+srimanth-thumbs-up-lora-plain : We use the plain dataset with srimanth mentioned above.
 **wandb link: https://wandb.ai/asrimanth/srimanth-thumbs-up-lora-plain**
 **Model card for srimanth-thumbs-up-lora-plain: https://huggingface.co/asrimanth/srimanth-thumbs-up-lora-plain**
 **Prompt: ```srimanth thumbs up```**
 
-person-thumbs-up-plain-lora wandb dashboard:
+person-thumbs-up-plain-lora wandb : We use the 
 **wandb link: https://wandb.ai/asrimanth/person-thumbs-up-plain-lora**
 **Model card for asrimanth/person-thumbs-up-plain-lora: https://huggingface.co/asrimanth/person-thumbs-up-plain-lora**
 **Prompt: ```tom cruise thumbs up```**
@@ -77,5 +78,18 @@ person-thumbs-up-lora-no-cap wandb dashboard:
 
 ### Deployment
 
+To run inference locally, choose a model and run the command:
+```
+python3 inference.py
+```
+
+To run the streamlit app locally, run the command:
+```
+streamlit run app.py
+```
+
 + I chose streamlit to deploy the application on HuggingFace spaces. It was developer friendly and the app logic can be found in app.py
 + Streamlit app would be a great choice for an MVP.
++ AWS sagemaker would be a good choice for deploying models, since it supports huggingface models with minimal friction.
++ A docker container orchestrated in a kubernetes cluster would be ideal.
++ In practice, evaluation of models in real-time would let us know if there is model drift and retrain accordingly.

app.py

@@ -71,7 +71,7 @@ if __name__ == "__main__":
         with col1_inp:
             n_images = int(st.number_input("Enter the number of images", value=3, min_value=0, max_value=50))
         with col2_inp:
-            n_inference_steps = int(st.number_input("Enter the number of inference steps", value=3, min_value=0))
+            n_inference_steps = int(st.number_input("Enter the number of inference steps", value=5, min_value=0))
         with col_3_inp:
             seed_input = int(st.number_input("Enter the seed (default=25)", value=25, min_value=0))
         submitted = st.form_submit_button("Predict")