Use of model in application

Dockerfile → app/Dockerfile

@@ -1,27 +1,27 @@
-# For more information, please refer to https://aka.ms/vscode-docker-python
-FROM python:3.10-slim
-WORKDIR /usr/src/app
-
-# Keeps Python from generating .pyc files in the container
-ENV PYTHONDONTWRITEBYTECODE=1
-
-# Turns off buffering for easier container logging
-ENV PYTHONUNBUFFERED=1
-
-# Install pip requirements
-COPY requirements.txt .
-RUN python -m pip install -r requirements.txt
-
-COPY . .
-
-# Creates a non-root user with an explicit UID and adds permission to access the /app folder
-# For more info, please refer to https://aka.ms/vscode-docker-python-configure-containers
-RUN adduser -u 5678 --disabled-password --gecos "" appuser && chown -R appuser /usr/src/app
-USER appuser
-
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-# During debugging, this entry point will be overridden. For more information, please refer to https://aka.ms/vscode-docker-python-debug
-ENTRYPOINT ["streamlit", "run", "app/main.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# For more information, please refer to https://aka.ms/vscode-docker-python
+FROM python:3.10-slim
+WORKDIR /usr/src/app
+
+# Keeps Python from generating .pyc files in the container
+ENV PYTHONDONTWRITEBYTECODE=1
+
+# Turns off buffering for easier container logging
+ENV PYTHONUNBUFFERED=1
+
+# Install pip requirements
+COPY requirements.txt .
+RUN python -m pip install -r requirements.txt
+
+COPY . .
+
+# Creates a non-root user with an explicit UID and adds permission to access the /app folder
+# For more info, please refer to https://aka.ms/vscode-docker-python-configure-containers
+RUN adduser -u 5678 --disabled-password --gecos "" appuser && chown -R appuser /usr/src/app
+USER appuser
+
+EXPOSE 8501
+
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+
+# During debugging, this entry point will be overridden. For more information, please refer to https://aka.ms/vscode-docker-python-debug
+ENTRYPOINT ["streamlit", "run", "main.py", "--server.port=8501", "--server.address=0.0.0.0"]

app/main.py

@@ -16,8 +16,7 @@ text = st.text_area("Input text", demo, height=275)
 model_name = st.selectbox(
     "Select the model you want to use below.",
     (
-        "distilbert-base-uncased-finetuned-sst-2-english",
-        "roberta-large-mnli",
+        "ogtega/tweet-toxicity-classifier",
     ),
 )
 
@@ -31,6 +30,7 @@ input = tokenizer(text, return_tensors="tf")
 
 if st.button("Submit", type="primary"):
     results = clf(text)[0]
+    print(results)
     classes = dict(d.values() for d in results)
     # st.write(f"The sentiment is {results}.")
     st.bar_chart(classes)

app/train.py

@@ -4,8 +4,13 @@ import numpy as np
 import tensorflow as tf
 from datasets import load_dataset
 from tensorflow.keras.optimizers import Adam
-from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
+from transformers import (
+    AutoTokenizer,
+    PushToHubCallback,
+    TFAutoModelForSequenceClassification,
+)
 
+output_dir = "out/model"
 checkpoint_path = "out/cp.ckpt"
 
 labels = ["toxic", "severe_toxic", "obscene", "threat", "insult", "identity_hate"]
@@ -53,6 +58,11 @@ cp_callback = tf.keras.callbacks.ModelCheckpoint(
     filepath=checkpoint_path, save_weights_only=True, verbose=1
 )
 
+push_to_hub_callback = PushToHubCallback(
+    output_dir=output_dir,
+    tokenizer=tokenizer,
+    hub_model_id="ogtega/tweet-toxicity-classifier",
+)
+
 model.compile(optimizer=Adam(3e-5), loss="categorical_crossentropy")
-model.fit(tf_dataset, callbacks=[cp_callback])
-model.save('out/model')
+model.fit(tf_dataset, callbacks=[cp_callback, push_to_hub_callback])

tflow

@@ -0,0 +1,14 @@
+mkdir -p $HOME/dockerx/app
+cp app $HOME/dockerx -r
+sudo docker run \
+      -it \
+      --network=host \
+      --device=/dev/kfd \
+      --device=/dev/dri \
+      --ipc=host \
+      --shm-size 16G \
+      --group-add video \
+      --cap-add=SYS_PTRACE \
+      --security-opt seccomp=unconfined \
+      -v $HOME/dockerx:/dockerx \
+      rocm/tensorflow:latest