big overhaul

app.py

@@ -10,10 +10,10 @@ CACHED_FILE_PATH = hf_hub_download(repo_id="sasha/co2_submissions", filename="co
 
 api = HfApi()
 
-def write_to_csv(hardware, training_time, provider, carbon_intensity, dynamic_emissions):
+def write_to_csv(hardware, gpu_tdp, num_gpus, training_time, provider, carbon_intensity, dynamic_emissions, experimentation_time, experimental_emissions, pue, pue_emissions, embodied_type, embodied_emissions, model_info):
     with open(CACHED_FILE_PATH,'a', newline='') as f:
         writer = csv.writer(f)
-        writer.writerow([hardware, training_time, provider, carbon_intensity, dynamic_emissions])
+        writer.writerow([hardware, gpu_tdp, num_gpus, training_time, provider, carbon_intensity, dynamic_emissions, experimentation_time, experimental_emissions, pue, pue_emissions, embodied_type, embodied_emissions, model_info])
     api.upload_file(
         path_or_fileobj=CACHED_FILE_PATH,
         path_in_repo="co2_emissions.csv",
@@ -48,39 +48,55 @@ instances = pd.read_csv(compute_url)
 providers = [p.upper() for p in instances['provider'].unique().tolist()]
 providers.append('Local/Private Infastructure')
 
+### Default values
+hardware = "N/A"
+gpu_tdp = 0
+num_gpus = 0
+training_time = 0.0
+provider = "N/A"
+carbon_intensity = 0.0
+dynamic_emissions = 0.0
+experimentation_time = 0.0
+experimental_emissions = 0.0
+pue = 1.0
+pue_emissions = 0.0
+embodied_type = 0.0
+embodied_emissions = 0.0
+model_info = "N/A"
+
+### Conversion factors
 kg_per_mile = 0.348
+embodied_conversion_factor = 0.0289
 
 electricity = pd.read_csv(electricity_url)
 servers = pd.read_csv(server_url)
-#print(servers.columns)
 embodied_gpu = pd.read_csv(embodied_gpu_url)
-#print(embodied_gpu.columns)
-
 #st.image('images/MIT_carbon_image_narrow.png', use_column_width=True, caption = 'Image credit: ')
 st.title("AI Carbon Calculator")
 
 st.markdown('## Estimate your AI model\'s CO2 carbon footprint! 🌎🖥️🌎')
-
-st.markdown('##### The calculators below will help you calculate different aspects of your model\'s carbon footprint, as we did for'
-            ' BLOOM 🌸, a 176-billion parameter language model [(see our preprint!)](https://arxiv.org/abs/2211.02001)')
-st.markdown('##### Don\'t forget to share your data to help us get a better idea of AI model\'s carbon emissions!')
+st.markdown('### Calculating the carbon footprint of AI models can be hard... this tool is here to help!')
+st.markdown('##### Use the calculators below to calculate different aspects of your model\'s carbon footprint' \
+            'and don\'t forget to share your data to help the community better understand the carbon emissions of AI!')
 
 st.markdown('### Dynamic Emissions 🚀')
 st.markdown('##### These are the emissions produced by generating the electricity necessary for powering model training.')
 with st.expander("Calculate the dynamic emissions of your model"):
-    col1, col2, col3, col4 = st.columns(4)
+    col1, col2, col3, col4, col5 = st.columns(5)
     with col1:
-        hardware = st.selectbox('GPU used', TDP['name'].tolist())
+        hardware = st.selectbox('Hardware used', TDP['name'].tolist())
         gpu_tdp = TDP['tdp_watts'][TDP['name'] == hardware].tolist()[0]
-        st.markdown("Different GPUs have different TDP (Thermal Design Power), which impacts how much energy you use.")
+        st.markdown("Different hardware has different TDP (Thermal Design Power), which impacts how much energy you use.")
     with col2:
-       training_time = st.number_input('Total number of GPU hours')
-       st.markdown('This is calculated by multiplying the number of GPUs you used by the training time: '
-                   'i.e. if you used 100 GPUs for 10 hours, this is equal to 100x10 = 1,000 GPU hours.')
+       num_gpus = st.number_input('Number of GPUs/CPUs/TPUs used', value = 16)
+       #st.markdown('This is calculated by multiplying the number of GPUs you used by the training time: '
+        #           'i.e. if you used 100 GPUs for 10 hours, this is equal to 100x10 = 1,000 GPU hours.')
     with col3:
+       training_time = st.number_input('Total training time (in hours)', value = 0.0)
+    with col4:
        provider = st.selectbox('Provider used', providers)
        st.markdown('If you can\'t find your provider here, select "Local/Private Infrastructure".')
-    with col4:
+    with col5:
         if provider != 'Local/Private Infastructure':
             provider_instances = instances['region'][instances['provider'] == provider.lower()].unique().tolist()
             region = st.selectbox('Provider used', provider_instances)
@@ -90,7 +106,7 @@ with st.expander("Calculate the dynamic emissions of your model"):
             carbon_intensity = st.number_input('Carbon intensity of your energy grid, in grams of CO2 per kWh')
             st.markdown('You can consult a resource like the [IEA](https://www.iea.org/countries) or '
                         ' [Electricity Map](https://app.electricitymaps.com/) to get this information.')
-    dynamic_emissions = round(gpu_tdp * training_time * carbon_intensity/1000000)
+    dynamic_emissions = round(gpu_tdp * num_gpus*training_time * carbon_intensity/1000000)
     st.metric(label="Dynamic emissions", value=str(dynamic_emissions)+' kilograms of CO2eq')
     st.markdown('This is roughly equivalent to '+ str(round(dynamic_emissions/kg_per_mile,1)) + ' miles driven in an average US car'
     ' produced in 2021. [(Source: energy.gov)](https://www.energy.gov/eere/vehicles/articles/fotw-1223-january-31-2022-average-carbon-dioxide-emissions-2021-model-year)')
@@ -106,7 +122,7 @@ with st.expander("Calculate the experimental emissions of your model"):
             experimental_emissions = round(gpu_tdp * (experimentation_time) * carbon_intensity/1000000)
             st.metric(label="Experimental emissions", value=str(0.0)+' kilograms of CO2eq')
 
-st.markdown('### Idle Emissions 🌐')
+st.markdown('### Datacenter (Overhead) Emissions 🌐')
 st.markdown('##### These are the emissions produced by generating the electricity needed to power the rest of the infrastructure'
             'used for model training -- the datacenter, network, heating/cooling, storage, etc.')
 with st.expander("Calculate the idle emissions of your model"):
@@ -134,7 +150,7 @@ with st.expander("Calculate the idle emissions of your model"):
 
         else:
             st.markdown('##### Try to find the PUE of your local infrastructure. Otherwise, you can use the industry average, 1.58:')
-            pue = st.number_input('Total number of GPU hours', value = 1.58)
+            pue = st.slider('Total number of GPU hours', value = 1.58)
     else:
         st.markdown('##### The PUE of the datacenter you used is: ')
         st.markdown('#### '+ str(pue))
@@ -145,23 +161,38 @@ st.markdown('### Embodied Emissions 🖥️🔨')
 st.markdown('##### These are the emissions associated with the materials and processes involved in producing'
             ' the computing equipment needed for AI models.')
 with st.expander("Calculate the embodied emissions of your model"):
-        st.markdown('##### These are the trickiest emissions to track down since a lot of the information needed is missing!')
+        st.markdown('These are the trickiest emissions to track down since a lot of the information needed is missing.')
+        st.markdown('##### Based on the number of GPUs and training time you indicated above, we can estimate that your model\'s embodied emissions are approximately: ')
+        hardware_type = TDP['type'][TDP['name'] == hardware].tolist()[0]
+        if hardware_type == 'cpu':
+            embodied_type = embodied_gpu['Value'][embodied_gpu['Ratio']=='Manufacturing emissions per additional CPU (kgCO₂eq)'].tolist()[0]
+        elif hardware_type == 'gpu' or hardware_type == 'tpu':
+            embodied_type = embodied_gpu['Value'][embodied_gpu['Ratio']=='Manufacturing emissions per additionnal GPU Card (kgCO₂eq)'].tolist()[0]
+        embodied_emissions = round(int(embodied_type)*embodied_conversion_factor*num_gpus*training_time/1000,1)
+        st.metric(label="Embodied emissions", value=str(embodied_emissions)+' kilograms of CO2eq')
+        st.markdown('This is a high-level estimate based on an hourly manufacturing emissions conversion factor (linearly ammortised) of 0.0289 [(source)](https://docs.google.com/spreadsheets/d/1DqYgQnEDLQVQm5acMAhLgHLD8xXCG9BIrk-_Nv6jF3k/).')
+
+st.markdown('### Model Information ℹ️')
+st.markdown('##### If you want to share the link to your model code or paper, please do so below! Otherwise, your submission will be anonymous.')
+model_info = st.text_input(label= "Enter a link to your model (optional)")
 
 m = st.markdown("""
 <style>
 div.stButton > button:first-child {
     background-color: rgb(80, 200, 120);
     background-image: none;
-    font-size: 20px;
+    font-size: 25px;
     height: 3em;
+    width: 15em;
 }
 </style>""", unsafe_allow_html=True)
-buttoncol1, cuttoncol2, buttoncol3 = st.columns(3)
-with cuttoncol2:
-    st.button(label="Anonymously share my data!", on_click = lambda *args: write_to_csv(hardware, training_time, provider, carbon_intensity, dynamic_emissions))
+buttoncol1, buttoncol2, buttoncol3 = st.columns(3)
+with buttoncol2:
+    st.button(label="Share my CO2 data!", on_click = lambda *args: write_to_csv(hardware, gpu_tdp, num_gpus, training_time, provider, carbon_intensity, dynamic_emissions, experimentation_time, experimental_emissions, pue, pue_emissions, embodied_type, embodied_emissions, model_info))
 
 st.markdown('### Methodology')
 with st.expander("More information about our Methodology"):
     st.markdown('Building on the work of the [ML CO2 Calculator](https://mlco2.github.io/impact/), this tool allows you to consider'
                 ' other aspects of your model\'s carbon footprint based on the LCA methodology.')
+    st.markdown('We considered all of these aspects when calculating the CO2 emissions of BLOOM 🌸, a 176-billion parameter language model [(see our preprint!)](https://arxiv.org/abs/2211.02001)'')')
     st.image('images/LCA_CO2.png', caption='The LCA methodology - the parts in green are those we focus on.')